Authors: Rui Zhao, Haofeng Hu, Zhenhai Gao, Jiaqiao Liu, Gao Fei
Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving, yet their reliance on implicit parametric knowledge limits generalization in long-tail scenarios. While Retrieval-Augmented Generation (RAG) offers a solution by accessing external expert priors, standard visual retrieval suffers from high latency and semantic ambiguity. To address these challenges, we propose \textbf{VLADriver-RAG}, a framework that grounds planning in explicit, structure-aware historical knowledge. Specifically, we abstract sensory inputs into spatiotemporal semantic graphs via a \textit{Visual-to-Scenario} mechanism, effectively filtering visual noise. To ensure retrieval relevance, we employ a \textit{Scenario-Aligned Embedding Model} that utilizes Graph-DTW metric alignment to prioritize intrinsic topological consistency over superficial visual similarity. These retrieved priors are then fused within a query-based VLA backbone to synthesize precise, disentangled trajectories. Extensive experiments on the Bench2Drive benchmark establish a new state-of-the-art, achieving a Driving Score of 89.12.
Authors: Pamela Barboza, V\'ictor Castelli, Bel\'en Pereira, Ricardo Grando, Bruna de Vargas, Augusto Calfani
Abstract: Visual perception plays a central role in competitive robotics, where environmental variations can directly affect real-time detection performance. The related literature on transformer-based detectors lack information regarding the impact of backbone scale and environmental settings on model performance. This work presents a comparative evaluation of RT-DETR for detecting round objects under environmental and hyperparameter variations relevant to competitive robotics. Four ResNet backbones (ResNet18, ResNet34, ResNet50, and ResNet101) were compared using dropout rates, analyzing their effect on confidence and accuracy. All models were trained under the same configuration and evaluated under changes in lighting and background contrast. Environmental conditions primarily impact prediction confidence, while inference latency remains largely unaffected and classification accuracy stays consistently high, approaching or above 1.00 in most cases. Two distinct behaviors were observed. Under illumination variation, ResNet50 achieves the best trade-off, combining near-perfect accuracy, confidence values up to approximately 0.869 and latency around 0.058-0.059 ms. Under background variation, ResNet34 provides the most balanced performance, reaching near-perfect accuracy and higher confidence values up to approximately 0.887. These results indicate that the optimal architecture depends on the type of environmental variation, with intermediate-depth models offering the best balance between performance and efficiency.
Authors: Yuriel Ryan, Hei Man Ip, Adriel Kuek, Paul Pu Liang, Roy Ka-Wei Lee
Abstract: Current vision language models face hallucination and robustness issues against ambiguous or corrupted modalities. We hypothesize that these issues can be addressed by exploiting the shared information between modalities to compensate for the impaired one. To this end, we analyze multimodal interactions -- redundant (shared), unique (exclusive), and synergistic (emergent) task-relevant information provided by the modalities -- to determine their impacts on model reliability. Specifically, amplifying redundant interactions would increase this exploitable shared information to resolve these issues; yet, modern instruction datasets often eliminate redundancies to prioritize visual grounding. We bridge this gap through a self-captioning workflow featuring a \textsc{Multimodal Interaction Gate}: a mechanism to convert unique interactions into redundant interactions. Our findings suggest that increasing redundancy can reduce visual induced errors by 38.3\% and improve consistency by 16.8\%.
Authors: Zi-Yi Jia, Zi-Jian Cheng, Xin-Yue Zhang, Kun-Yang Yu, Zhi Zhou, Yu-Feng Li, Lan-Zhe Guo
Abstract: Multi-model learning has attracted great attention in visual-text tasks. However, visual-tabular data, which plays a pivotal role in high-stakes domains like healthcare and industry, remains underexplored. In this paper, we introduce \textit{VT-Bench}, the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks. VT-Bench aggregates 14 datasets across 9 domains (medical-centric, while covering pets, media, and transportation) with over 756K samples. We evaluate 23 representative models, including unimodal experts, specialized visual-tabular models, general-purpose vision-language models (VLMs), and tool-augmented methods, highlighting substantial challenges of visual-tabular learning. We believe VT-Bench will stimulate the community to build more powerful multi-modal vision-tabular foundation models. Benchmark: https://github.com/Ziyi-Jia990/VT-Bench
Authors: Junyi Hu, Qiji Zhou, Lei Zhang, Yue Zhang
Abstract: Zero-shot recognition aims to classify an image by selecting the most compatible label description from a set of candidate classes without any task-specific supervision. In fine-grained settings, however, the relevant evidence often lies in localized parts, attributes, or textures rather than in the full image, making whole-image alignment suboptimal. Recent localized visual-text alignment methods address this by comparing class descriptions with multiple image regions, but they typically rely on large sets of random or redundant crops, increasing inference cost and introducing many highly redundant or weakly relevant candidates. Moreover, introducing semantic guidance too early can create an error-amplifying feedback process in which inaccurate intermediate predictions bias later localization and reinforce subsequent mistakes; we refer to this failure mode as the prediction loop. We propose LAGO (LAnguage-Guided adaptive Object-region focus), a framework for efficient and robust zero-shot localized visual-text alignment. LAGO first performs class-agnostic object-centric candidate discovery to obtain a stable visual initialization, and then applies adaptive language-guided refinement with the strength of semantic guidance controlled by intermediate confidence. It further combines object-level, contextual, and full-image evidence through an effective object-context dual-channel aggregation strategy. Extensive experiments show that LAGO consistently achieves state-of-the-art performance on standard zero-shot benchmarks and challenging distribution-shift settings, while requiring substantially fewer candidate regions at inference time.
Authors: Haopeng Jin, Hongzhu Yi, Wenlong Zhao, Jinwen Luo, Shani Ye, Zhenyu Guan, Shiquan Dong, Tiankun Yang, Tao Yu
Abstract: Long-video understanding with multimodal language models suffers from three compounding bottlenecks: heavy decode cost to obtain dense RGB frames, quadratic token growth with frame count, and weak motion perception under sparse keyframe sampling. We present HY-Himmel, a hierarchical video-language framework that allocates semantic and motion capacity separately. A small set of sparse anchor I-frames is routed to the expensive host ViT to ground object identity and scene layout, while the far denser inter-frame intervals are encoded by a lightweight compressed-domain tri-stream adapter that distils motion evidence from motion-vector maps, residual maps, and I-frame context into aligned motion tokens. These tokens are injected into the LLM via a differentiable placeholder mechanism after a dedicated Stage-1 contrastive alignment that places the motion representation in a geometry compatible with the frozen visual backbone. On Video-MME, HY-Himmel surpasses the dense 32-frame baseline by +2.3 pp (61.2 to 63.5%) while using 3.6x fewer context tokens. Extensive ablations over stream composition, motion encoder family, fusion mode, alignment objective, anchor count, LoRA rank, and video duration confirm that the full tri-stream is necessary and sufficient for the observed gains.
Authors: Girmaw Abebe Tadesse, Titien Bartette, Andrew Hassanali, Allen Kim, Jonathan Chemla, Andrew Zolli, Yves Ubelmann, Caleb Robinson, Inbal Becker-Reshef, Juan Lavista Ferres
Abstract: Monitoring archaeological sites at scale is vital for protecting cultural heritage, yet pinpointing when disturbances occur remains difficult because visual cues are subtle and ground-truth data are sparse. We introduce WATCH, a framework for month-level change-event localization over PlanetScope satellite mosaics (2017-2024, 4.7 m/px) that supports three complementary scoring approaches: (i) Temporal Embedding Distance (TED), a training-free method that scores month-to-month deviations from a local temporal reference; (ii) Self-Supervised Change Detection (SSCD), an ensemble of reconstruction, forecasting, and latent-novelty signals; and (iii) a Weakly Supervised (WS) temporal localization model trained with sparse event-month labels. We benchmark WATCH on 1,943 archaeological sites in Afghanistan using embeddings from six foundation models (CLIP, GeoRSCLIP, SatMAE, Prithvi-EO-2.0, DINOv3, and Satlas-Pretrain) alongside a handcrafted spectral and texture baseline, and assess cross-regional generalization on sites in Syria, Turkey, Pakistan, and Egypt. The unsupervised approaches (TED, SSCD) consistently outperform the weakly supervised alternative. TED with SatMAE achieves the highest exact-month recall (55% at m=0), while TED with GeoRSCLIP, CLIP, or Satlas-Pretrain reaches 92.5% within a three-month tolerance (m=3). Handcrafted features remain competitive for exact-month detection under weak supervision. Our directional margin analysis reveals systematic temporal biases: SSCD paired with GeoRSCLIP or Prithvi-EO-2.0 exhibits the strongest early-warning profile, detecting anomalies before the recorded event, while TED favors confirmation-oriented detection after a change has materialized. These results show that satellite imagery combined with foundation-model embeddings enables scalable, decision-relevant heritage monitoring. Code: https://github.com/microsoft/WATCH
Authors: Hussain Alasmawi
Abstract: Tumor segmentation in whole-body PET/CT imaging is crucial for precise disease evaluation and treatment planning. However, it remains challenging due to variability in lesion size, contrast, and anatomical distribution. Relying on manual segmentation makes the process time-consuming and prone to intra- and inter-observer variability. This work presents a whole-body tumor segmentation method developed for the AutoPET III challenge, where the goal is to build models that generalize across tracers and multi-center data. We employ the nnU-Net framework with a ResNet-based encoder as our baseline and systematically investigate the impact of training strategies, including intensity normalization, batch dice optimization, and data augmentation using CraveMix. Our experiments show that these strategies significantly influence model performance, particularly in reducing false positives and improving robustness to lesion variability. The best-performing configuration achieves a Dice score of up to 0.80 on the preliminary test phase, and our method ranked third in the AutoPET III challenge. The code is publicly available here.
Authors: Liwei Cheng, Zirui Song, Shibo Feng, Lunjie Zhou, Yixuan Guan, Dayan Guan
Abstract: Text-in-image editing has become a key capability for visual content creation, yet existing benchmarks remain overwhelmingly English-centric and often conflate visual plausibility with semantic correctness. We introduce MULTITEXTEDIT, a controlled benchmark of 3,600 instances spanning 12 typologically diverse languages, 5 visual domains, and 7 editing operations. Language variants of each instance share a common visual base and are paired with a human-edited reference and region masks, isolating the language variable for cross-lingual comparison. To capture script-level errors that coarse text-matching metrics miss, such as missing diacritics, reversed RTL order, and mixed-script renderings, we introduce a language fidelity (LSF) metric scored by a two-stage LVM protocol that first traces the edited target text and then judges it in isolation, reaching a quadratic-weighted \k{appa} of 0.76 against native-speaker annotators. Evaluating 12 open-source and proprietary systems with LSF alongside standard semantic and mask-aware pixel metrics, we find pronounced cross-lingual degradation for every model, largest on Hebrew and Arabic and smallest on Dutch and Spanish, and concentrated in text accuracy and script fidelity rather than in coarse structural dimensions. We also uncover a pervasive semantic and pixel mismatch, where outputs preserve global layout and background fidelity yet distort script-specific forms.
Authors: Fatma Betul Buyuk, Gozde Karatas Baydogmus, Ali Buldu, Ayaulym Tulendiyeva, Zhuldyz Baizhumanova
Abstract: The increasing availability of advanced image editing tools has led to a significant rise in manipulated digital content, posing serious challenges for digital forensics and information security. This study presents a transfer learning-based framework for digital image forgery detection that integrates compression-aware feature enhancement with deep convolutional neural network (CNN) architectures. The proposed approach introduces a hybrid input representation that combines RGB images with compression difference-based features (FDIFF), explicitly highlighting subtle manipulation artifacts that are often difficult to detect. In addition, a model-specific adaptive threshold optimization strategy based on the Youden Index is employed to improve classification reliability by achieving a better balance between true positive and false positive rates. Experiments conducted on the CASIA v2.0 dataset using multiple pretrained CNN architectures, including DenseNet121, VGG16, ResNet50, EfficientNetB0, MobileNet, and InceptionV3, demonstrate the effectiveness and robustness of the proposed framework. The models are evaluated using comprehensive performance metrics such as accuracy, precision, recall, F1-score, Matthews correlation coefficient (MCC), and area under the ROC curve (AUC). The results show that DenseNet121 achieves the highest accuracy and AUC, while ResNet50 provides the most balanced and reliable predictions with the highest MCC. The findings emphasize that relying solely on accuracy is insufficient for forensic applications, where minimizing false negatives is critical. Overall, the proposed framework improves the visibility of manipulation artifacts and enhances classification robustness, making it suitable for real-world digital image forgery detection scenarios.
Authors: Savitha N J, Lata B T
Abstract: Automated culprit identification in surveillance systems is a critical task that requires high accuracy along with computational efficiency for real-time deployment. In this paper, an optimized deep learning framework is proposed using a lightweight MobileNet architecture integrated with channel and spatial attention mechanisms. The proposed model enhances feature representation by selectively focusing on the most discriminative regions while suppressing irrelevant background information, thereby improving identification performance. The framework incorporates efficient preprocessing, attention based feature refinement, and a robust classification strategy optimized using the Adam Optimizer. Experiments were conducted on benchmark face recognition datasets, including Labelled Faces in the Wild (LFW), CASIA-WebFace, and a subset of VGGFace2, under realistic conditions with variations in illumination, pose, and occlusion. The results demonstrate that the proposed model achieves a high classification accuracy of 97.8%, outperforming conventional models such as baseline CNN, ResNet, and standard MobileNet. The confusion matrix analysis indicates strong class-wise discrimination with minimal misclassification, while ROC-AUC evaluation confirms robust performance across all classes. Additionally, the proposed approach maintains low computational complexity and reduced inference time, making it suitable for real-time surveillance and edge-based applications.
Authors: Daniel Saragih
Abstract: Anatomical mesh segmentation requires models that operate directly on irregular surface geometry while remaining robust to arbitrary patient pose and mesh resolution variation. Existing task-specific mesh and point-cloud methods are not equivariant, and can degrade sharply under test-time perturbation, for example dropping by 25-26 IoU points on intraoral scan segmentation at $40^\circ$ tilt. We present EAMS, an Equivariant Anatomical Mesh Segmentor built on Equivariant Mesh Neural Networks (EMNN), and evaluate it across four clinically distinct tasks spanning edge-, vertex-, and face-level supervision. We combine intrinsic mesh descriptors with anatomy-aware priors, including PCA-derived frames for dental arches and liver surfaces, and augment message passing to provide lightweight global context. Across intracranial aneurysm and intraoral segmentation, EAMS variants are competitive with specialized baselines on unperturbed inputs while remaining stable under geometric perturbations, and on liver surfaces they expose a favorable trade-off between canonical-pose accuracy and rotation robustness. These results show that a lightweight ($<2$M parameters) equivariant framework can deliver robust anatomical mesh segmentation across diverse supervision types without task-specific architectures.
Authors: Honggui Li, Zhengyang Zhang, Dingtai Li, Sinan Chen, Nahid Md Lokman Hossain, Xinfeng Xu, Yinlu Qin, Ruobing Wang, Hantao Lu, Yuting Feng, Maria Trocan, Dimitri Galayko, Amara Amara, Mohamad Sawan
Abstract: The generalization performance (GP) of deep learning-based arbitrary-scale image super-resolution (ASISR) methods is subject to limited training datasets and unlimited testing datasets. It is vitally significant to enhance the GP of the pretrained ASISR models by making full use of the testing samples. The ASISR models usually employ an open-loop architecture from low-resolution (LR) images to super-resolution (SR) images. The degradation model from SR samples to LR samples is known bicubic down-sampling for the classical ASISR, is supposed down-sampling with additive random noise for the blind ASISR, and is learnable for the real-world ASISR. Combining the ASISR and degradation models, it is potentially possible to adopt a closed-loop architecture based on the automatic control theory for strengthening the GP of the ASISR methods. Therefore, this paper proposes a closed-loop architecture, circular ASISR (CASISR), to lift the capability of image reconstruction. A mathematical nonlinear loop equation is established to describe the CASISR, the reasonability of the CASISR is proven by conditional probability theory, and the stability of the CASISR is proven by Taylor series approximation. The first-order and second-order absolute difference images are defined to compare the image reconstruction performance of the ASISR and the CASISR methods. Comprehensive simulation experiments show that the proposed CASISR approach outperforms the eight state-of-the-art ASISR approaches in the quality of image reconstruction. Especially, the proposed CASISR is extraordinarily suitable for fractional SR scale factors and is extremely effective for text and stripe images with drastically changed edges.
Authors: Archishman Ghosh, Abhinaba Roy, Dorien Herremans
Abstract: While significant progress has been made in Video Question Answering and cross-modal understanding, causal reasoning about how visual dynamics drive musical structure in music videos remains under-explored. We introduce KARMA-MV, a large-scale multiple-choice QA dataset derived from 2,682 YouTube music videos, designed to test models' ability to integrate temporal audio-visual cues and reason about visual-to-musical influence across reasoning, prediction, and counterfactual questions. Unlike traditional datasets requiring manual annotation, KARMA-MV leverages LLM reasoning for scalable generation and validation, yielding 37,737 MCQs. We propose a causal knowledge graph (CKG) approach that augments vision-language models (VLMs) with structured retrieval of cross-modal dependencies. Experiments on state-of-the-art VLMs and LLMs show consistent gains from CKG grounding -- especially for smaller models -- establishing the value of explicit causal structure for music-video reasoning. KARMA-MV provides a new benchmark for advancing causal audio-visual understanding beyond correlation.
Authors: Weicai Yan, Xinhua Ma, Wang Lin, Tao Jin
Abstract: Parameter-efficient fine-tuning methods introduce a small number of training parameters, enabling pre-trained models to adapt rapidly to new data distributions. While these methods have shown promising results, they exhibit notable limitations. First, most existing methods operate in the signal space domain, which results in substantial information redundancy. Second, most existing methods utilize fixed prompts or adaptation layers, failing to fully account for the multi-scale characteristics of signals. To address these challenges, we propose the Multi-Scale Frequency Adapter (FreqAdapter), which integrates textual information and performs multi-scale fine-tuning of signals in the frequency domain. Additionally, we introduce a multi-scale adaptation strategy to optimize receptive fields across different frequency ranges, further enhancing the model's representational capacity. Extensive experiments on multimodal models, including CLIP and LLaVA, demonstrate that FreqAdapter significantly improves both performance and efficiency. FreqAdapter improves performance with minimal cost and fast convergence within one epoch. Code is available at https://github.com/Kelvin-ywc/FreqAdapter.
Authors: Bo Ye, Kai Gan, Tong Wei, Min-Ling Zhang
Abstract: Generalized Category Discovery (GCD) seeks to identify novel categories from unlabeled data while retaining the classification ability of seen categories. Prior GCD methods commonly leverage transferable representations from pre-trained models, adapting to downstream datasets via partial fine-tuning (updating only the final ViT block) and visual prompt tuning (appending learnable vectors to inputs). However, conventional partial fine-tuning offers limited flexibility, as it fails to adapt the entire model; meanwhile, visual prompt tuning is prone to overfitting, due to its sensitivity to initialization and inherently constrained capacity. To address these limitations, we propose LAGCD, a simple yet effective GCD approach that embeds a residual linear adapter into each ViT block. From the perspective of feature sparsity, we systematically show that non-linearity in conventional adapters impairs performance, whereas our linear adapter enhances it by enabling more flexible model capacity. We further introduce an auxiliary distribution alignment loss to mitigate the negative impact of biased predictions between seen and novel categories. Extensive experiments on both generic and fine-grained datasets confirm that LAGCD consistently improves performance over many sophisticated baselines. The source code is available at https://github.com/yebo0216best/LAGCD
Authors: Mathis Immertreu, Fitim Abdullahu, Thomas Kinfe, Helmut Grabner, Patrick Krauss, Achim Schilling
Abstract: Human attention is the gateway to conscious perception, memory and decision-making. However, its role in modern transformer models remains largely unexplored. As these systems increasingly influence what people see, prefer and buy, the question arises as to whether they encode principles of human interest or merely exploit large-scale correlations. Addressing this issue is crucial for understanding cognition and ensuring the responsible use of AI in communication and marketing. In order to address this issue, the concept of visual interest was examined within the multimodal vision-language-model Qwen3-VL-8B, using a pre-defined Common Interestingness (CI) score derived from large-scale human engagement data on the photo-sharing platform Flickr. Here, we analyzed internal representations across vision and language components using methods from the neurosciences. Our analyses revealed that CI information is linearly decodable from final-layer embeddings, indicating that it is aligned with human-derived measures of visual interestingness. Dimensionality reduction and Generalized Discrimination Value (GDV) analyses demonstrate that CI-related hidden representations emerge in intermediate vision transformer layers and becomes progressively more distinguishable across language model layers. Concept vectors derived using geometric, probe, and Sparse Auto-Encoder based methods converge in higher layers, as confirmed by representational similarity analysis. This indicates a robust and structured encoding of visual interestingness without explicit supervision. Future work will seek to identify shared computational principles linking human brain dynamics and transformer architectures, with the ultimate goal of uncovering the organizing mechanisms that give rise to attention and interest in both biological and artificial systems.
Authors: Maria Stoica, Abdelrahman Hekal, Alessio Lomuscio
Abstract: Reliable out-of-distribution (OOD) detection is a critical requirement for the safe deployment of machine learning systems. Despite recent progress, state-of-the-art OOD detectors are highly susceptible to adversarial attacks, which undermines their trustworthiness in automated systems. To address this vulnerability, we apply median smoothing to baseline OOD detection scores, balancing clean and adversarial accuracies. Our key insight is that the noisy samples generated for median smoothing can be repurposed to quantify the local instability of the base score. We observe that OOD samples exhibit higher instability under perturbation. Based on this, we propose ROSS, a novel and robust post-hoc OOD detector that leverages the instability of baseline scores to further distinguish between in-distribution (ID) and OOD samples. ROSS achieves symmetric robustness, performing strongly against both score-minimising and score-maximising attacks, unlike prior work. This symmetric defence leads to state-of-the-art robustness, outperforming prior methods by up to 40 AUROC points. We demonstrate ROSS's effectiveness on extensive experiments across CIFAR-10, CIFAR-100, and ImageNet. Code is available at: https://github.com/Abdu-Hekal/ROSS.
Authors: Youssef Saied, Fran\c{c}ois Fleuret
Abstract: Normalization Equivariance (NE), equivariance to global contrast and brightness transforms, improves robustness to distribution shift in image-to-image prediction. Existing methods enforce this prior by constraining internal layers to NE-compatible families, limiting compatibility with standard components such as attention and LayerNorm, and adding runtime cost. We characterize the full NE function class: a function is NE if and only if it admits a normalize-process-denormalize factorization. This turns exact NE enforcement, for the ideal wrapper, from an internal architectural constraint into an input-output parameterization problem, allowing a parameter-free wrapper (WNE) to enforce NE around any backbone, including transformers. In a single-noise mismatch diagnostic for blind denoising, the wrapper improves CNN and transformer robustness with no measurable GPU overhead; architectural NE baselines incur up to a 1.6x slowdown.
Authors: Alain P. Ndigande, Josiah Wiggins, Sedat Ozer
Abstract: Recent natural disasters have highlighted the urgent need for efficient data-driven approaches to disaster management. Machine learning (ML) and deep learning (DL) techniques have shown considerable promise in enhancing the key phases of disaster management including mitigation, preparedness, detection, response, and recovery. A critical enabler of successful ML or DL based applications in remote sensing, however, is the accessibility and quality of annotated datasets. With the growing availability of high-resolution imagery from unmanned aerial vehicles (UAVs) and satellites, computer vision and remote sensing algorithms have become essential tools for rapid detection, situational assessment, and decision-making in disaster scenarios. This survey provides a comprehensive overview of publicly available image-based datasets relevant to ML/DL-based disaster management pipelines. Emphasis is placed on datasets that support computer vision and remote sensing tasks across all phases of disaster events including pre-disaster, during, and post-disaster. The goal of this work is to serve as a centralized reference for researchers and practitioners seeking high-quality datasets for rapid development and deployment of remote sensing-driven disaster response solutions.
Authors: Yingxue Xu, Zhengyu Zhang, Xiuming Zhang, Mengwei Xu, Fengtao Zhou, Yihui Wang, Jiabo Ma, Yi Xin, Danyi Li, Chengyu Lu, Zhijian Cen, Ying Tan, Qingbing Yao, Qi Wang, Zizhao Gao, Yong Zhang, Jingjing Chen, Feifei Liu, Qian Xu, Yi Dai, Hongxuan Tan, Cheng Jin, Huajun Zhou, Zhengrui Guo, Ling Liang, Hongyi Wang, Yingcong Chen, Xi Wang, Zhenhui Li, Ronald Cheong Kin Chan, Ning Mao, Muyan Cai, Zhe Wang, Li Liang, Hao Chen
Abstract: Pathology foundation models have shown strong retrospective performance, but whether such systems can support clinically relevant use remains unclear. This challenge is particularly important in breast cancer, where pathological assessment serves as the gold standard for diagnosis and guides treatment planning, surgical decision-making and risk stratification across pre-, intra- and post-operative stages. Here we present \textbf{BRAVE}, a breast-adaptive pathology foundation model developed and evaluated using a total resource of 101,638 breast whole-slide images from 32 sources across Asia, Europe and North America. We assessed BRAVE across 34 tasks in 82 cohorts spanning pre-operative biopsy, intra-operative frozen section and post-operative resection, using an evidence chain comprising retrospective benchmarking, clinically challenging scenarios, workflow-oriented clinical impact simulations, prospective observational validation with the thresholds locked in the retrospective cohorts and crossover pathologist-AI interaction studies. Across these settings, BRAVE supported practical roles in the clinical workflow, including safe exclusion of low-risk cases from routine review, AI-assisted second-review rescue of initially missed positives and prioritization of cases for further assessment. In prospective validation across three centres, BRAVE excluded 76.9% of negative biopsy cases (NPV 0.953) and 70.1% of negative frozen-section cases (NPV 0.973), and triaged 78.8% of post-operative subtyping cases as high-confidence clear-cut cases (NPV 1.000). In reader studies, AI assistance improved balanced accuracy from 88.5% to 95.1% (OR 3.14, P<0.001), with better efficiency, confidence and inter-rater agreement. BRAVE-derived scores also independently predicted disease-free survival (adjusted HR 4.79, P<0.001) and overall survival (adjusted HR 8.14, P<0.001).
Authors: Sanaz Karimijafarbigloo, Armin Khosravi, Alireza Kheyrkhah, Reza Azad, Mauricio Reyes, Dorit Merhof
Abstract: Multi-rater medical image segmentation captures the inherent ambiguity of clinical interpretation, where diagnostic boundaries vary across experts and imaging devices. Existing approaches often reduce this diversity to consensus labels or treat rater differences as noise, resulting in overconfident and poorly calibrated models. We propose a harmonized probabilistic framework that disentangles acquisition artifacts from genuine annotator variability through adaptive feature conditioning and frequency-domain personalization. A lightweight Harmonizer Network implicitly models scanner-specific artifacts and performs dynamic feature modulation to standardize latent representations, ensuring that uncertainty reflects anatomy rather than noise. To represent rater-specific styles, we introduce a novel High-Frequency Prompt Modules that operate in the spectral domain to encode annotator-dependent boundary precision and textural sensitivity. These prompts adaptively modulate harmonized features to produce personalized yet anatomically consistent segmentations. Furthermore, a Generalized Energy Distance based regularization aligns the generative distribution with empirical annotation variability, promoting diversity where experts disagree and consensus where they converge. Experiments on LIDC-IDRI and NPC-170 show SOTA aggregated and individualized segmentation, with notable GED reductions and improved Dice scores, especially on noisy cases. Beyond accuracy, the model exhibits clinically meaningful uncertainty. Confidence rises in agreement regions and declines in ambiguous areas, supporting its use as a reliable and interpretable tool for multi-expert clinical workflows.
Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green
Abstract: Manual pruning of radiata pine, a species of major economic importance to New Zealand forestry, is hazardous, labour-intensive, and increasingly constrained by workforce shortages. Existing autonomous pruning platforms typically rely on expensive sensors such as LiDAR and are limited to thick branches, which restricts their wider adoption. This paper investigates whether a single low-cost stereo camera mounted on a drone can provide sufficiently accurate branch detection and three-dimensional positioning to support autonomous pruning of branches as thin as 10 mm, thereby removing the need for auxiliary depth sensors. The proposed pipeline comprises two stages: branch segmentation and depth estimation. For segmentation, Mask R-CNN variants and the YOLOv8 and YOLOv9 families are compared on a custom dataset of 71 stereo image pairs captured with a ZED Mini camera; YOLOv8 and YOLOv9 are selected as representative state-of-the-art real-time segmentors at the time of data collection, and the framework is designed to remain compatible with newer YOLO releases. For depth estimation, a traditional method (SGBM with WLS filtering) and deep-learning-based methods (PSMNet, ACVNet, GWCNet, MobileStereoNet, RAFT-Stereo, and NeRF-Supervised Deep Stereo) are evaluated, including cross-dataset fine-tuning experiments that expose the domain gap between urban driving benchmarks and natural forestry scenes. The main novelty of this work lies in coupling stereo segmentation with a centroid-based triangulation algorithm and Median-Absolute-Deviation outlier rejection that converts a segmentation mask and disparity map into a single robust branch-to-camera distance, addressing the challenges of sparse texture, thin structures, and noisy disparity values typical of forest scenes. Qualitative evaluations at distances of 1-2 m show that the learning-based stereo methods produce more coherent depth es...
Authors: Sangwu Park, Wonjoong Kim, Yeonjun In, Sein Kim, Hongseok Kang, Chanyoung Park
Abstract: Visual Foresight VLA (VF-VLA) has become a prominent architectural choice in the recent VLA due to its impressive performance. Nevertheless, the inherent design of VF-VLA makes it particularly vulnerable to out-of-distribution (OOD) shifts. Because the quality of action directly depends on the accuracy of the predicted future visual information, OOD conditions affect both stages at once. To address this vulnerability, we propose Test-Time Training Visual Foresight VLA ($T^3$VF), a test-time training approach motivated by the observation that the predicted future image and its subsequent observation form a natural supervision pair. To further address the practical challenges that arise from indiscriminate test-time updates, we introduce an adaptive update filtering mechanism. Empirically, $T^3$VF mitigates the OOD vulnerability of VF-VLA at a modest additional inference cost, without requiring any architectural modification or auxiliary modules.
Authors: Sarah Binta Alam Shoilee, Victor de Boer, Jacco van Ossenbruggen, Susan Leg\^ene
Abstract: Handwritten archival tables contain rich historical information, yet transforming them into structured representations, such as Knowledge Graphs, requires integrating table structure recognition, handwriting recognition, and semantic interpretation - a complex multimodal process. End-to-end AI implementations can obscure these steps, resulting in opaque algorithmic operations that hinder human oversight, critical assessment, and trust. To address this, we present a modular, provenance-aware pipeline to convert handwritten tabular images into KGs supporting human-AI collaboration. The pipeline decomposes the workflow into three stages - table reconstruction, information extraction, and KG construction - while exposing intermediate representations for inspection, evaluation, and correction. A key contribution of our approach is the systematic integration of data provenance at every stage, ensuring that all extracted entities and literals remain traceable to their visual and textual origins. The proposed pipeline is demonstrated through a number of experiments on real-world archival material concerning military careers. The results across three different table reconstruction variants highlight the importance of modularisation. By coupling modularity with data provenance, our work advances transparent and collaboratively controllable image-to-KG pipelines for complex historical data.
Authors: Sarra Arab, Anfal Achouri, Seif Eddine Bouziane
Abstract: The rapid proliferation of AI-generated images (AIGI) presents a significant challenge to digital information integrity. While human observers and existing detection models struggle to keep pace with the increasing sophistication of generative models, the need for robust, real-time detection systems has become critical. This paper introduces SPECTRA-Net, a scalable pipeline for explainable, cross-domain tensor representations for AIGI detection. Our approach leverages a multi-view representation of images, combining global semantic features from a Vision Foundation Model (VFM), spectral analysis, local patch-based anomaly detection, and statistical descriptors. By fusing these complementary data streams, SPECTRA-Net achieves state-of-the-art performance in both in-domain and cross-domain settings, demonstrating high accuracy and generalization capabilities across a wide range of challenging datasets, including WildFake, Chameleon, and RRDataset. The proposed pipeline not only provides a robust solution for AIGI detection but also offers explainability through artifact localization, paving the way for more trustworthy and reliable content verification in real-world applications.
Authors: Farhana Yasmin, Mahade Hasan, Haipeng Liu, Amjad Ali, Ghulam Muhammad, Yu Xue
Abstract: Cardiac magnetic resonance (CMR) segmentation underpins quantitative assessment of ventricular structure and function, yet reliable delineation remains difficult due to low tissue contrast, fuzzy boundaries, and inter scan variability. We present CardiacNAS, an evolutionary neural architecture search (NAS) framework that couples a UNet like supernet with a cardiac aware search space spanning depth width, kernel size, filter size, attention, fusion, activation, dropout, and residual scaling. The search is explicitly resource aware, jointly optimizing dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (HD95) versus model size and floating point operations (FLOPs) under fixed compute budgets. Candidate architectures are instantiated from the supernet, trained with proxy budgets, and evolved through crossover, mutation, and elitist selection. We evaluate on the ACDC dataset and compare against six state of the art methods, using qualitative comparisons, learning curve analyses, and design factor correlation studies. The resulting model attains 93.22% average DSC and 4.73 mm HD95 with 3.58M parameters and 14.56 GFLOPs, demonstrating a favorable accuracy efficiency trade off. Analyses indicate that searched attention and fusion choices, together with residual scaling, contribute to improved boundary fidelity and stability. CardiacNAS offers a principled, resource aware approach to deployable CMR segmentation with transparent reporting of architectural complexity and compute budgets.
Authors: Bibin Wilson
Abstract: Self-supervised learning (SSL) has transformed representation learning for large models, yet remains unexplored for microcontroller (MCU)-class models with fewer than 500K parameters. We identify three obstacles at this scale -- projection head dominance, representation bottleneck, and augmentation sensitivity -- and propose Capacity-Aware Distilled Self-Supervised Learning (CA-DSSL), a teacher-guided framework that overcomes them without labels or text supervision. CA-DSSL combines asymmetric distillation from a frozen DINO ViT-S/16 teacher, multi-scale feature distillation for spatial representations, and a progressive augmentation curriculum. On a MobileNetV2-0.35 backbone (396K parameters) pretrained on CIFAR-100, CA-DSSL reaches 62.7 0.5% linear-probe accuracy (3-seed mean) -- surpassing SimCLR-Tiny by 18 pp, matching SEED (61.7%) with 10 fewer projection parameters (426K vs. 3.15M), and reaching 94.0% of a supervised upper bound. Standard SSL methods (BYOL-Tiny, DINO-Tiny) collapse entirely at this scale. On Pascal VOC detection, CA-DSSL achieves 2.3 the mAP of random initialization and +3 pp over SEED, though SimCLR-Tiny matches CA-DSSL on detection mAP. The deployed backbone occupies 378 KB (INT8) with no inference overhead from pretraining. Preliminary ImageNet-100 experiments reveal that CA-DSSL's advantage is specific to small-data regimes; scaling to ImageNet-1K is discussed as future work.
Authors: Harshvardhan Saini, Samyak Jha, Yiming Tang, Dianbo Liu
Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input. We investigate the root causes of these failure modes with a mechanistic analysis focusing on the decoder-based VLMs. We trace these failure modes to a geometric over-alignment: to bridge the modality gap required by attention mechanisms, decoder-based VLMs over-align visual embeddings with the text manifold, injecting a statistical linguistic bias that systematically overshadows fine-grained visual evidence. While prior work either aggressively closes this gap or suppresses hallucinations through expensive black-box decoding strategies, none addresses the underlying geometric cause. We provide the first quantitative characterization of this over-alignment, demonstrating that linguistic bias concentrates in the top principal components of a universal, dataset-agnostic text subspace. Building on this insight, we propose two complementary remedies: a training-free inference strategy and a bias-aware fine-tuning paradigm, both of which explicitly project out this subspace from visual representations. Our methods significantly reduce hallucinations across POPE, CHAIR, and AMBER benchmarks, and improve CLAIR scores on long-form captioning tasks, with the training-free variant adding no computational overhead over the base model.
Authors: Pravin Kumar, Mritunjay Shall Peelam, Ramakant Kumar, Sanjay Kumar, Vinay Chamola
Abstract: Railway track intrusions pose a critical safety challenge for Indian Railways, encompassing wildlife incursions and deliberate malicious obstructions. The December 2025 collision in Assam, in which seven elephants were killed by the Rajdhani Express, underscores the urgency of effective real-time detection. Existing solutions such as the optical fiber-based Gajraj system suffer from prohibitive costs (\$1000/km) and high false alarm rates, limiting deployment to only 20 of India's 101 elephant corridors. This paper proposes NETRA, a cost-effective, internet-independent intrusion detection system deployed on Raspberry Pi Zero W and Raspberry Pi 4 edge platforms. NETRA employs probabilistic sensor fusion integrating a PIR motion sensor and an HC-SR04 ultrasonic distance sensor with a tunable threshold (tau_c = 0.65), enabling event-driven camera activation that reduces unnecessary visual processing by 52%. Upon confirmed intrusion, edge-AI classification using MobileNet-SSD (Pi Zero) or YOLOv5 ONNX (Pi 4) identifies threats including humans, large animals, and track obstructions. Confirmed threats are transmitted via LoRa (868 MHz) to alert the locomotive driver within 2.4 seconds end-to-end. Experimental evaluation across 113 motion events demonstrated 95% detection accuracy with zero false alarms through probabilistic fusion, compared to 85% for binary methods. Raspberry Pi 4 with YOLOv5 achieved 83.5% elephant F1-score, a 5.6x improvement over Pi Zero's heuristic approach (14.8%). LoRa communication achieved 100% packet delivery across 1-2 km in field trials. NETRA reduces deployment cost by 75% (\$247/km vs \$1000/km for Gajraj) while providing unified detection of both wildlife and obstruction threats.
Authors: Izaldein Al-Zyoud Abdulmotaleb El Saddik
Abstract: Frozen vision foundation models do not merely extract features; they organize images through a learned coordinate system. We ask whether that coordinate system remains internally coherent within a single input. This leads to Representational Consistency: the study of whether a frozen foundation model represents one sample coherently across its semantic subregions. We introduce Dimensional Coactivation (DCA), a per-dimension instrument for measuring this coherence. DCA compares semantic regions by asking whether the same feature dimensions coactivate across them. Unlike classical similarity measures, it deliberately avoids centering, L2 normalization, and full Gram coupling. These operations are useful when comparing different models or distributions, but they are mismatched to the intra-sample setting, where the coordinate system is fixed and raw magnitude carries signal. Deepfake detection provides a natural validation task. Synthetic faces may reproduce plausible eyes, noses, and mouths while breaking the representational structure that links those regions in real faces. Using frozen DINOv3 features, DCA exposes this break: an eyes-mouth-nose fingerprint achieves 0.9106 AUC on CelebDF-v2 and 0.9289 on DFD under FF++ c23 cross-dataset transfer. The design is also sharply validated by ablation: reintroducing centering collapses CelebDF-v2 AUC to 0.459, L2 normalization reduces it to 0.862, and cross-dimension coupling reduces it to 0.478. Finally, replacing DINOv3 with FaRL collapses CelebDF-v2 AUC to 0.582. DCA therefore depends on a stable per-dimension coordinate system, not on region extraction alone. These results position DCA as an instrument for measuring intra-sample representational coherence in frozen foundation models, with deepfake detection as the first validation task.
Authors: Xiaoce Wang, Sifan Zhou, Kaifei Wang, Leli Xu, Xuerui Qiu, Tao He, Ming Li
Abstract: Recent advances in diffusion transformers (DiTs) have enabled promising single-turn image editing capabilities. However, multi-turn editing often leads to progressive semantic drift and quality degradation.In this work, we study this problem from a latent-space frequency perspective by decomposing the editing process into two functional components: VAE and DiT. Through systematic analysis in the VAE latent space, we uncover that the DiT introduces dominant low-frequency drift that accumulates as semantic misalignment across editing rounds, while the VAE contributes comparatively stable reconstruction bias.Based on this insight, we propose VAE-LFA (Low Frequency Alignment), a training-free, plug-and-play method that performs alignment in VAE latent space. VAE-LFA decomposes latent discrepancies across editing rounds via low-pass filtering, and aligns low-frequency statistics to an exponential moving average of previous rounds, effectively suppressing accumulated semantic drift while preserving high-frequency details.Our method requires no retraining, ground-truth priors, or access to diffusion parameters, making it applicable to both white-box and black-box DiT editors. For white-box models, VAE-LFA is seamlessly integrated into the editing pipeline by eliminating redundant VAE round trips; for black-box models, it operates via an off-the-shelf VAE to perform inter-round latent alignment.Extensive experiments demonstrate that VAE-LFA improves semantic consistency and visual fidelity across diverse multi-turn editing scenarios, including both controlled and in-the-wild images.
Authors: Ankit Sanjyal
Abstract: Multimodal emotion recognition on CMU-MOSEI faces an extreme imbalance as Happy accounts for 65.9% of samples while three Ekman categories collectively represent under 7%, causing standard fusion models to maximize accuracy by ignoring minority emotions entirely. We present Affect-Diff, a Causal-Diffusion Bridge that addresses this through three jointly trained mechanisms: a NOTEARS-learned causal graph that re-weights modality contributions before fusion, a beta-VAE bottleneck for regularized latent compression, and a stop-gradiented 1D DDPM prior that structures the latent space against majority-class collapse. On 3,292 aligned CMU-MOSEI samples, Affect-Diff achieves validation balanced accuracy 0.384, an 18% relative improvement over the strongest baseline (TETFN: 0.324), while all evaluated baselines produce zero F1 on Fear, Disgust, and Surprise. Ablation studies confirm independent, non-redundant contributions from the diffusion prior (-24% without it) and causal graph (-13%). Notably, only the deterministic-encoder variant detects all six emotion classes, revealing KL regularization strength as a direct lever for minority-class sensitivity.
Authors: Zequan Xie, Weiming Zeng, Yunhua Chen, Sichang Ling, Tongyang Chen, Jinsheng Xiao
Abstract: Spiking Neural Networks (SNNs) offer notable advantages in biological plausibility and energy efficiency, making them promising candidates for building low-power Transformers. However, existing Spiking Transformers largely adhere to a passive reactive paradigm, which struggles to focus on task-relevant information and incurs substantial computational overhead when processing redundant visual data. To overcome this fundamental yet underexplored limitation, we propose SAFformer, a novel Spiking Transformer architecture based on an active predictive filtering paradigm. Inspired by the brain's predictive coding mechanism, SAFformer actively suppresses predictable signals and focuses on salient visual features. Extensive experiments show that SAFformer establishes new state-of-the-art performance on CIFAR-10/100 and CIFAR10-DVS. Remarkably, on ImageNet-1K, it achieves 80.50% Top-1 accuracy with only 26.58M parameters and an energy consumption of 5.88 mJ, demonstrating an exceptional balance between accuracy and efficiency.
Authors: Jiazheng Li, Chi-Hao Wu, Yunze Liu, Kaize Ding, Jundong Li, Chuxu Zhang
Abstract: Understanding ultra-long videos such as egocentric recordings, live streams, or surveillance footage spanning days to weeks, remains a challenge. For current multimodal LLMs: even with million-token context windows, frame budgets cover only tens of minutes of densely sampled video, and most evidence is discarded before inference begins. Memory-augmented and agentic approaches help with scale, but their retrieval remains fragmented across modalities and lacks long-range narrative summaries that span days or weeks. We propose \textbf{MAGIC-Video}, a training-free framework built around a multimodal memory graph with interleaved narrative chain: the graph unifies episodic, semantic, and visual content through six typed edges and supports cross-modal retrieval, while the chain distils long-horizon entity biographies and recurring activity events. At inference time, an agentic loop interleaves graph retrieval with narrative fact injection, covering both the modality and time dimensions of ultra-long video in a single retrieval pipeline. On EgoLifeQA, Ego-R1 and MM-Lifelong, MAGIC-Video consistently outperforms strong general-purpose, long-video, and agentic baselines, with gains of 10.1, 7.4, and 5.9 points over the prior best agentic system on each benchmark. Code is available at https://github.com/lijiazheng0917/MAGIC-video.
Authors: Weiming Chen, Xitong Ling, Zhenyang Cai, Xidong Wang, Jiawen Li, Tian Guan, Benyou Wang, Yonghong He
Abstract: Cell-level dense prediction is central to computational pathology, but remains challenging due to fine-grained histological structures, strong domain shifts, and costly dense annotations. Existing ViT-based pathology foundation models rely on patch tokenization, which can disrupt spatial continuity and weaken local morphological details needed for cell-level prediction. To address this, we propose Masked-Diffusion Convolutional Foundation Models, termed ConvNeXt Masked-Diffusion (CMD), a self-supervised convolutional generative pretraining framework for dense pathology representation learning. CMD uses a fully convolutional ConvNeXt-UNet backbone, performs masked-diffusion pretraining in pixel space, and incorporates frozen pathology foundation model features through adaptive normalization. Experimental results demonstrate that CMD consistently outperforms existing ViT-based pathology foundation models and even surpasses state-of-the-art end-to-end segmentation methods while fine-tuning only a small number of task-specific parameters across multiple pathology dense prediction tasks. The advantage is particularly pronounced under limited annotation settings, where CMD exhibits stronger robustness and generalization ability. Our findings suggest that purely convolutional architectures can also serve as competitive pathology foundation models for cell-level dense prediction, achieving leading performance within the current ViT-dominated paradigm and providing a scalable, high-performance solution that better preserves histological structural priors for fine-grained pathology understanding.
Authors: Xinyi Guo, Mingyi He, Haobin Ding, Weiming Chen, Xinrui Chen, Jiawen Li, Di Zhang, Minxi Ouyang, Yizhi Wang, Xitong Ling
Abstract: Implicit neural representations (INRs) encode images as neural-network weights, making image classification a problem of weight-space classifiability. A natural geometric hypothesis is that classifier feedback should make image-specific weights cluster by class in the shared-anchor coordinate. We test this hypothesis in the SIREN-based Meta Weight Transformer (MWT) regime, where end-to-end training meta-learns a shared initialization and inner-loop update schedule for fitting image-specific SIRENs. We find that this prediction fails. Exposed weight-space geometry and supervised clustering pressure do not reliably track trained-reader accuracy; clustering can even make local neighborhoods more class-consistent while making the trained reader worse. Crucially, the reader constructs rather than inherits class-aligned geometry: token-flow diagnostics show that class-aligned neighborhoods become strongly predictive of trained-reader accuracy only after late reader interactions, not in the input coordinate. We further identify the native SIREN bias column in the augmented weight token as a low-dimensional, sample-dependent causal readout route for the trained reader; targeted controls rule out generic scalar-column and marginal-distribution artifacts. The diagnosis motivates interventions that strengthen reader routing, add an explicit bias route, or use denser inner-loop fitting; under the lane-specific training conventions used here, route-directed variants often outperform the shared-anchor baseline but interact non-additively. Task-induced INR weights are classifiable not because they form raw geometric clusters, but because their class signal is routed through the reader.
Authors: Yijing Wang, Ruonan Li, Qilin Wang, Rongqiang Zhao, Jie Liu
Abstract: 3D semantic scene understanding has broad applications in digital twins, autonomous driving, smart agriculture, and embodied perception. However, dense point-wise annotation for point clouds is extremely expensive, making fully supervised 3D semantic learning difficult to scale. Recent annotation-free methods can discover semantic regions without manual 3D labels, but they often suffer from weak object-level consistency, inefficient global grouping, and category-agnostic segmented regions. We propose an annotation-free 3D scene semantic understanding method based on multi-granularity distillation and graph-diffusion-based segmentation. The proposed method first leverages structured visual knowledge guidance and superpoint graph diffusion to perform efficient global semantic propagation, alleviating the problem of inconsistent region-level semantics. It then conducts semantic inference through segmentation-cluster association, assigning interpretable category names to segmented 3D regions and improving the overall effectiveness of annotation-free 3D semantic understanding. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed framework. Compared with the advanced existing annotation-free baselines, our method improves oAcc, mAcc, and mIoU by 5.9%, 8.1%, and 2.4% at most, respectively. These results highlight the promise of the proposed framework for scalable annotation-free 3D scene understanding, especially in real-world scenarios requiring both object segmentation and semantic recognition.
Authors: Yize Cai, Rui Feng, Anlan Yu, Baoshen Guo, Zhiqing Hong
Abstract: Human Activity Recognition (HAR) from wearable sensors supports broad healthcare and behavior science applications. However, data heterogeneity and the scarcity of labeled data limit its real-world generalization. Recent advances in self-supervised learning (SSL) in vision and language domains have shown strong capability for learning generalizable representations from unlabeled data. Yet, few studies have systematically compared the generalization performance of SSL methods or explored how to adapt them for generalizable HAR. To address these gaps, we present BenchHAR, a unified framework for evaluating the generalization capability of SSL methods for sensor-based HAR on unseen target distributions. BenchHAR curates a large-scale dataset (~258K samples) and evaluates eight representative SSL methods across 12 encoder-classifier architectures. Our results reveal that existing SSL methods struggle to achieve satisfactory generalization performance. We find that: (1) For HAR models, the hybrid paradigm (combining reconstruction and contrastive pretraining) achieves the best overall performance. The CNN encoder exhibits the strongest ability to learn generalizable representations, while more expressive classifier architectures further improve generalization. (2) For data scale, increasing the amount of pretraining data from downstream activity classes consistently improves generalization, while adding more labeled data yields limited gains. Interestingly, incorporating unlabeled data from non-downstream activity classes does not improve generalization. (3) Sensor data collected from custom-grade devices generalizes better than that from research-grade devices, and data from limb transfers more effectively to trunk positions. BenchHAR provides a unified benchmark and actionable insights for generalizable sensor-based HAR systems. Our code is available at https://github.com/saiketa/HAR-Bench.
Authors: Weijing Wu, Qihua Liang, Bineng Zhong, Haiying Xia, Zhiyi Mo, Shuxiang Song
Abstract: Refining visual representations by eliminating their internal feature-level redundancy is crucial for simultaneously optimizing the performance and computational cost of models in visual tracking. To enhance their performance, many contemporary Transformer-based trackers leverage a larger number of historical template frames to capture richer spatio-temporal cues. However, this strategy leads to a massive number of input visual tokens. This creates two critical issues: it imposes a quadratic computational burden and can also degrade the tracker's overall performance. To bridge this gap, we propose a compress-then-interact tracking framework, ETCTrack, that learns to efficiently compress template tokens from historical template frames into a robust target representation, moving beyond handcrafted rules. Our method first employs the Adaptive Token Compressor to dynamically construct compact yet highly discriminative template tokens by filtering out redundant visual tokens. These refined template tokens are then processed by our Hierarchical Interaction Encoder to achieve a deep, adaptive interaction with the search features. Refined search features ensure subsequent precise target localization. Experiments on seven benchmarks demonstrate that our method outperforms current state-of-the-art trackers. ETCTrack-B224 reduces the number of template tokens by 60%, leading to a 21.4% reduction in MACs with only a 0.4% drop in accuracy. The source code are available at https://github.com/PJD-WJ/ETCTrack.
Authors: Haotang Li, Zhenyu Qi, Shaohan Henry Wang, Kebin Peng, Zi Wang, Qing Guo, Sen He, Huanrui Yang
Abstract: Visual Geometry Transformer (VGGT) is a strong feed-forward model for multiple 3D tasks, but its Alternating-Attention (AA) stack scales quadratically in the total token count, making long clips expensive. Existing token-reduction accelerators operate inside AA, leaving the patch grid that enters AA uncompressed. We introduce PaceVGGT, a pre-AA token pruning framework that prunes DINO patch tokens before the first AA block of a frozen VGGT. PaceVGGT trains a lightweight Token Scorer that estimates per-token importance from DINO features. The scorer is first distilled against an AA-internal attention target from the unpruned backbone, then refined under downstream camera, depth, and point-map losses. A per-frame keep budget fixes the backbone-visible sequence length, while an importance-adaptive merge/prune assignment preserves residual content from high-saliency frames under a fixed total merge budget. A Feature-guided Restoration module reconstructs the dense spatial grid required by the prediction heads. On ScanNet-50 and 7-Scenes, PaceVGGT remains on the reconstruction quality--latency frontier while reducing inference latency. On ScanNet-50, it reduces latency by \(5.1\times\) over unmodified VGGT at \(N=300\) and \(1.47\times\) over LiteVGGT at \(N=1000\). These results identify pre-AA pruning as a viable acceleration route for frozen VGGT-style geometry transformers.
Authors: M. Moein Esfahani, Sepehr Salem Ghahfarokhi, Mohammed Alser, Jingyu Liu, Vince Calhoun
Abstract: Recent advances in neuroimaging have deepened our understanding of the brain's complex functional and structural organization. Among these, functional Magnetic Resonance Imaging (fMRI) - particularly resting-state fMRI (rs-fMRI) - has emerged as a tool for identifying biomarkers of intrinsic brain connectivity and delineating large-scale neural networks. These networks are typically represented as volumetric spatial maps that capture functionally coherent brain regions and reflect individual differences in brain activity and structure. The spatial resolution of these maps plays an important role, as it determines the ability to localize functional units with precision, perform reliable brain parcellation, and detect subtle, spatially specific neurobiological alterations associated with development, aging, or disease. Therefore, improving the effective resolution of neuroimaging-derived maps holds significant promise for enabling more detailed insights into brain architecture and its relationship to behavior and pathology. To address this need, we propose NeuroGAN-3D, a novel 3D generative super-resolution model tailored to the computational demands of volumetric neuroimaging. Our model leverages a generative adversarial network architecture to enhance the spatial resolution of rs-fMRI spatial maps, significantly outperforming a conventional baseline.
Authors: Shuang Chen, Ruochen Li, Zihan Zhu, Ronald Thenius, Farshad Arvin, Amir Atapour-Abarghouei
Abstract: Underwater image enhancement (UIE) is a practically important yet underexplored application of spiking neural networks (SNNs), where the dominant degradations are large-scale and low-frequency, such as wavelength-dependent colour casts and scattering-induced veiling. Existing SNN restoration designs rely on locally bounded spiking perception, which can limit global correction and lead to saturated or inconsistent representations. To address these challenges, we propose a scale-aware SNN framework for UIE named UIESNN. At its core is a Multi-scale Pooling LIF Block (MPLB) that injects hierarchical multi-scale pooling responses into membrane dynamics, thereby enlarging the effective receptive field while preserving fine-grained details and inducing heterogeneous scale-dependent activations. Building on MPLB, we design a spiking residual architecture that integrates frequency decomposition and attention-based refinement in a fully spike-driven pipeline. Extensive experiments on the EUVP and LSUI benchmarks demonstrate that UIESNN achieves state-of-the-art performance among SNN-based methods, delivering improved colour fidelity and spatial coherence with competitive energy cost.
Authors: Mingyu Liu, Sihan Huang, Yijia Fan, Yinlin Yan, Quan Zhang, Jian-Fang Hu, Jianhuang Lai
Abstract: Zero-shot composed image retrieval (ZS-CIR) retrieves a target image from a reference image and a text modification without human-annotated CIR triplets. Projection-based ZS-CIR methods are attractive because they do not rely on LLMs at inference and remain lightweight, but they often underperform LLM-based approaches on complex semantic modifications. This gap reflects a semantic transition bottleneck in projection-based ZS-CIR: endpoint-level matching can let the edit text act as a target-side attribute cue rather than grounding it as a source-conditioned semantic transition. We further show that adding semantic transition supervision to the same text adapter creates an endpoint--transition conflict between endpoint alignment and semantic transition alignment. To address this conflict, DeCIR decouples endpoint and transition learning. It constructs paired forward/reverse edit tuples from image-caption pairs, trains separate low-rank text adapter branches for endpoint alignment and semantic transition alignment, and merges them with Low-Rank Directional Merge (LRDM) into one deployable adapter. Extensive experiments on CIRR, CIRCO, FashionIQ, and GeneCIS demonstrate that DeCIR consistently improves projection-based ZS-CIR without increasing inference complexity.
Authors: Harinarayan Krishnan, Shubhabrata Mukerjee, Jeffrey Donatelli, Daniela Ushizima
Abstract: The increasing complexity of modern computational environments often burdens researchers with infrastructure management, authentication protocols, and container deployments. We present Sci-Orchestra, a layered orchestration framework designed to fully automate experimental workflows, allowing scientists to prioritize scientific discovery over backend operations. By abstracting execution through an API-driven interface, the system assumes responsibility for secure authentication, resource management, and scalable deployment across diverse high-performance computing environments using Kubernetes architectures. A key innovation of Sci-Orchestra is its autonomous marketplace, which serves as a catalyst for cross-institutional collaboration. Through an intuitive user interface, researchers can rapidly deploy and share specialized services via simple selections, eliminating the need for complex installations and technical setups. This modular infrastructure is specifically designed to facilitate industry partnerships as it provides a secure execution environment and allows external collaborators to test and validate proprietary tools without the need for source-code exchange. This ``black-box'' interoperability protects intellectual property while enabling seamless integration into broader scientific pipelines, ultimately accelerating the transition from laboratory prototypes to industrial-scale applications.
Authors: Sara Ghazanfari, Siddharth Garg, Prashanth Krishnamurthy, Farshad Khorrami
Abstract: Multimodal Large Language Models (MLLMs) have made rapid progress in single-video understanding, yet their ability to reason across multiple independent video streams remains poorly understood. Existing multi-video benchmarks rely largely on human-annotated real-world footage, limiting the precision of spatial, temporal, and physical ground truth and making it difficult to diagnose model failures. We introduce SYNCR, a controlled synthetic benchmark for cross-video reasoning with programmatically verified grounding. Built using Habitat, Kubric, and CLEVRER simulator engines, SYNCR contains 8,163 multi-video question-answer pairs grounded in 9,650 unique videos. It evaluates MLLMs across eight tasks spanning four diagnostic pillars: Temporal Alignment, Spatial Tracking, Comparative Reasoning, and Holistic Synthesis. Our zero-shot evaluation of leading open- and closed-weight MLLMs reveals a substantial gap between current models and humans: the best model achieves only 52.5% average accuracy, compared to an 89.5% human baseline. Models perform relatively well on temporal ordering but struggle with precise physical and spatial reasoning, with the best model reaching only 26.0% accuracy on Kinematic Comparison. We further find that parameter scaling and reasoning-specialized post-training improve temporal alignment capabilities, but do not reliably address fine-grained physical tracking or global spatial synthesis. Finally, an exploratory sim-to-real correlation analysis suggests that several SYNCR tasks track model-level trends on real-world multi-video benchmarks, while also exposing reasoning capabilities underrepresented by existing evaluations. Code available at https://github.com/SaraGhazanfari/SYNCR.
Authors: Pascal Tilli, Mohsen Mesgar
Abstract: Visual Document Retrieval (VDR) models mostly rely on late interaction architectures, in which documents are represented by a set of local patch embeddings and then matched against query tokens. While efficient, this architecture prioritizes local similarity over global layout structure of documents to estimate relevancy between documents and query. In practice, this leads to errors as relevance originates from layout structure of documents with heterogeneous layouts combining figures, tables, and text. We make document layout learnable without changing inference. We propose a multimodal encoder that augments local patch representations with a global layout embedding, trained via textual descriptions encoding document layout information. Across four ViDoRe-v2 datasets, our model improves over the strongest architecturally comparable ColPali/ColQwen baseline by +2.4 nDCG@5 and +2.3 MAP@5, with statistically significant per-dataset gains over ColQwen.
Authors: Jian Lan, Zhicheng Liu, Xinpeng Wang, Yuhao Zhou, Haokun Chen, Jiancheng Lv, Barbara Plank, Thomas Seidl
Abstract: The ability to derive precise spatial and physical insights is a cornerstone of vision-language models (VLMs), yet their poor performances in related spatial intelligence tasks such as physical reasoning remain a fundamental barrier. The community critically lacks a scientific analysis revealing whether VLMs faithfully reach answers or plausibly make guesses. This work aims to provide a fundamental understanding of how VLMs perceive the physical world, and utilize physical laws, while assessing the reliability of model confidence. We propose NICE and FACT, a dual-diagnostic paradigm that explicitly decomposes quantitative reasoning for kinematic physics: FACT diagnoses visual fidelity, physical law comprehension, and temporal grounding. NICE studies our novel neighborhood-informed calibration method and novel metrics to evaluate and calibrate confidence reliability. Evaluated across 6 latest state-of-the-art VLMs, we uncover that models fail to identify visual preconditions or utilize necessary physical laws to reach answers. This work highlights and establishes a standardized diagnostic paradigm to guide the development of faithful, physically-grounded VLMs.
Authors: Haroon Wahab, Irfan Mehmood, Hassan Ugail
Abstract: Wireless capsule endoscopy (WCE) enables non-invasive visual assessment of the small bowel, but its clinical utility is constrained by the large volume of frames generated per examination and the difficulty of recognising subtle abnormalities under highly variable imaging conditions. Existing learning-based approaches for WCE are predominantly vision-only, often confined to narrow pathology sets, and show limited transfer across datasets and centres. To address these limitations, this study introduces CapCLIP, a domain-specific vision-language representation learning framework for WCE. CapCLIP aligns capsule endoscopy frames with clinically grounded textual descriptions derived from standardised nomenclature and pathology-aware caption templates, thereby learning embeddings that are both semantically informed and transferable. The proposed framework is evaluated against relevant open-source vision and vision-language foundation models under strict zero-shot conditions using unseen WCE datasets. Evaluation covers three downstream tasks: K-nearest neighbour classification, CLIP-style image-text classification, and text-to-image retrieval. Across these settings, CapCLIP consistently outperforms the compared baselines, with particularly strong gains in zero-shot image-text classification and cross-modal retrieval on out-of-distribution datasets. The results indicate that language-guided representation learning can improve both generalisation and semantic interpretability in WCE analysis. These findings position CapCLIP as a step toward foundation models tailored to capsule endoscopy and support the use of language-grounded WCE analysis.
Authors: Nhut Le, Ehsan Karimi, Maryam Rahnemoonfar
Abstract: Post-disaster situational awareness relies heavily on understanding both the extent and the volume of floodwaters. While 2D semantic segmentation provides accurate flood masking, it lacks the vertical dimension required to assess navigability and structural risk. This paper presents a geometric "Water Surface Elevation" approach for estimating flood depth from monocular aerial imagery. Our pipeline utilizes Mask2Former, a state-of-the-art transformer-based segmentation model, to generate precise 2D flood masks. These masks are fused with Digital Elevation Models (DEMs) to identify the water-land boundary, calculate a global water surface elevation ($Z_{water}$), and compute per-pixel depth based on the principle of local hydrostatic equilibrium. We evaluate this workflow using the FloodNet and CRASAR-U-DROIDS datasets, demonstrating how high-performance segmentation can be leveraged to extract 3D volumetric data from 2D imagery without the latency of hydrodynamic simulations.
Authors: Hoang Hai Pham, Shuntian Zheng, Jiaqi Li, Yu Guan
Abstract: Millimeter-wave (mmWave) radar has emerged as a promising sensing modality for human perception due to its robustness under challenging environmental conditions and strong privacy-preserving properties. However, recovering accurate 3D human body meshes from radar observations remains difficult due to severe signal clutter and the inherently partial nature of radar measurements. Previous works typically adopt end-to-end frameworks that directly regress human body parameters from raw radar data, without decoupling signal interpretation from geometric reasoning or exploiting temporal motion cues, limiting learning performance. To address this, we propose a two-stage framework for radar-based human body reconstruction. First, we introduce a human reflection extraction module that performs coarse-to-fine localization and voxel-wise segmentation to produce a confidence-weighted radar volume encoding voxel-level human likelihood. Second, we design a motion-aware mesh recovery network that reconstructs the human body by jointly modeling per-frame geometry and inter-frame dynamics using a dual-branch architecture. Extensive experiments demonstrate that the proposed method outperforms existing approaches while maintaining computational efficiency.
Authors: Salim Khazem, Ibrahim Mohamed Serouis, Zakaria Ezzahed
Abstract: Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight residual modules. While effective, these methods usually treat adaptation as a discrete Euclidean perturbation of frozen representations, without explicitly modeling the geometry of the task-induced feature displacement. We propose \textsc{MC-RFM}, a mixed-curvature Riemannian flow-matching framework for few-shot adaptation of frozen visual backbones. The key idea is to represent adapted features on a product manifold combining a hyperbolic factor, which captures hierarchy-sensitive semantic structure, and a Euclidean factor, which preserves locally discriminative visual variation. Adaptation is formulated as a task-conditioned continuous transport from frozen features to support-set prototypes, trained with a flow-matching objective and coupled to a hybrid prototype-linear classifier. The method is lightweight, backbone-agnostic, and operates entirely on cached frozen features. Across seven visual recognition benchmarks, five frozen backbones, and 1/4/16-shot regimes, \textsc{MC-RFM} is the best-performing method in a majority of evaluated settings, with the strongest gains on Transformer backbones and fine-grained datasets. Ablations show that the mixed-curvature head, task conditioning, adaptive branch gating, prototype shrinkage, and discriminative supervision each contribute to performance. These results suggest that few-shot adaptation benefits not only from deciding which parameters to update, but also from modeling how representations should move through a geometry matched to the structure of the downstream task.
Authors: Hassan Shapourian, Kasra Hejazi, Olabode M. Sule, Beren Millidge
Abstract: We present ZAYA1-VL-8B, a compact mixture-of-experts vision-language model built upon our in-house language model, ZAYA1-8B. Despite its compact size, ZAYA1-VL achieves performance competitive with leading base models such as Molmo2-4B and InternVL3.5-4B, while surpassing models including Qwen2.5-VL-3B, PLM-3B, and MolmoE-1B across a range of image understanding, reasoning, and counting benchmarks. The architecture incorporates two key innovations: (1) vision-specific LoRA adapters integrated into the LLM to increase modality-specific capacity without increasing the number of experts, and (2) bidirectional attention over image tokens within the LLM to enhance visual understanding. We detail the full training pipeline including data composition at each stage, sequence packing, and the attention masking scheme. The model comprises 9.2B total parameters, with 1.4B active parameters including the vision encoder, and is publicly available at https://huggingface.co/Zyphra/ZAYA1-VL.
Authors: Yongkang Li, Brian Wong, King Wai Chiu, Hanwen Xu, Tangqi Fang, Erin Dunnington, Dan Fu, Sheng Wang
Abstract: Chemical imaging enables label-free visualization of cells, tissues and living systems while providing direct biochemical information that is difficult to obtain with conventional fluorescence microscopy. Despite its promise in applications ranging from intraoperative diagnosis to drug-response analysis, its broader use remains limited by slow data acquisition, particularly for three-dimensional imaging. Here we present MicroDiffuse3D, a pretrained foundation model for 3D microscopy image restoration that recovers high-quality volumetric structure from degraded low-resolution measurements acquired at substantially higher throughput. We evaluated MicroDiffuse3D across three challenging restoration settings, including 3D super-resolution under 16-fold volumetric sparsity, joint degradation in resolution and noise, and 3D denoising in the low signal-to-noise ratio (SNR) regime, where the model delivered clear gains over strong baselines. Under the sparse 3D super-resolution setting, MicroDiffuse3D produced clearer continuity across depth with fewer artifacts and improved segmentation quality by 10.58% and line-profile concordance by 15.59%. Together, our results establish pretrained 3D restoration as a broadly applicable strategy for overcoming the throughput and SNR limitations in volumetric chemical imaging, enabling high-resolution analysis at scales and speeds that were previously difficult to achieve.
Authors: Haotian Xue, Yipu Chen, Liqian Ma, Zelin Zhao, Lama Moukheiber, Yuchen Zhu, Yongxin Che
Abstract: Action-conditioned world models (ACWMs) have shown strong promise for video prediction and decision-making. However, existing benchmarks are largely restricted to egocentric navigation or narrow, task-specific robotics datasets, offering only limited coverage of the rich physical interactions required for generalized world understanding. We introduce ACWM-Phys, a new benchmark for evaluating action-conditioned prediction under diverse physical dynamics in a clean, controllable simulation environment with a carefully designed action space. ACWM-Phys contains training and evaluation data spanning rigid-body dynamics, kinematics, deformable-object interactions, and particle dynamics. To evaluate both interpolation and generalization, we design in-distribution and out-of-distribution protocols with controlled shifts in interaction patterns or scene configurations. By building the benchmark in a fully controllable simulator, ACWM-Phys enables precise data collection, reproducible evaluation, and systematic analysis of model capabilities for physically grounded world modeling. Through systematic experiments on ACWM-DiT, we find that OoD generalization depends not only on the physical regime but also on effective task complexity: models generalize well on visually simple, low-dimensional interactions with clear geometric structure, but suffer larger drops on deformable contacts, high-dimensional control, and complex articulated motion. This suggests that the model still relies heavily on visual appearance patterns instead of fully learning the underlying physics. Ablations show that cross-attention improves high-dimensional action conditioning, causal VAEs outperform frame-wise encoders, and larger action spaces are harder to model but can improve generalization by providing richer control signals. These findings guide the design of physically grounded world models.
Authors: Alen Mrdovic (Tony), Qingze (Tony), Liu, Danrui Li, Mathew Schwartz, Kaidong Hu, Sejong Yoon, Mubbasir Kapadia, Vladimir Pavlovic
Abstract: Diffusion models for multi-agent trajectory prediction are limited by iterative denoising, which causes inference latency that hinders their use in time-critical settings like autonomous driving. Fast-sampling variants using DDIM and informed initial noise distributions partially alleviate this issue, but they either fail to achieve true single-step generation or are constrained by the chosen noise distribution. Consistency Models (CMs) offer high-quality one-step generation by mapping noise directly to data, but are difficult to train from scratch . We propose ECTraj, an enhanced CM pipeline with improved training and conditional generation for trajectory prediction. Our framework extends the student-teacher consistency training scheme: the student produces standard outputs, while the teacher explicitly fuses its predictions with parts of the ground truth to give stronger supervision. We also exploit CMs' direct denoising for top-K multi-shot generation during training. Combining conditional generation with this enhanced consistency objective yields faster inference and improved prediction accuracy, establishing competitive new benchmarks on the large-scale Argoverse 2 dataset.
Authors: Kaixiang Zheng, Jacob H. Seidman
Abstract: As synthetic images become increasingly realistic, reliable synthetic image detection techniques are of pressing need to prevent their misuse. Despite satisfactory in-distribution performance, deep neural network-based synthetic image detectors (SIDs) lack reliability in deployment and often fail in the presence of common covariate shifts, resulting in poor detection accuracy. To avoid the risk caused by potential errors, we adopt a selective classification (SC) strategy by allowing SIDs to abstain from making low confidence predictions. For practicality, we focus on post-hoc methods which perform confidence estimation on a given SID without retraining. However, we show that conventional logit-based confidence score functions (CSFs) exhibit pathological behavior under covariate shifts, leading to SC performance close to or even worse than random guessing. To address this, we propose a simple yet effective SC framework for Reliable Synthetic Image Detection (ReSIDe). First, we generalize the notion of logits to an SID's intermediate layers from a centroid matching perspective, extending the use of logit-based CSFs to any layer of an SID. Then, we introduce a preference optimization algorithm that aggregates confidence scores extracted from different layers to a final confidence estimate by minimizing an upper bound of the area under the risk-coverage curve (AURC). Extensive experimental results show that ReSIDe significantly boosts the SC performance of various logit-based CSFs under common covariate shifts, achieving up to 69.55% AURC reduction.
Authors: Antoni Nowinowski, Krzysztof Krawiec
Abstract: In modern GANs, maintaining an Exponential Moving Average (EMA) of the generator's weights is a standard practice, as such an averaged model consistently outperforms the actively trained generator. However, the EMA generator is used for final deployment only and does not influence the training process. To address this missed opportunity, we introduce Self-Distilled GAN (SD-GAN) that employs the EMA generator as a teacher to guide the active generator (student) via perceptual loss. We prove the local asymptotic stability of SD-GAN in the Dirac-GAN setting and show that it dampens the parasitic cycling behavior that plagues the conventional GANs. Empirical evaluations across established architectures and datasets demonstrate that SD-GAN improves the final image quality on several metrics (FID and random-FID in particular), stabilizes the optimization trajectory and provides additional learning guidance that is not trivially correlated with the conventional adversarial loss. It also proves effective for fine-tuning pretrained GAN models.
Authors: Lujia Zhong, Yihao Xia, Shuo Huang, Jianwei Zhang, Yonggang Shi
Abstract: Deep learning models in medical imaging typically operate as parametric memory, diagnosing patients by recalling fixed knowledge learned during training. This contrasts sharply with clinical practice, where physicians employ analogical reasoning to diagnose new cases by referencing similar records from past exemplars. While In-Context Learning (ICL) frameworks such as Tabular Prior-Fitted Networks (TabPFN) offer a promising diagnosis-by-reference paradigm, they are designed with tabular-specific inductive priors and rely on non-differentiable preprocessing pipelines, leading to manifold mismatch and gradient fracture when applied to heterogeneous multimodal data. To address these limitations, we propose PromptDx, a novel diagnosis-by-reference framework that leverages a pre-trained TabPFN as an ICL engine while enabling seamless integration with multimodal representations. Our core contribution is a Differentiable Prompt Tuning (DPT) mechanism that aligns a Masked Multimodal Modeling module with the pre-trained ICL engine. By training a lightweight adapter as a differentiable surrogate for the engine's non-differentiable preprocessors, we enable an end-to-end optimization of multimodal prompts within the ICL paradigm. We validate our method on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset using 3D MRI and tabular biomarkers. Experiments demonstrate that our approach outperforms traditional parametric baselines. Notably, our method achieves superior performance using only 1% context samples compared to 30% in standard ICL, demonstrating exceptional manifold condensation ability. We further validate the generalizability of our DPT framework across six tabular datasets with diverse scales. Overall, our method offers a more data-efficient and clinically aligned paradigm for Alzheimer's Disease diagnosis.
Authors: Baoquan Zhang, Zhehao Yu, Lisai Zhang, Kenghong Lin, Tianran Chen, Yuxi Sun, Yunming Ye, Yao He
Abstract: Parameter Efficient Fine-Tuning (PEFT) is a key technique for adapting a large pretrained model to downstream tasks by fine-tuning only a small number of parameters. Recent methods based on Fourier transforms have further reduced the fine-tuned parameters scale by only fine-tuning a few spectral coefficients. Its basic assumption is that the weight change \delta W is a spatial-domain matrix with a sparse spectrum. However, in this paper, we observe that the spectrum of weight change is not sparse, but instead distributed like power-uniform. This fact implies that fine-tuning only a few spectral coefficients is insufficient to accurately model the weight change with uniform spectrum. To address this issue, we propose to seek an invertible transformation that can transform a latent spatial-domain matrix with sparse spectrum to the weight change, and then perform PEFT on such sparse spectrum domain with few spectral coefficients, called S2FT. To seek such transformation, we first pre-estimate a coarse weight change as a prior. Then, inspired by that sparse spectrum often correspond to locally smooth spatial structures, we regard this transformation as a row and column rearrangement operation on the pre-estimated weight change that smooth spatial structures while keep the structure information of neurons. Finally, we propose to solve the rearrangement search problem in a simple nearest neighbor search manner, thereby obtaining the invertible transformation. Extensive results show our S2FT achieves superior performance by only using 0.08% training parameters.
Authors: Yongliang Zhen, Bo L\"U, Hang Yang, Xiaotian WU
Abstract: On-orbit servicing and active debris removal involving non-cooperative spacecraft require reliable pose estimation to supply accurate position and orientation data for autonomous visual navigation. Learning-based monocular methods have seen widespread adoption in spacecraft pose estimation, yet they suffer from an intrinsic depth ambiguity problem and tend to fail under the harsh illumination conditions routinely encountered in orbit. Active depth sensors could in principle address the geometric ambiguity, but their power and mass requirements make them poorly suited to most spacecraft platforms. This work addresses these issues through a passive stereo vision framework for six-degree-of-freedom (6-DOF) pose estimation of non-cooperative spacecraft. A binocular stereo matching network called TSCA-Stereo is developed to cope with weak-texture surfaces, specular highlights, and severe lighting variations typical of space imagery. A cross-modal fusion Transformer is introduced to combine RGB appearance information with stereo depth features in an adaptive manner, supporting reliable pose recovery. A synthetic binocular multimodal dataset is also built for the experiments, covering stereo disparity maps and 6-DOF pose annotations across a range of illumination scenarios, attitude configurations, and noise levels. Experimental results show that TSCA-Stereo outperforms the baseline across every evaluated metric on this space-specific dataset. The full pose estimation pipeline achieves a mean translation error of 0.0419 m and a mean orientation error of 0.8632{\deg} under varied imaging conditions, confirming that the passive stereo approach is both effective and resilient when operating under the demanding visual conditions of the space environment.
Authors: Soyeon Na, Seung Young Noh, Ju Yong Chang
Abstract: Egocentric human mesh recovery (HMR) from monocular head-mounted cameras is increasingly important for AR/VR applications, but remains challenging due to the lack of reliable ground-truth (GT) annotations based on parametric human body models such as SMPL and SMPL-X for real egocentric images. Existing egocentric HMR methods typically rely on pseudo-GT and focus on body pose estimation, which limits their ability to recover fine-grained whole-body details such as hands and face. We study egocentric whole-body human mesh recovery and propose a prior-guided learning framework that reconstructs whole-body meshes from a single egocentric image. We construct more accurate optimization-based pseudo-GT aligned with 3D joint supervision, and leverage multiple priors by adapting an exocentric HMR foundation model together with a diffusion-based pose prior. A deterministic undistortion module is further adopted to handle fisheye distortions in egocentric images. Experiments across multiple egocentric benchmarks demonstrate improved whole-body reconstruction compared to state-of-the-art methods, and show that our optimization-based pseudo-GT is substantially more accurate than existing regression-based pseudo-GT. To facilitate reproducibility, the code and dataset annotations are publicly available at https://github.com/naso06/EgoSMPLX.
Authors: Devesh Shah
Abstract: Out-of-distribution (OOD) detection is essential for reliable deployment of deep learning systems, yet the majority of existing methods are evaluated on small, visually homogeneous benchmarks. In this work, we study six OOD detection methods spanning post-hoc scoring, auxiliary objectives, energy-based models, and constrained optimization on the Plant Pathology 2021 dataset, a fine-grained task with natural distribution shifts. Energy-based fine-tuning performs best across OOD settings, improving detection over the softmax baseline while preserving in-distribution accuracy. Analysis shows these gains stem from both a restructuring of the embedding space alongside calibration of the scoring function. We further document practical training instabilities that arise when scaling constrained optimization methods to moderate-sized datasets, findings that are largely absent from existing literature. Our results demonstrate that principled OOD detection is achievable on real-world domain-specific data and that benchmark evaluations alone may not capture the challenges that emerge in practice.
Authors: Ao Li, Xiaoning Liu, Sheng Li, Yapeng Du, Zhen Long, Lei Luo, Le Zhang, Ce Zhu
Abstract: All-in-one image restoration aims to handle diverse degradations within a single model. However, existing methods often suffer from three key limitations: 1) per-input computational overhead from dynamic degradation estimation; 2) optimization challenges due to task heterogeneity; and 3) inefficient, frequency-agnostic encoder designs. To overcome these, we introduce the Dynamic Reparameterization Network (DRNet), a novel framework operating on an initialization-stage reconfiguration paradigm that fundamentally eliminates per-input overhead. At its core, a Dynamic Reparameterization MLP (DRMLP) guided by a Task-Specific Modulator (TSM), which effectively mitigates task heterogeneity by orchestrating both specific restoration goals and a versatile general-purpose mode within a unified architecture. Furthermore, we incorporate a Continuous Wavelet Transform Encoder (CWTE) that explicitly leverages frequency characteristics via wavelet decomposition for a lightweight yet powerful design. Extensive experiments demonstrate that DRNet achieves state-of-the-art performance across five restoration tasks with superior parameter efficiency. Crucially, it showcases unique flexibility, excelling as both a highly competitive foundation model for blind restoration and a top-performing user-guided specialist.
Authors: Yeon-Ji Song, Kiyoung Kwon, Junoh Lee, Jin-Hwa Kim, Byoung-Tak Zhang
Abstract: Reconstructing dynamic 3D scenes from blurry monocular videos is challenging as motion-induced blur entangles object motion and geometry, hindering geometric consistency. We present Kinematics-GS, a kinematics-aware framework that models blur as motion-aligned deformation and introduces a kinematic prior to reparameterize Gaussian shapes along motion trajectories, thereby mitigating degenerate shape collapse without auxiliary motion supervision. To stabilize optimization, we decompose scenes into dynamic and static components using temporal deformation variance and employ a coarse-to-fine deformation strategy to capture both global motion and fine-grained details. We also introduce a challenging real-world dataset of deformable and elastic objects exhibiting non-rigid motion with spatially non-uniform motion blur that obscures geometric cues. Extensive experiments on real-world benchmarks with realistic motion blur demonstrate that Kinematics-GS outperforms prior methods by a clear margin in monocular dynamic scene reconstruction, highlighting its effectiveness in handling complex and non-rigid motion scenarios.
Authors: Hendrik Sommerhoff, Michael Moeller
Abstract: Plug-and-play (PnP) methods for solving inverse problems have recently achieved strong performance by leveraging denoising priors based on powerful generative diffusion and flow models. However, existing diffusion- and flow-based PnP methods typically rely on stochastic renoise-denoise operations, which complicate the analysis of their convergence behavior. In this work, we identify and formalize the deterministic renoise-denoise operator underlying flow-based plug-and-play methods. This perspective reveals that these methods implicitly define a deterministic operator given by the expectation of a denoiser over the latent noise distribution. Building on this insight, we propose FlowADMM, a PnP algorithm that integrates the renoise-denoise operator into the classical alternating direction method of multiplier (ADMM) framework. We establish convergence guarantees for FlowADMM under weak Lipschitz conditions on the underlying flow network, and extend the analysis to non-stationary time schedules. Empirically, FlowADMM achieves state-of-the-art performance among flow-based PnP methods on a range of inverse problems, including denoising, deblurring, super-resolution, and inpainting, while requiring fewer data consistency evaluations than prior approaches.
Authors: Lei Wang, Wenxiang Diao, Andrew Busch, Jun Zhou, Yongsheng Gao
Abstract: Video anomaly detection (VAD) systems often prioritize accuracy while overlooking privacy concerns, limiting their suitability for real-world deployment. We propose the Orthogonal Projection Layer (OPL), a lightweight module that removes task-irrelevant variations to produce representations focused on anomaly-relevant cues. To address privacy risks in human-centered scenarios, we introduce Guided OPL (G-OPL), which suppresses facial attributes using weak supervision from face-presence signals while preserving non-identifying features such as pose and motion. A cosine alignment objective enforces consistent capture and removal of facial information without identity labels or adversarial training. We further present a privacy-aware evaluation framework that jointly assesses detection performance and privacy preservation, and enables analysis of how sensitive information is filtered. Experiments show that embedding privacy constraints into model design reduces sensitive information while maintaining or improving detection accuracy, supporting projection-based architectures as a principled approach for privacy-aware VAD.
Authors: Md. Shakhoyat Rahman Shujon, Sheikh Md. Galib Mahim, Md. Milon Islam, Md Rezwanul Haque, Md Rabiul Islam, Hamdi Altaheri, Fakhri Karray
Abstract: We propose CAST, a dual-stream architecture that utilizes channel-aware spatial transfer learning for isolated sign language recognition addressing the challenges of magnitude-only 60~GHz radar Range-Time Maps (RTM). The proposed framework combines three physics-aware architectures with pretrained vision backbones, which operate under radar-only constraints across clinical and alphabetical gestures. First, an explicit decibel-to-linear inversion is combined with a windowed fast Fourier transform that extracts Cadence Velocity Diagrams (CVD) while avoiding the harmonic artifacts that arise from the spectral analysis of log-compressed signals. Second, a cross-antenna spatial attention module applies attention to raw antenna channels before the convolution, preserving inter-receiver amplitude covariance. Third, an asymmetric cross-attention mechanism fuses representations from parallel ConvNeXt-Tiny (CVD) and EfficientNetV2-S (RTM) backbones. Extensive experiments reveal that the architecture achieves a Top-1 accuracy of 80.5% under 5-fold cross-validation, establishing a 3.3% improvement over the best single-model baseline (77.2%). The findings suggest that physics-aware signal representations form a promising direction for radar-only sign language recognition under constrained sensor modalities. The source code is available at: https://github.com/Shakhoyat/CAST-at-SignEval2026.
Authors: Juan Wang, Xinyu Sun, Ke Zhang, Jin Wang, Bing Li, Weiming Hu, Liang Wang
Abstract: Current image quality assessment methods are heavily biased towards global distortions (e.g., noise, blur), neglecting local perceptual artifacts such as ghosting, lens flare, and moire effects. Although significant progress has been made in artifact removal, the fundamental problem of automatic artifact detection remains largely unexplored. In this paper, we formalize the Image Perceptual Artifact Detection (IPAD) task to address this gap. We contribute a benchmark dataset comprising 3,520 artifact images, including 520 real-captured and 3,000 synthetic samples, each paired with pixel-level masks across three representative artifact categories. The core challenge of IPAD lies in the localized, subtle, and semantically weak nature of these artifacts, which makes them prone to missed detection. To overcome this, we introduce IPAD-CLIP, a novel framework built upon CLIP that enhances artifact discrimination in both textual and visual spaces while preserving generalization capabilities. Our key insight is that local artifacts often exhibit strong correlations with specific semantic contexts. Accordingly, we learn artifact-aware text embeddings to explicitly model the object-artifact relationships, resulting in enhanced representations that clear differentiate between clean and artifact prompts. These text embeddings are then used as anchors to shift the visual encoder's attention from high-level semantics to subtle, low-level artifacts. Extensive experiments demonstrate that IPAD-CLIP offers a resource-efficient adaptation of CLIP for detection, significantly outperforming advanced image anomaly detection and manipulation detection methods on our benchmark. To the best of our knowledge, this is the first study addressing multi-class local perceptual artifact detection in terms of both dataset and model.
Authors: Van-Loc Nguyen, AprilPyone MaungMaung, Minh-Triet Tran, Isao Echizen
Abstract: Forensic analysis of AI-edited images requires more than binary real-versus-fake prediction: a useful system should localize the edit, identify its semantic type, and ground its decisions in visual evidence. Existing image-forensics datasets typically emphasize detection or localization, while reasoning-supervised vision-language datasets rarely target image manipulation and often rely on LLM-generated rationales whose faithfulness is difficult to verify. We introduce EditSleuth, a dataset of 257,725 image-edit triplets constructed from existing image-editing corpora for grounded image-edit forensic reasoning. Each example includes an edited image, its source image, a binary edit mask, a 12-class edit taxonomy label, a difficulty score, and a six-step reasoning chain. EditSleuth chains are generated deterministically from triplet-grounded upstream artifacts, with each statement tied to a specific computable source of evidence. Our analysis reveals that a naive four-component difficulty formulation suffers from a rank-2 correlation collapse among magnitude features; a simplified three-component formulation substantially increases score dispersion on both Pico-Banana and MagicBrush. Difficulty also varies meaningfully within most edit categories, indicating that the score is not a proxy for edit type. As an initial learning study, we fine-tune Qwen2-VL-2B with LoRA and find that chain-as-target supervision matches a label-only baseline on classification accuracy among parseable answers, while additionally yielding grounded explanatory prose that label-only supervision cannot produce. We release the dataset, the deterministic construction pipeline, and pilot training scripts.
Authors: Md Abu Obaida Zishan, Jannatun Noor, Annajiat Alim Rasel
Abstract: Stable Diffusion (SD) has evolved DDPM (Denoising Diffusion Probabilistic Model) based image generation significantly by denoising in latent space instead of feature space. This popularized DDPM-based image generation as the cost and compute barrier was significantly lowered. However, these models could only generate fixed-resolution images according to their training configuration. When we attempt to generate higher resolutions, the resulting images show object duplication artifacts consistently. To solve this problem without finetuning SD models, recent works have tried dilating the convolution kernels of the models and have achieved a great level of success. But dilated kernels are harder to fine-tune due to being zero-gapped. Apart from this, other methods, such as patched diffusion, could not solve the object-duplication problem efficiently. Hence, to overcome the limitations of dilated convolutions, we propose kernel interpolation of SD models for higher-resolution image generation. In this work, we show mathematically that interpolation can correctly scale convolution kernels if multiplied by a constant coefficient and achieve competitive empirical results in generating beyond-training-resolution images with Stable Diffusion using zero training. Furthermore, we demonstrate that our method enables interpolation of deep neural networks to adapt to higher-dimensional training data, with a worst-case performance drop of $2.6\%$ in accuracy and F1-Score relative to the baseline. This shows the applicability of our method to be general, where we interpolate fully-connected layers, going beyond convolution layers. We also discuss how we can reduce the memory footprints of training neural networks, using our method up to at least $4\times$.
Authors: Guodong Ding, Angela Yao
Abstract: This paper tackles compositional personalization of vision-language models (VLMs). In this problem, multiple user-defined concepts must be recognized or described jointly at test time. We introduce Gate-and-Merge, a zero-shot framework that enables compositional personalization without the need for co-occurrence training. During personalization, each concept is learned independently as a lightweight LoRA adapter, paired with a concept token. The base model remains unchanged and concepts are kept disentangled. At inference, we enable composition by merging concept-specific LoRA updates directly in weight space. To suppress irrelevant activations and prevent interference, a gating mechanism is employed to estimate textual and visual cues and select only the modules that contribute to the prediction. We further stabilize composition by combining only the most meaningful and mutually consistent updates, helping preserve each concept's identity. Our quantitative and qualitative analyses show consistent gains in performance across multiple personalization tasks in both single-concept and compositional settings.
Authors: Hongrui Li, Yichen Shi, Hongyang Wang, Yuhao Gao, Hui Ma, Jun Feng, Zitong Yu
Abstract: Unified face attack detection (UAD) requires recognizing physical spoofing and digital forgery within a shared decision space, yet existing discriminative or prompt-based methods largely rely on appearance correlations and provide limited evidence-grounded reasoning. We propose UniShield, a knowledge-grounded multimodal reasoning framework for unified face attack defense. UniShield constructs a Face Attack Knowledge Graph (FAKG) that links attack categories to diagnostic visual cues and attack-conditioned relations, and uses it to synthesize 52,025 FAKG-QA examples for Attack-Graph Instruction Tuning (AGIT). To improve rationale consistency, we further introduce Graph-Consistent Reasoning Optimization (GCRO), a GRPO-based objective with a KG-consistency reward that encourages generated rationales to match graph-supported cues while penalizing incompatible claims. Experiments on our multimodal UAD benchmark show that UniShield achieves strong performance across binary, coarse-grained, and fine-grained protocols, with consistently high ACC and low HTER. These results suggest that structured attack knowledge can improve both detection accuracy and reasoning reliability over discriminative baselines and general-purpose MLLMs. Our code will be released at https://anonymous.4open.science/r/Unishield-A6A3/.
Authors: Bohan Li, Shuojue Yang, Baorui Peng, Xianda Guo, Erli Zhang, Youqi Tao, Junfeng Duan, Daguang Xu, Qi Dou, Xin Jin, Wenjun Zeng, Hao Zhao, Yueming Jin
Abstract: Action-conditioned surgical video generation is a critical yet highly challenging problem for robotic surgery. The core difficulty is that low-dimensional control vectors must precisely govern complex image-space evolution. In this work, we propose a kinematic-to-visual lifting paradigm that converts articulated kinematics into a unified set of five image-aligned control modalities. Building on this representation, we introduce a hierarchically routed visual control framework that selectively activates the most relevant control modalities and motion scales. Instead of uniformly applying all control signals, our model performs hierarchical routing to dynamically allocate conditioning capacity. We further design kinematic-prior-guided routing loss functions to ensure physically meaningful, temporally stable, and efficient expert utilization. To improve efficiency, we propose a budgeted training and inference scheme that leverages routing-induced sparsity. By selectively discarding low-significance control pathways during training and execution, our approach enables adaptive computation that is complementary to standard distillation. We additionally construct a new benchmark with curated articulated annotations, obtained through human-in-the-loop semantic labeling and differentiable pose tracking, providing realistic supervision for action-conditioned surgical video generation. Extensive experiments demonstrate that our method consistently improves action faithfulness, visual fidelity, and cross-domain generalization over diverse baselines. Moreover, our efficient variant achieves substantial reductions in latency while maintaining strong control accuracy.
Authors: Huilai Li, Xiaomeng Di, Ying Xing, Yonghao Dang, Yiming Wang, Jianqin Yin
Abstract: Weakly supervised Audio-Visual Video Parsing (AVVP) aims to recognize and temporally localize audio, visual, and audio-visual events in videos using only coarse-grained labels. Faced with the challenging task settings, existing research advances along two main paths: pre-training pseudo-label generators for fine-grained cross-modal semantic guidance, or refining AVVP model architectures to enhance audio-visual fusion. However, since audio and visual signals are typically unaligned, achieving accurate video parsing fundamentally relies on precise perception of uni-modal events. Yet these multi-modal focused strategies excessively emphasize multi-modal fusion while inadequately guiding and preserving uni-modal semantics, resulting in noisy pseudo-labels and sub-optimal video parsing performance. This paper proposes a novel framework that enhances uni-modal representations for both the pseudo-label generator and the AVVP model. Specifically, we introduce a similarity-based label migration approach to annotate pre-training data, thereby enabling the pseudo-label generator to better understand uni-modal events. We also employ a soft-constrained manner to refine modeling of uni-modal features in parallel with multi-modal fusion. These designs enable coordinated attention to both uni-modal and cross-modal representations, thus boosting the localization performance for events. Extensive experiments show that our method outperforms state-of-the-art methods in both pseudo-label and AVVP performance.
Authors: Weiren Zhao, Yi Dong, Cheng Chen
Abstract: Unifying multimodal understanding and generation is a compelling frontier that is beginning to emerge in the medical field. However, the limited existing unified medical models typically treat understanding and generation as disjoint objectives, lacking a meaningful functional synergy. In this work, we identify and address a critical question in unified medical modeling: what form of understanding truly benefits generation. We present SynerMedGen, a unified framework built on the proposed principle of generation-aligned understanding, which synergizes understanding objectives with generation tasks via task alignment. SynerMedGen introduces three generation-aligned understanding tasks and a two-stage training strategy that transfers generation-beneficial representations learned during understanding training to medical image synthesis. Remarkably, even with understanding training alone, our SynerMedGen achieves strong zero-shot performance across 22 medical image synthesis tasks and demonstrates robust generalization to unseen datasets. When combined with generation training, SynerMedGen consistently outperforms state-of-the-art specialized medical image synthesis models as well as recent unified medical models. We also release a large-scale dataset named SynerMed consisting of 1M paired synthesis samples and 2M generation-derived understanding instances to support further research on understanding-generation synergy. Our project can be accessed at https://github.com/Mhilab/SynerMedGen.
Authors: Jiaming Liang, Chi-Man Pun, Weisi Lin, Greta Seng Peng Mok
Abstract: Learned image compression (LIC) integrates deep neural networks (DNNs) to map high-dimensional images into compact latent representations, reducing redundancy and achieving superior rate-distortion (RD) performance in benign settings. Unfortunately, due to inherent vulnerabilities in DNNs, LIC systems are susceptible to adversarial perturbations that lead to downstream deterioration, compression rate degradation, untargeted distortion, and both local semantic manipulation (LSM) and low-resolution ($3\times28\times28$) global semantic manipulation (GSM). However, high-resolution GSM remains unexplored due to its intractability. Notably, the existing project gradient descent (PGD) method achieves near-perfect white-box attacks for classification, segmentation, and other tasks, yet fails to generalize to high-resolution GSM. Our theoretical and empirical analyses reveal that well-performing GSM drives adversarial examples from the Identity Region to the Amplification Region through the Lazying-Oscillating-Refining stages. General $\ell_{\infty}$-bounded attacks fail on high-resolution GSM because their step-size schedules cannot accommodate both the Oscillating and Refining stages. Based on this, we propose the Periodic Geometric Decay schedule that enables $\ell_{\infty}$-bounded high-resolution GSM. To verify our approach, we integrate it with PGD, yielding a minimal variant, PGD$^{2}$-GSM. Extensive experiments on the Kodak $(3\times768\times512)$ demonstrate that our PGD$^{2}$-GSM is the first to stably achieve high-resolution GSM, thereby exposing a novel threat to LIC systems. Code is available at https://github.com/chinaliangjiaming/PGD2-GSM.
Authors: Shihao Cheng, Jiaxu Zhang, Quanyue Song, Shansong Liu, Zhizhi Guo, Xiaolei Zhang, Chi Zhang, Xuelong Li, Zhigang Tu
Abstract: Motion, speech, and sound effects are fundamental elements of human-centric videos, yet their heterogeneous temporal characteristics make joint generation highly challenging. Existing audio-video generation models often fail to maintain consistent alignment across these modalities, leading to noticeable mismatches between motion, speech, and environmental sounds. We present Unison, a unified framework that explicitly promotes coherence across the motion, speech, and sound modalities. Within the audio stream, Unison employs a semantic-guided harmonization strategy that decouples the generation of speech and sound-effect components. Leveraging bidirectional audio cross-attention and semantic-conditioned gating for semantic-driven adaptive recomposition, this approach effectively mitigates speech dominance and enhances acoustic clarity. For audio-motion synchronization, we propose a bidirectional cross-modal forcing strategy where the cleaner modality guides the noisier one through decoupled denoising schedules, reinforced by a progressive stabilization strategy. Extensive experiments demonstrate that Unison achieves state-of-the-art performance in both audio perceptual quality and cross-modal synchronization, highlighting the importance of explicit multimodal harmonization in human-centric video generation.
Authors: Joowon Kim, Seungho Shin, Joonhyung Park, Eunho Yang
Abstract: Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on goal-directed tasks: long-horizon drift on multi-step tasks and mid-clip simulation errors that compound. Both stem from the absence of explicit reasoning built upon the VGM's short-horizon visual prior, a role naturally filled by Vision-Language Models (VLMs), but where to place the VLM is non-trivial: upfront plans commit before any frame is generated and post-hoc critiques over whole videos intervene too late. We propose VLM-VGM Collaborative Video Reasoning (CollabVR), a closed-loop framework that couples the VLM with the VGM at step-level granularity: the VLM plans the immediate next action, inspects the clip the VGM generates, and folds the verifier's diagnosis directly into the next action prompt to repair detected failures. On Gen-ViRe and VBVR-Bench, CollabVR improves both open-source and closed-source VGMs over single-inference, Pass@$k$, and prior test-time scaling baselines at matched compute, with the largest gains on the hardest tasks. It also yields further improvements on top of a reasoning-fine-tuned VGM, indicating that step-level VLM supervision is orthogonal to and stackable with reasoning-oriented fine-tuning. We provide video samples and additional qualitative results at our project page: https://joow0n-kim.github.io/collabvr-project-page.
Authors: Luchao Wang, Kaimin Liao, Qian Ren, Hua Wang, Zhi Chen, Yaohua Tang
Abstract: A converged 3D Gaussian Splatting (3DGS) model may approximate the target scene while remaining poorly parameterized for further optimization. We identify this failure mode as \emph{parameterization degeneration}: high-opacity floaters attenuate gradients to true surfaces through alpha compositing, and redundant overlapping clusters create strongly coupled parameter blocks with nearly collinear Jacobian responses. These effects explain why continued optimization can plateau even when the model still contains removable artifacts. We propose ReorgGS, an equivalent distribution reorganization method for converged 3DGS models. ReorgGS treats the existing Gaussian set as an empirical probability field, resamples centers from it, estimates local anisotropic covariances with kNN, initializes low opacity, and continues optimization with the original 3DGS renderer and loss. Unlike opacity reset, which only rescales opacity on the old overlap graph, ReorgGS rebuilds centers, covariances, and visibility structure, thereby changing the graph itself. Our analysis shows that distributional equivalence is not optimization equivalence. The reorganized model preserves scene support while improving gradient accessibility under alpha compositing and reducing opacity-weighted overlap, thereby weakening local parameter coupling during subsequent optimization. Under the same additional optimization budget, ReorgGS improves fitting quality at a fixed Gaussian count, suppresses persistent floaters, and reduces rendering overhead from redundant overlap.
Authors: Mariafrancesca Patalano, Giovanna Capizzi, Kamran Paynabar
Abstract: Advanced manufacturing technologies allow for the production of intricate parts featuring high shape complexity and spatially-varying material composition. Data fusion of point clouds with chromatic attributes provides 4D point clouds, a compact and informative representation that encodes both shape and material information. In this paper, we present a registration-free framework for Simultaneous Monitoring of shApe and Color (SMAC) via 4D point clouds. The proposed framework leverages Laplace-Beltrami operator spectral properties to capture and monitor geometric features and the relationship between shape and surface color. A combined monitoring scheme is proposed to effectively detect shape deformations and color anomalies, along with a spatially-aware post-signal diagnostic procedure to determine the source of change and localize color anomalies. Importantly, neither component relies on registration or mesh reconstruction, eliminating error-prone and computationally expensive preprocessing steps. A Monte Carlo simulation study and a case study on functionally graded materials demonstrate that SMAC achieves effective detection performance, particularly for subtle defects, while providing diagnostic capabilities to identify the source and location of anomalies.
Authors: Jin Liu, Wang Wang, Hongxu Pu, Zhen Cao, Yasong Wang, Hu Wang, Kunming Luo
Abstract: AI-assisted bridge defect inspection often produces bounding boxes with crude geometry or raster masks that are costly to store, transmit, and reuse. This study investigates how detected defects can be represented as compact, recoverable contour-level vector records in image space. We propose Frequency-Supervised Fourier Series Detection (FS-FSD), which directly regresses Fourier contour descriptors and evaluates boxes, masks, and contours under a unified polygon-space protocol. On 3,767 UAV-collected bridge images with 42,346 defect instances, FS-FSD achieves higher polygon-space accuracy and better matched-TP geometric quality than representative detection, segmentation, and contour baselines. These results show that, compared with bounding boxes and raster masks, Fourier contour records preserve defect-boundary geometry in a more compact, recoverable, and shareable form for engineering review and downstream information workflows. Future work will study the modeling of multi-region, fragmented, and adjacent bridge-defect boundaries and extend the framework toward long-term bridge-defect tracking and lifecycle-oriented management.
Authors: Benlei Cui, Fangao Zeng, Weitao Jiang, Yuwen Zhai, Haiwen Hong, Longtao Huang, Hui Xue, Wenxiang Shang, Pipei Huang
Abstract: Product poster generation poses distinct challenges beyond general poster design, requiring both faithful preservation of product appearance and precise control over dense, multi-line text layouts. Prior methods typically adopt inpainting frameworks augmented with auxiliary modules such as ControlNet and OCR encoders. However, these approaches introduce architectural complexity and computational overhead while still suffering from text errors and subject extension artifacts. We present SimplePoster, a simple yet effective inpainting-based framework that achieves faithful subject preservation and accurate, position-controllable text rendering without external controllers. Our approach builds on two observations: (1) full-parameter fine-tuning of the base model effectively suppresses subject extension, outperforming ControlNet-based alternatives; and (2) a zero-cost character-level position encoding enables geometry-aware text generation without dedicated layout modules. Experiments show that SimplePoster achieves a $98.7\%$ subject preservation rate, compared to $55.2\%$ for SeedEdit 3.0 and $85.3\%$ for PosterMaker, while also improving text rendering accuracy. Code, models, benchmark and a part of training data will be available at https://github.com/Alibaba-YuFeng/SIMPLEPOSTER
Authors: Mashrafi Monon, Umaima Rahman, Asif Hanif, Numan Saeed, Mohammad Yaqub
Abstract: Recent advances in 3D medical vision-language models have enabled joint reasoning over volumetric images and text, showing strong performance in medical visual question-answering (VQA) and report generation. Despite this progress, it remains unclear whether these models learn spatially grounded anatomy from 3D volumes or rely primarily on learned priors and language correlations. This uncertainty stems from the lack of systematic evaluation of semantic-spatial reasoning in volumetric medical VLMs for clinically reliable decision support. To address this gap, we introduce CT-SpatialVQA, a benchmark designed to evaluate semantic-spatial reasoning in 3D CT data. The benchmark comprises 9077 clinically grounded question-answer (QA) pairs derived directly from 1601 radiology reports and CT volumes, which are validated via a robust LLM-assisted pipeline with a 95% human consensus agreement rate. Our dataset requires explicit anatomical localization, laterality awareness, structural comparison, and 3D inter-structure relational reasoning. We also introduce a standardized evaluation protocol and benchmark eight 3D medical VLMs, finding severe degradation on semantic-spatial reasoning tasks, averaging 34% accuracy and often below random, highlighting the need for deeper integration of volumetric evidence for trustworthy clinical use.
Authors: Jiahui Guang, Zexun Zhan, Zhenlin Xu, Cuiyun Gao, Haiyan Wang, Jing Li, Zhaoquan Gu, Yanchun Zhang
Abstract: Multimodal Large Language Models (MLLMs) may memorize sensitive cross-modal information during pretraining. However, existing MLLM unlearning benchmarks rely on synthetic knowledge injection or complete subject-level deletion, which fail to capture realistic, personalized deletion requests that require fine-grained factual control. In this paper, we introduce PPU-Bench, a real-world and fine-tuning-free benchmark for personalized partial unlearning in MLLMs. PPU-Bench contains 24K multimodal and unimodal samples derived from pre-existing knowledge of 500 public figures under three progressively challenging settings: Complete, Selective, and Personalized unlearning. The benchmark evaluates whether methods can remove target knowledge while preserving non-target facts, model utility, and cross-modal consistency. Extensive experiments show that Complete Unlearning often suppresses visual identity rather than factual knowledge, while Selective and Personalized Unlearning expose significant forget--retain trade-offs and challenges in intra-subject factual boundaries. Robustness analysis under cross-image and prompt-based attacks reveals distinct vulnerabilities across different unlearning settings. Motivated by these findings, we propose Boundary-Aware Optimization (BAO), which explicitly models intra-subject forget-retain boundaries. Experimental results on two representative methods demonstrate that BAO can effectively enforce intra-subject factual boundaries.
Authors: Ziyang Ding, Linjian Meng, Yiming Wu, Yuhan Li, Yuhao Liu, Zhen Zhao
Abstract: Due to the potential for exploratory reasoning of Latent Visual Reasoning, recent works tend to enable MLLMs (Multimodal Large Language Models) to perform visual reasoning by propagating continuous hidden states instead of decoding intermediate steps into discrete tokens. However, existing works typically rely on hard alignment objectives to force latent representations to match predefined visual features, thereby severely limiting the exploratory of latent reasoning process. To address this problem, we propose CoLVR (Contrastive Optimization for Latent Visual Reasoning). To obtain a more exploratory visual reasoning, CoLVR introduces a latent contrastive training framework. Firstly, CoLVR learns diverse and exploratory representations with a latent contrastive objective guided by angle-based perturbation, which expands the semantic latent space and avoids over-constrained embedding. Then, CoLVR employs a latent trajectory contrastive reward for RL (Reinforcement Learning) post-training to enable fine-grained optimization of latent visual reasoning process and thus fostering diverse reasoning behaviors. Experiments demonstrate that CoLVR significantly enhances the exploratory capability of latent representations, achieving average improvements of 5.83% on VSP and 8.00% on Jigsaw, while also outperforming existing latent models on out of domain benchmarks, with a 3.40% gain on MMStar. The data, codes, and models are released at https://github.com/Oscar-dzy/CoLVR.
Authors: Qing Zhong, Guodong Ding, Lingqiao Liu, Zaiwen Feng, Lin Yuanbo Wu, Angela Yao
Abstract: Audio-Visual Segmentation (AVS) targets pixel level localization of sounding emitting objects in videos. However, existing models rely on dense cross-modal attention with quadratic computational cost, limiting their suitability for resource efficient deployment. Most efficiency oriented methods focus on backbone reduction and overlook the interaction module as the primary bottleneck. This paper proposes LightAVSeg, a lightweight framework that replaces heavy attention with a decoupled design for semantic filtering and spatial grounding, resulting in interaction costs that scale linearly with spatial resolution. Furthermore, we introduce an auxiliary alignment loss to enforce semantic consistency during training with zero inference overhead. Extensive experiments demonstrate that LightAVSeg achieves a new state-of-the-art among lightweight methods: with 20.5M parameters ~1/7 of AVSegFormer), it reaches 50.4 mIoU on the MS3 benchmark and enables efficient inference on a mobile processor.
Authors: Zehua Wang, Changwang Mei, Huaijiang Sun, Pengqi Hu, Zhaoyang Yin
Abstract: Existing 2D-3D lifting human pose estimation methods have achieved strong performance. But the utilization of historical pose representations across network depth was overlooked. In current pipelines, information is propagated through fixed residual connections, which restricts effective reuse of early-layer features such as fine-grained spatial structures and short-term motion cues. However, naively incorporating historical features across layers is non-trivial. We further identify that maintaining a consistent representation space across layers is a prerequisite for effective cross-layer feature aggregation. To address this issue, we propose a history-aware framework that enables effective network cross-layer history feature utilization. Specifically, we adopt a spatial-temporal parallel Transformer backbone to prevent alternating spatial-temporal transformations during sequential processing, thereby maintaining a consistent representation space. Building upon this, we introduce a History Pose Accumulation (HPA) mechanism that adaptively aggregates features from all preceding layers to enhance current representations. Furthermore, we propose a Layer Pose History Aggregation (LPA) module that transforms layer pose features into a compact and structured form, reducing redundancy and enabling more stable aggregation. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on benchmarks.
Authors: Ziyao He, Yingjie Liu, ZhangYangRui, Mingsong Chen, Xuan Tang, Xian Wei
Abstract: Accurate 3D scene description is fundamental to robotic navigation and augmented reality, yet current dense captioning methods face significant limitations in processing sparse point cloud data. % Existing approaches that apply Euclidean embedding spaces struggle to simultaneously preserve fine-grained local geometric details and model exponentially growing global semantic hierarchies, leading to either inaccurate localization or disjointed, shallow scene descriptions. % In this work, we propose a novel \textbf{\textsc{Curvature-Aware Captioning}} framework, integrating novel non-Euclidean geodesic attention mechanisms, to resolve the localization-contextualization conflict. % Specifically, self-attention within Oblique space enforces dimensional homogeneity while establishing long-range dependencies. Bidirectional geodesic cross-attention within Lorentz space models hierarchical semantic relationships across scene instances, enabling simultaneous precision in object localization and coherence in scene descriptions. % Theoretical analysis confirms that the curvature complementarity between the Oblique manifold and Lorentz hyperboloid resolves the Euclidean-hyperbolic conflict, ensuring feature stability via isotropic optimization while preserving inherent hierarchical relationships. Extensive experiments on ScanRefer and Nr3D benchmarks demonstrate state-of-the-art performance, with significant gains in both localization accuracy and descriptive richness.
Authors: Wei Cao, Hao Xu, Xiaolei Diao
Abstract: Chinese character categories are extremely large, and unseen characters frequently arise in open-world scenarios, making zero-shot Chinese character recognition an important yet challenging problem. Existing IDS-based retrieval methods usually encode a character image and its ideographic description sequence into a single global vector for matching. Although efficient, such holistic alignment often under-models local component differences. Moreover, directly introducing patch-token level fine-grained interaction suffers from both the noise of structural operators in IDS and the high cost of full-candidate retrieval.To address these issues, we propose a Global-Local Hierarchical Perception Network (GL-HPN), which jointly learns global and local representations of character images and IDS sequences within a unified cross-modal alignment framework. The global branch supports efficient coarse recall, while the local branch improves component-level discrimination through patch-token interaction. We further introduce a structure filtering mask to suppress structurally meaningful but visually non-entity IDS operators in local similarity aggregation. On top of this, we design a coarse-to-fine hierarchical inference strategy that performs global retrieval over the full candidate set and local reranking only on Top-$K$ candidates, followed by parameter-free multiplicative fusion of normalized posterior scores. Experimental results show that GL-HPN achieves competitive performance across multiple zero-shot splits, performs especially well under low-resource settings, and substantially reduces the inference cost of large-scale candidate retrieval.
Authors: Felix Krones
Abstract: Deep learning techniques have revolutionised medical imaging, improving diagnostic accuracy and enabling both more accurate and earlier disease detection. However, the relationship between pre-training strategies and downstream performance in medical imaging models requires further exploration. Here, we systematically compare convolutional neural networks and transformers, examining various pre-training approaches, including supervised and self-supervised learning, as well as different initialisations and data modalities. Models are evaluated on natural images, chest X-rays, chest CT and retina OCT images, considering the effects of matching pre-training data with target modalities. Our findings indicate that only pre-training on data closely matching the target modality significantly improves downstream performance. While self-supervised learning can outperform supervised methods, its effectiveness varies with context. The study underscores the importance of pre-training strategies to enhance the reliability and effectiveness of deep learning models in medical imaging. By addressing these key factors, our research aims to contribute to the development of more accurate and dependable diagnostic tools, ultimately improving patient outcomes in clinical settings.
Authors: Xinyu Yan, Boyang Chen, Jiaming Zhang, Tiantong Wu, Hong Xi Tae, Yichen He, Tiantong Wang, Yachun Mi, Yurong Hao, Yilei Zhao, Lei Xiao, Longtao Huang, Pengjun Xie, Wei Liu, Wei Yang Bryan Lim
Abstract: Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to concrete real-world claims, creating new challenges for verifying visual evidence. A concrete emerging risk is AI-generated refund fraud, in which manipulated or synthetic images are used to support claims about damaged products, poor delivery conditions, or service-related defects. Existing AI-generated image detection benchmarks mainly evaluate standalone authenticity classification, cross-generator transfer, or forensic localization, leaving claim-conditioned fraudulent evidence detection underexplored. To bridge this gap, we introduce FraudBench, a multimodal benchmark for detecting AI-generated fraudulent refund evidence. FraudBench is constructed from real-world user-review evidence across e-commerce, food delivery, and travel-service scenarios. We curate real evidence images together with their associated review and product metadata, identify genuine damaged and undamaged evidence through MLLM-assisted filtering and human annotation, and synthesize fake-damaged evidence from genuine undamaged reference images using six state-of-the-art image editing and generation models. Using FraudBench, we evaluate MLLMs, specialized AI-generated image detectors, and human participants under the same settings. Experiments show that current MLLMs often recognize real-damaged evidence but fail on many fake-damaged subsets, with fake-damage detection rates (TPR) far below the 50% baseline on most generator subsets. Specialized detectors generally perform better but remain inconsistent across generators and can produce false positives on real-damaged samples, revealing a clear gap between generic AI image detection and reliable claim-conditioned refund-evidence verification.
Authors: Meisen Wang, Hao Deng, Wei Bao, Ma Yuanxiao, Chengjie Wang, Zhiqiang Tian, Shaoyi Du, Siqi Li
Abstract: Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion and challenging illumination conditions. However, existing Event-based Object Detection (EOD) methods face limitations at both the representation and model levels: prior event representations usually encode temporal information indirectly through redundant structures, while detection models struggle to explicitly aggregate fragmented event responses into coherent high-order object features. To address these limitations, we present Event Dual Temporal-Relational Aggregation Detector (Ev-DTAD), a unified EOD framework that integrates representation-level temporal encoding with model-level temporal-hypergraph reasoning. Specifically, we introduce Hierarchical Temporal Aggregation (HTA), a compact three-channel pseudo-RGB representation that explicitly embeds temporal information across intra- and inter-window events. To further enhance detection under sparse and fragmented event responses, we propose Frequency-aware Hypergraph Temporal Fusion (FHTF), which refines multi-scale event features through temporal evolution modeling and high-order relational reasoning. Extensive experiments on Gen1 (+0.8 mAP and 1.7$\times$ faster), 1Mpx/Gen4 (+0.5 mAP and 1.6$\times$ faster), and eTraM (+3.0 mAP and \textbf{2.0$\times$ faster}) demonstrate that Ev-DTAD achieves a competitive accuracy-efficiency trade-off, validating the complementarity between compact temporal representation and temporal-hypergraph feature reasoning.
Authors: Rui Zhao, Jianlin Yu, Zhenhai Gao, Jiaqiao Liu, Fei Gao
Abstract: End-to-end autonomous driving requires models to understand traffic scenes, infer driving intent, and generate executable motion plans. Recent vision-language-action (VLA) models inherit semantic priors from large-scale vision-language pretraining, yet still face a coupling trade-off: fully shared backbones preserve multimodal interaction but may entangle language reasoning and trajectory prediction, whereas decou pled reasoning-action pipelines reduce task conflict but weaken semantic-motion coupling. We propose VECTOR-DRIVE, a tightly coupled VLA framework built on Qwen2.5-VL-3B. VECTOR-DRIVE keeps all tokens coupled through shared self attention and routes feed-forward computation according to token semantics. Vision and language tokens are processed by a Vision-Language Expert to preserve semantic priors, while target-point, ego-state, and noisy action tokens are routed to a Trajectory Expert for motion-specific computation. On the action-token pathway, a flow-matching planner refines noisy action tokens into future waypoints and speed profiles. This design couples semantic reasoning and motion planning within a single multimodal Transformer while separating task-specific FFN computation. On Bench2Drive, VECTOR-DRIVE achieves 88.91 Driving Score and outperforms representative end-to end and VLA-based baselines. Qualitative results and ablations further validate the benefits of shared attention, semantic-aware expert routing, progressive training, and flow-based action de coding.
Authors: Zhen-Hao Xie, Yan Wang, Hao Sun, Han-Jia Ye, De-Chuan Zhan, Da-Wei Zhou
Abstract: Class-Incremental Learning (CIL) requires a learning system to learn new classes while retaining previously learned knowledge. However, in real-world scenarios such as autonomous driving, a system trained on urban roads in sunny weather may later need to operate in rural or highway environments with different traffic patterns and weather conditions. This requires the model not only to overcome catastrophic forgetting, but also to effectively handle domain shifts. In this paper, we propose CrOss-sample Relational Fusion (CORF), a unified framework to address domain shift and catastrophic forgetting simultaneously. To enhance generalizability, we perform selective refinement of training samples by leveraging spatial contribution maps to highlight semantically informative regions. Furthermore, we incorporate predictive confidence to adaptively weigh samples, thereby facilitating the learning of domain-agnostic representations. To alleviate forgetting, we propose a cascaded distillation framework that captures cross-sample relational dependencies across multiple feature hierarchies, enabling multi-grained knowledge transfer from previous tasks. CORF can be seamlessly integrated into existing CIL algorithms to enhance their generalizability, achieving competitive performance across various benchmark datasets. Code is available at https://github.com/LAMDA-CL/TMM26-CORF .
Authors: Junli Zha, Jiahui Wang, Xinkai Lu, Jinbo Wang
Abstract: Vision-Language Models (VLMs) exhibit systematic bias toward visual illusions, recalling memorized facts rather than perceiving actual visual differences. This paper presents a training-free framework for the 5th DataCV Challenge Task 1 at CVPR 2026, addressing this perception-versus-memory conflict through three complementary strategies:(1) illusion-aware image preprocessing that weakens illusion-inducing context via type-specific transformations (edge extraction, color isolation, morphological processing, and reference-line overlay), (2) anti-illusion prompt engineering guiding VLMs toward qualitative visual comparison, and (3) multi-vote ensemble that further improves robustness. Our method achieves 90.48% accuracy on the official 630-image test set using Claude (claude-opus-4-6) with 5-vote majority ensemble, and 98.41% on a human-verified subset. The approach requires no finetuning, relying solely on visual manipulation and prompt design. Our solution secured 2nd place in the challenge, only 0.47% behind the 1st-place solution. Code is available at https://github.com/jasminezz/sf-illusion-aware-vlm.git.
URLs: https://github.com/jasminezz/sf-illusion-aware-vlm.git.
Authors: Jialin Li, Zhuo Zhang, Yue Cao, Guipeng Lan, Jiabao Wen, Shuai Xiao, Jiachen Yang
Abstract: The scarcity of high-quality imaging data for coronary angiography (CAG) stenosis limits the clinical translation of automated stenosis detection. Synthetic stenosis data provides a practical avenue to augment training sets, improving data quality, diversity, and distributional coverage, and enhancing detection precision and generalization. However, diffusion-based editing commonly relies on soft guidance in a noise-initialized reverse process, offering limited pixel-level precision and structure preservation. We propose the OT-Bridge Editor, which reframes localized editing as a constrained entropic optimal transport (OT) problem and leverages geometric information to steer the generation path, enabling stronger geometric control. Extensive experiments show that our synthesized angiograms consistently improve downstream stenosis detection, yielding substantial relative gains of 27.8% on the public ARCADE benchmark and 23.0% on our multi-center dataset, supported by consistent qualitative results.
Authors: Insoo Kim, Jinwoo Shin
Abstract: Generative flow models offer powerful priors learned from large-scale natural images, but directly adapting them to restoration tasks such as motion deblurring causes severe fidelity degradation, as their training objective is inherently misaligned with restoration. We present DeblurFlow, a framework that resolves this misalignment by reformulating the flow trajectory itself: we replace the noise endpoint with the blur observation, which makes the underlying vector field coincide with the residual error between blur and clean images. Under this formulation, the standard flow matching loss naturally takes the form of a residual loss, allowing pretrained flow models to be optimized under restoration-aligned objectives via LoRA adaptation. This formulation further enables a dual-expert sampling strategy: a fidelity expert provides a high-fidelity initialization, e.g., PSNR 33.69 dB, and DeblurFlow enhances perceptual quality with only a marginal fidelity reduction to 33.05 dB, whereas directly applying a generative model on top of a fidelity expert decreases PSNR to 27.60 dB. To make this practical, we further introduce r-space, a latent space tailored for residual decoding rather than image reconstruction, which reduces encoder-decoder cost by up to 9$\times$over standard VAE latents. Extensive experiments on GoPro, HIDE, RealBlur, and RWBI demonstrate that DeblurFlow achieves strong restoration fidelity and perceptual realism, while remaining computationally practical.
Authors: Piotr Borycki, Magdalena Tr\k{e}dowicz, Jacek Tabor, {\L}ukasz Struski, Przemys{\l}aw Spurek
Abstract: Ante-hoc interpretability methods based on prototypes provide highly accurate explanations by utilizing the intuitive "this looks like that" reasoning paradigm. On the other hand, post-hoc models can explain predictions for a single image without relying on an underlying dataset or requiring costly neural network retraining. Recent approaches successfully solve the retraining problem for prototype-based networks. However, they still face a fundamental limitation: they require access to a subset of data (e.g., a test or validation set) to search for and extract the visual prototypes. In this paper, we address this issue and introduce ProDG: Generative Prototypes for Data-Free Post-Hoc Explainability, a novel framework that leverages generative models to synthesize pure, high-fidelity prototypes directly from the frozen model's weights, completely eliminating the dependency on any external data. By establishing this new frontier in Data-Free XAI, ProDG unlocks robust visual interpretability for privacy-sensitive domains, where original data is strictly restricted or fundamentally inaccessible. Project page: https://github.com/piotr310100/ProDG
Authors: Hoang M. Truong, Hai Nguyen-Truong, Dang Huynh
Abstract: Open-vocabulary semantic segmentation requires adapting image-level vision-language models such as CLIP to dense pixel-level prediction, which is challenging due to the mismatch between hierarchical structure and semantic alignment in the embedding space. While recent works leverage hyperbolic geometry to model hierarchical relationships, they align embeddings across hierarchical levels but overlook semantic misalignment among embeddings within the same level. In this work, we propose HyRo, a hyperbolic fine-tuning framework that decouples hierarchical and semantic alignment in the Poincar\'e ball model. HyRo aligns hierarchical levels by adjusting the hyperbolic radius and refines semantic relationships through angular alignment using an orthogonal transformation that theoretically preserves the hyperbolic radius. Experiments on standard open-vocabulary semantic segmentation benchmarks demonstrate that HyRo achieves state-of-the-art performance over prior methods.
Authors: Mengyuan Tian, Qiyan Zhao, Yanan Wang, Da-Han Wang
Abstract: In recent years, pre-trained visual-linguistic models have demonstrated tremendous potential, becoming a crucial foundational framework for numerous downstream tasks. However, the information density between text and images is not uniformly distributed. Existing methods often overlook the inherent and dynamic differences in information density and semantic scope between text tags and image blocks. These common uniform alignment strategies result in coarse-grained cross-modal interactions and loss of fine semantic details. Moreover, pursuing finer alignment typically requires substantial computational overhead, limiting practical model deployment. To address this challenge, this paper proposes a novel framework for dynamic cross-modal alignment with continuous detail introduction. First, we design a dynamically adaptive cross-modal matching mechanism that uses a learnable matching function to dynamically assign varying numbers and sizes of image tags to text tags of the same size but different information density, enabling more precise attention interaction. Second, we develop a continuous detail introduction module to progressively incorporate high-resolution visual feature enhancement into the alignment process. Extensive experiments across multiple benchmarks demonstrate significant improvements in the accuracy of various downstream tasks while reducing computational overhead.
Authors: Han Li, Yulu Gao, Si Liu, Yuhang Wang, Bo Liu, Beipeng Mu
Abstract: Autonomous vehicles need to perceive not only physical elements in the driving scene, such as lane lines and traffic lights, but also logical elements like lane centerlines and their topology. Existing lane topology reasoning methods typically follow a reasoning-by-detection paradigm, where lane topological relationships are primarily derived from lane detection results. In this paper, we propose an innovative method called Unified Modeling of Lane and Lane Topology (UniTopo), which represents the topological relationships between lanes as connected lanes, encompassing predecessor lanes, successor lanes, and their interconnections. This unified representation of lanes and lane topology allows us to simultaneously obtain both the positions and topological information of lanes within a shared perception pipeline, establishing a new paradigm for directly perceiving lane topology from original image features. We validate our method on the driving scene reasoning benchmark OpenLane-V2, which consists of two subsets, built based on Argoverse2 and nuScenes, respectively. Our method achieves TOP_ll of 30.1% and 31.8% on the two subsets, significantly surpassing the existing state-of-the-art method T^2SG by 6.0% and 8.6%.
Authors: Xueyang Kang, Zijian Yu, Kourosh Khoshelham, Liangliang Nan
Abstract: Interactive segmentation allows efficient label generation by leveraging user-provided clicks to progressively refine predictions, which is critical when fully supervised labels are costly or generalization to unseen classes is needed. Existing 3D interactive methods are limited: most operate sequentially, predicting only one object per iteration with binary masks, while several recent approaches depend on 2D foundation models and camera alignment to bridge the 2D-3D gap. To address these limitations, we propose a novel interactive segmentation framework that operates directly on sparse, randomly downsampled 3D points and processes multiple object clicks in a single forward pass. Our framework consists of a point Transformer-based encoder and a hierarchical mask decoder, which integrates multi-level crop-and-merge operations conditioned on learnable semantic embeddings. Unlike prior interactive approaches that require repeated model updates after each manually corrective click, our method jointly reasons over all click queries, modeling inter-instance relationships and refining both spatial masks and semantic predictions through spatial and semantic embeddings. Extensive experiments demonstrate that our model improves the mIoU metric by over 20 percent compared to strong baselines and achieves 8-10 percent gains under cross-dataset evaluation for a one-click per instance setting, often requiring only a single click per object. Our approach provides a generalizable and efficient solution for interactive 3D instance segmentation, particularly suitable for real-time applications such as robotic manipulation, navigation, and rapid 3D semantic annotation.
Authors: Qiqi Li, Pengfei Wang, Nenggan Zheng
Abstract: Action quality assessment (AQA) aims to automatically quantify the execution quality of human actions in videos and is valuable for applications such as competitive sports judging. In multimodal AQA, quality evidence from different modalities is heterogeneous, and quality cues evolve progressively over time. Existing methods often rely on coarse fusion or unified temporal modeling, which may blur modality-specific cues, preserve cross-modal redundancy, and weaken stage-specific quality evidence. To address these issues, we propose a progressive implicit decoupling and fusion network (PIDNet) that progressively integrates modality-specific information, cross-modal complementary cues, and global quality semantics for accurate assessment. Specifically, we design an iMambaWave module that maps RGB, optical flow, and audio features into a shared latent space and disentangles them with a Bi-Mamba branch and a wavelet-transform branch to capture long-range temporal dependencies and local perturbation details, respectively. A gated aggregation mechanism adaptively fuses temporal and frequency-domain information. We further build a three-stage progressive fusion network using Group3M blocks, where modality complementary attention retrieves cross-modal evidence while suppressing redundancy, and multi-scale convolutions enrich feature representations. Experiments on the Rhythmic Gymnastics and Fis-V datasets show that PIDNet achieves highly competitive score correlation with favorable error control compared with existing unimodal and multimodal methods. Ablation studies verify the effectiveness of each component. Moreover, iMambaWave consistently improves visual representation and temporal modeling across multiple backbones, showing good generalization and plug-and-play capability.
Authors: Yu Li, Volker Schwieger
Abstract: In LiDAR-based environment perception systems, ground segmentation is a key preprocessing step supporting various applications such as mapping and navigation. Although extensively studied, problems such as reflection noise and isolated ground remain challenging. To address these issues, we propose FugSeg, a fast uncertainty-aware ground segmentation method. A polar grid map is adopted as the point cloud representation to ensure generalizability across LiDAR types. Building on that, we develop a within- and cross-segment ground labeling strategy that identifies not only directly visible ground cells but also those that are isolated or occluded. During this process, an adaptive slope is introduced, which incorporates measurement uncertainties to enhance its reliability under complex terrain. Finally, to achieve point-level ground segmentation, a fine-grained ground elevation estimation method is introduced. Throughout the complete workflow, reflection noise is explicitly handled via the proposed noisy ground cells. We conduct comprehensive evaluations on four public datasets covering both structured and unstructured environments. Results show that FugSeg outperforms state-of-the-art non-learning methods, achieving the highest F1, accuracy, and mIoU across all datasets, while maintaining the fastest runtime (135 Hz and 487 Hz for 64- and 32-layer LiDARs) using a single CPU thread, making it suitable for resource-limited systems. The code will be available at https://github.com/Leo-YuLi/FugSeg.
Authors: Naeun Lee, Hyunjong Kim, Sunghwan Choi, Injin Kong, Yohan Jo
Abstract: Despite strong performance of Multimodal Large Language Models (MLLMs) on multimodal tasks, predicting whether and why an image is persuasive remains challenging. We first show that prompting MLLMs to reason before prediction does not consistently help, and can even reduce persuasiveness prediction performance, suggesting that naively generated rationales are unreliable signals for this task. Yet, no established methodology exists for training MLLMs to reason about visual persuasion or evaluating whether their rationales faithfully support their decisions. To address this gap, we show empirically and theoretically that diverse teacher-generated rationales, when used for supervised fine-tuning, improve visual persuasiveness prediction. We further introduce a three-dimensional faithfulness evaluation framework covering rationale-to-decision consistency, rationale-to-image groundedness, and rationale-to-decision sensitivity. Applying this framework shows that prediction performance alone does not guarantee faithful rationales, while rationale-to-decision sensitivity is most aligned with human rationale preferences. These findings motivate faithfulness-aware training objectives and scalable rationale supervision for visual persuasiveness evaluation. Our code and dataset will be made publicly available.
Authors: Said Harb, Mehdi Maboudi, Markus Gerke
Abstract: Computer-Aided Design is ubiquitous in todays world, as almost every manufactured object begins as a digital model across industries. At the same time, advances in 3D sensing have made point clouds a dominant form of raw 3D data. Recovering the CAD model of a physical object from its point cloud scan has two major applications: reverse engineering, where physical or hand-crafted prototypes need to be reconstructed automatically as editable digital models, and quality control, where recovering the CAD description of a manufactured object helps quantify and understand deviations introduced during the production process. Thus, converting unordered point clouds into structured CAD models is increasingly important for modern applications. Deep learning has enabled major progress in computer vision for both 2D and 3D data, and new datasets facilitate data-driven CAD reconstruction. Building on this foundation, we develop an end-to-end model that reconstructs CAD models from point clouds and introduce a segmentation approach that decomposes them into individual extrusions. These partial shapes increase data diversity, improving the generalization and robustness of deep learning models. Our strategy thereby provides a simple, yet effective way to increase reconstruction performance of deep learning models.
Authors: Tri Cao, Khoi Le, Thong Nguyen, Cong-Duy Nguyen, Quynh Vo, Anh Tuan Luu, Chunyan Miao, See-Kiong Ng, Shuicheng Yan, Bryan Hooi
Abstract: While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We argue this stems from a failure in spatio-temporal monitoring, the ability to persistently track object identities, states, and relations over time. Existing benchmarks obscure this deficit by relying on single final-answer evaluations for queries that can often be resolved via local visual cues or statistical priors. To rigorously diagnose this, we introduce STEMO-Bench (Spatio-TEmporal MOnitoring), a benchmark of human-verified object-centric facts that evaluates intermediate reasoning by decomposing queries into sub-questions, distinguishing genuine temporal understanding from coincidental correctness. To address failure modes exposed by STEMO, we propose STEMO-Track, a novel object-centric framework that explicitly constructs and reasons over structured object trajectories via chunk-wise state extraction and temporal aggregation. Extensive experiments demonstrate that our object-centric framework significantly reduces hallucinated answers and improves spatio-temporal reasoning consistency over state-of-the-art MLLMs.
Authors: Kechen Fang, Yihua Qin, Chongyi Wang, Wenshuo Ma, Tianyu Yu, Yuan Yao
Abstract: Visual encoding constitutes a major computational bottleneck in Multimodal Large Language Models (MLLMs), especially for high-resolution image inputs. The prevailing practice typically adopts global encoding followed by post-ViT compression. Global encoding produces massive token sequences, while post-ViT compression incurs the full quadratic attention cost of the ViT before any token reduction takes place. In this work, we revisit this convention along two dimensions: the encoding strategy and visual token compression. First, controlled experiments show that slice-based encoding outperforms global encoding across benchmarks, suggesting that preserving local details through sliced views can be more beneficial than applying global attention for fine-grained perception. Second, we introduce intra-ViT early compression, which reduces tokens in shallow ViT layers and substantially lowers visual-encoding FLOPs while preserving downstream performance. By integrating intra-ViT compression into the slice-based encoding framework, we present LLaVA-UHD v4, an efficient and compute-controllable visual encoding scheme tailored for high-resolution inputs. Across a diverse set of benchmarks covering document understanding, OCR, and general VQA, LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% while matching or even surpassing baseline performance. These results suggest that visual-encoding efficiency can be substantially improved without sacrificing downstream performance, providing a practical design direction for efficient high-resolution MLLMs. All model weights and code will be publicly released to support further research.
Authors: Lavsen Dahal, Joseph Y. Lo
Abstract: In this retrospective multi-institutional study, a quantitative phenotyping framework, CT-IDP (CT Image-Derived Phenotypes) was developed on the MERLIN abdominal CT benchmark (training, validation, and test sets- 15,175, 5,018, and 5,082 studies, respectively) and externally evaluated on two independent dataset: Duke-Abdomen (2,000) and AMOS (1,107). Multi-organ segmentations were generated with TotalSegmentator and used to derive over 900 organ and compartment-level descriptors spanning morphometry, attenuation, and contextual/burden findings. Sparse disease-specific logistic regression with elastic-net regularization was trained on MERLIN and externally validated under a frozen specification. Performance was compared against a DINOv3-based vision-transformer baseline using AUC and average precision (AP), supported by phenotype-stratified audits and coefficient-level inspection. Macro-AUC for CT-IDP versus the baseline was 0.897 versus 0.880 on MERLIN, 0.877 versus 0.857 on the Duke-Abdomen dataset, and 0.780 versus 0.756 on AMOS.
Authors: Yixin Tang, Jiawei Guo, Junxian Li, Zhiteng Li, Jixin Zhao, Bingya Zhang, Chenbo Wang, Yulun Zhang, Shangchen Zhou
Abstract: Recently, diffusion-based object removal models have achieved impressive results in eliminating objects and their associated visual effects. However, they indiscriminately denoise all tokens across all timesteps, ignoring that removal usually involves small foreground regions. This strategy introduces substantial computational overhead and prolonged inference times. To overcome this computational burden, we propose a latent discriminator to implement Region-aware Adversarial Distillation (RAD), yielding a highly efficient few-step model named FlashClear. Furthermore, tailored to few-step diffusion models, we propose FPAC (Foreground-Prioritized Asymmetric Attention and Caching), a training-free acceleration strategy. Extensive experiments demonstrate that our framework provides massive acceleration while maintaining or exceeding the performance of our base model, ObjectClear. Notably, on the OBER benchmark, our FlashClear achieves up to 8.26$\times$ and 122$\times$ speedup over ObjectClear and OmniPaint, respectively, while maintaining high visual quality and fidelity.
Authors: Mikhail G. Mozerov
Abstract: This paper presents a novel Direct Integration Theorem (DIT), derived as a non-trivial corollary of the classical Central Slice Theorem (CST). The DIT provides a mathematically consistent transition from the continuous to the discrete domain - a fundamental challenge in computed tomography - thereby eliminating the need for frequency-domain interpolation without resorting to conventional ramp-filtering. The proposed approach circumvents two principal limitations inherent in traditional methods: (i) the zero-frequency singularity and spectral distortions introduced by the mandatory ramp-filtering step, and (ii) discretization inaccuracies associated with frequency-domain interpolation. Based on the DIT, we develop a rigorous framework for consistent discrete solutions of the inverse Radon problem. Mathematical modeling demonstrates that this approach achieves quasi-exact reconstruction, with errors constrained solely by sampling parameters and grid geometry. Furthermore, while Filtered Back Projection (FBP) inherently distorts the variance of the reconstructed image, the DIT-based algorithm preserves it. Comparative simulations confirm that the proposed method eliminates common artifacts, such as intensity cupping, and consistently outperforms FBP in terms of PSNR, SSIM, and reprojection fidelity, faithfully restoring the original image's statistical characteristics.
Authors: Adrian Azzarelli, Nantheera Anantrasirichai, James Pollock, David R. Bull
Abstract: Virtual production (VP) use LED walls to provide both background imagery and image-based lighting. While this enables on-set compositing, it couples lighting to background and scene appearance, limiting flexibility for downstream editing. In addition, inverse rendering conventionally relies on physically-based rendering to estimates 3D geometry and lighting, using environment maps. However, these maps are typically low-resolution and assume far-field lighting. In VP, with near-field and high-resolution image-based lighting, this can lead to inaccuracies and introduce complexities when editing. Addressing this, we propose a VP-specific framework for 3D reconstruction and relighting using Gaussian Splatting. This uses the known background imagery to condition the relighting process. This avoids relying on environment maps and reduces compositing to a background-image editing task. To realize our framework, we introduce a process (and associated dataset) that captures real VP scenes under varying background content and illumination conditions. This data is used to decompose a 3D scene into fixed appearance and variable lighting components. The variable lighting process simulates light transport by parameterizing each primitive with a UV coordinate, intensity value and resolution modifier. Using mipmaps, these directly sample the background texture in image space - implicitly capturing reflections and refractions without physically-based rendering. Combined with the fixed appearance component, this allows us to render relit scenes using a Gaussian Splatting rasterizer. Compared to baselines, our approach achieves higher-quality 3D reconstruction and controllable relighting. The method is efficient (<3 GB RAM, <5 GB VRAM, <2 hours training, ~35 FPS) and supports rendering useful arbitrary output variables including depth, lighting intensity, lighting color, and unlit renders.
Authors: Kiran Naseer, Naveed Anwer Butt
Abstract: Federated learning enables hospitals to collaboratively train segmentation models without sharing patient data. However, current evaluation protocols report only average performance across clients, masking failures at individual sites. In clinical deployment, a model that fails consistently at one hospital is a real safety risk that a good mean score can hide entirely. We introduce MedFL-Stress, a controlled stress-testing framework that exposes exactly this failure mode. Using 2D axial slices from BraTS 2020 distributed across four simulated hospital clients, we apply graded MRI appearance shifts (gamma contrast, scale-shift, and noise-plus-blur) reflecting scanner and acquisition variability in real multi-site deployments. Three federated baselines are evaluated: FedAvg, FedProx, and FedBN. Worst-hospital Dice and inter-hospital disparity are treated as primary metrics, not supplementary observations. FedAvg achieves the highest global mean Dice (0.8159) but conceals a 0.0850 gap between its best and worst-performing hospital. FedBN closes that gap by 41% (0.0850 to 0.0503) while sacrificing less than half a Dice point in mean accuracy (0.8159 to 0.8109), and the weakest hospital gains 3.5 Dice points outright (0.7309 to 0.7656). These findings demonstrate that robustness-oriented evaluation protocols are essential for reliable federated medical imaging deployment.
Authors: J\"org Frochte
Abstract: Raw cosine in the 768-dimensional output space of the Contrastive Style Descriptor (CSD) is now widely read as an absolute, calibrated style-fidelity score for text-to-image and style-imitation evaluation. We introduce the discrimination gap, a corpus-internal, prototype-free and threshold-free diagnostic that tests whether contrastive style cosines admit an absolute same-versus-different interpretation on a candidate artist corpus. On a 1799-artwork, 91-artist public-domain corpus, raw CSD cosine yields negative point-estimate gaps for $23/91$ artists at the pairwise level ($2/91$ robust under bootstrap) and for $15/91$ in the aggregated-pool scoring regime style-fidelity evaluations typically use. CSLS readout on the frozen backbone reduces the aggregated negative-gap count to $4/91$; combined with positional-embedding interpolation to $336$ pixels it raises unsupervised pair-verification AUC from $0.883$ to $0.905$ across $25$ artist-disjoint splits. We refer to this diagnostic-driven readout protocol on the frozen backbone (CSLS as default, pos-interp $336$ as the stronger optional setting) as CSD+, not a new encoder.A cross-backbone check on CLIP-ViT-L/14, SigLIP-large and DINOv2-Large reproduces the same shared-tradition failure pattern, providing evidence that the residual reflects a shared limitation of the four backbones we tested rather than a CSD-specific artefact. Practical implication: before reporting CSD cosine as an absolute style-fidelity score, run the diagnostic on the candidate corpus; CSLS is the minimal correction when it fails.
Authors: Timo Kleger, Qi Ma, Deheng Zhang, Luc Van Gool, Danda Pani Paudel
Abstract: We introduce SeasonScapes framework and a the SeasonScapes dataset: Swiss Sparse-view Mountain Scenes with Seasonal Changes that covers over 50 km x 60 km, composed of more than 85,000 webcam images captured from 32 different locations across 13 timestamps throughout a full year. By projecting these timestamp-specific images onto a 3D mesh, we construct seasonal 3D landscapes that reflect natural appearance changes over time. To address occlusions and missing data, we leverage conditional diffusion models for image-guided inpainting directly on the mesh. The resulting completed meshes can be further relighted using standard physically-based renderer.
Authors: Jiankun Peng, Jianyuan Guo, Yiguang Yang, Yue Liu, Jiashuang Yan, Ying Xu
Abstract: Online topological planning has become an effective paradigm for Vision-Language Navigation in Continuous Environments (VLN-CE), but existing methods still suffer from two limitations: redundant local depth information and weakened focus on current frontier candidates as the topological graph grows. To address this, we propose LCGNav, a modular local geometric enhancement framework for topological VLN. LCGNav explicitly converts candidate depth views into 3D point clouds and applies physical truncation based on the agent's reachable range, enabling more compact local geometric modeling. It further introduces a dimension-preserving local fusion strategy with transient state degradation, so that geometric enhancement is applied only to the currently relevant ghost nodes without changing the original planner interface. Experiments on R2R-CE and RxR-CE show that LCGNav serves as an effective cross-architecture enhancement module, consistently improving multiple key metrics of representative online topological baselines with low additional training cost. When integrated with ETP-R1, LCGNav achieves the best performance among the compared online topological methods on the val-unseen splits of the R2R-CE and RxR-CE benchmarks. The code is available at https://github.com/shannanshouyin/LCGNav.
Authors: Rajalaxmi Rajagopalan, Romit Roy Choudhury
Abstract: Scene graphs (SGs) represent objects and their relationships as structured graphs, enabling applications in image generation, robotics, and 3D understanding. Recent work suggests that conditioning image generation on scene graphs improves compositional fidelity compared to text-only prompting. However, since users typically provide text rather than structured graphs, a key challenge is to generate scene graphs from natural language. Prior work on discrete diffusion has demonstrated success in generating generic graphs such as molecules and circuits, but fails to account for the hierarchical structure and strong dependencies between objects, edges, and relations in scene graphs. We address this limitation by introducing a dependency-aware, hierarchically constrained discrete diffusion model for scene graph generation. Our approach decouples structure and semantics across the forward and reverse processes, enabling the model to capture conditional dependencies. At inference time, we perform training-free conditioning to sample text-aligned scene graphs. We evaluate our method on standard SG benchmarks and demonstrate improvements over both continuous and discrete graph generation baselines across graph and layout metrics. When fed to downstream image generation, our approach yields improved compositional alignment compared to text-to-image models, particularly in multi-object scenarios.
Authors: Francesco Chiumento, Gianluigi Crimi, Elisa Moretta, Rocco Milieri, Alberto Bazzocchi, Giulio Vara, Giacomo Dal Fabbro, Stefano Zaffagnini, Fulvia Taddei, Serena Bonaretti
Abstract: Purpose: To develop and evaluate cross-sequence transfer learning for automatic femoral cartilage segmentation, testing bidirectional transfer between dual-echo steady-state (DESS) and sagittal proton density-weighted 3D fast spin-echo (Cube) sequences. Materials and Methods: We optimized a modified 2D U-Net on 507 DESS images from the Osteoarthritis Initiative (OAI). We then established same-sequence baselines using subject-level cross-validation on a subset of 44 OAI DESS images and 44 Cube images acquired at the Istituto Ortopedico Rizzoli, Bologna, Italy. Each subset included 22 non-lesioned and 22 lesioned subjects. Finally, we performed transfer learning across sequences by fine-tuning the pretrained models on the target sequence with increasing training set sizes to study convergence, while keeping validation and test sets fixed. Segmentations were evaluated using Dice similarity coefficient (DSC) and average surface distance (ASD). Lesion effects were assessed with two-sided Mann-Whitney U tests with Bonferroni correction. Results: Same-sequence training yielded higher accuracy on DESS than Cube (DSC, $0.900$ vs $0.830$; $P < .001$). Cube-to-DESS transfer matched DESS performance (DSC, $0.903 \pm 0.032$ vs $0.900 \pm 0.027$), reaching a performance plateau at 9 training subjects. DESS-to-Cube yielded a lower combined DSC ($0.802 \pm 0.049$ vs $0.830 \pm 0.042$), reaching a plateau at 24 training subjects. Lesions did not affect DESS ($P \ge .39$) but reduced Cube accuracy (DSC, $0.805$ vs $0.856$; $P < .001$). Conclusion: Transfer learning across sequences can substantially reduce target-sequence annotation requirements for femoral cartilage segmentation, but performance is direction- and sequence-dependent, and the effects of lesions on segmentation may vary across MRI sequences.
Authors: Rohith Ramanan, A. N. Rajagopalan
Abstract: Score Distillation Sampling (SDS) and its variants have been widely used for text-to-3D generation by distilling 2D image diffusion priors. However, the standard SDS objective is prone to severe mode collapse, frequently yielding over-smoothed and over-saturated results. Although recent advancements, such as Score Distillation via Inversion (SDI), mitigate these artifacts and produce visually sharper models, they ultimately fail to faithfully capture the full target distribution. In this work, we show that the bottleneck limiting the sampling capacity of SDI stems from its reliance on the posterior mean estimator, which is mathematically equivalent to a single-step Euler approximation of the deterministic reverse DDIM trajectory. To address this, we propose a naturally motivated extension termed Probability-Flow Distillation (PFD). We establish that PFD corresponds exactly to a Wasserstein gradient flow, thereby inducing principled distribution-matching dynamics. Finally, we show that PFD can synthesize 3D assets with fine-grained, high-fidelity details and achieve improved quality compared to existing methods.
Authors: Abhishek Kumar, Riya Tapwal, Carsten Maple, Mark Hooper
Abstract: Digital identity verification systems used in remote onboarding rely on document images to authenticate users, making them vulnerable to localized manipulations of key identity fields such as facial photographs and textual information. Existing forgery detection methods, developed primarily for natural-image forensics, show limited transferability to structured identity documents. We propose FLiD, a lightweight field-localized framework that targets critical identity regions rather than processing full-document images. A fine-tuned object detector first localizes face and text fields; a frozen MobileNetV3-Small backbone then extracts compact field-level embeddings, which are classified by lightweight neural network with only 191K trainable parameters. FLiD achieves AUC scores of 0.880 (face), 0.954 (text), and 0.923 (both-field attacks), with corresponding EERs of 18.05%, 11.61%, and 15.16%, representing absolute reductions of 29-35 percentage points over a full-document baseline trained from scratch. FLiD also consistently outperforms general-purpose manipulation detectors (TruFor, MMFusion, UniVAD) across all attack scenarios while requiring 13x fewer parameters and 21x fewer FLOPs
Authors: Gabriele Lombardo, Luigi Maiorana, Liliana Lo Presti, Marco La Cascia
Abstract: Visual Grounding benchmarks assume that the object described by a referring expression is always present in the image, and grounding models are therefore rarely evaluated under semantically mismatched captions. In such cases, models frequently exhibit approximation behavior, producing a plausible bounding box that satisfies only part of the expression (\eg, preserving the original object while ignoring modified contextual cues). Because mismatched captions represent realistic edge cases, this behavior compromises reliability and raises concerns from an explainability perspective. Identifying its underlying causes is thus essential for improving model faithfulness and interpretability. Adopting a mechanistic interpretability viewpoint, this work examines whether embedding anisotropy contributes to counterfactual failures. A similarity-controlled counterfactual caption generation protocol is introduced to systematically perturb object or contextual components within predefined embedding similarity intervals, enabling a fine-grained analysis of grounding behavior as a function of alignment. Experiments on two Transformer-based models with markedly different embedding geometries (BERT-based TransVG and CLIP-based SwimVG) reveal no meaningful correlation between cosine similarity and approximation. These findings suggest that anisotropy alone does not account for counterfactual errors, and that robustness requires investigating finer-grained geometric properties of the embedding space.
Authors: Haozhe Luo, Shelley Zixin Shu, Ziyu Zhou, Robert Berke, Mauricio Reyes
Abstract: Vision--language models (VLMs) show promise for clinical decision support in radiology because they enable joint reasoning over radiological images and clinical text, thereby leveraging complementary clinical information. However, radiological findings are long-tailed in practice, leaving some conditions underrepresented and making zero-shot inference essential. Yet current CLIP-style medical VLMs are sensitive to prompt variations and often lack trustworthy external knowledge at inference time, which hinders reliable clinical deployment. We present \textit{KEPIL}, a prompt-robust framework that integrates curated medical knowledge to stabilize zero-shot generalization. KEPIL comprises: (i) \emph{dynamic prompt enrichment} using ontologies with LLM assistance, (ii) a \emph{semantic-aware contrastive loss} aligning embeddings of equivalent prompt variants via a dual-embedding objective, and (iii) \emph{entity-centric report standardization} to yield ontology-aligned representations. Across seven benchmarks, KEPIL achieves state-of-the-art zero-shot inference performance; under prompt-variation tests, it improves AUC by \(6.37\%\) on \textit{CheXpert} and by \(4.11\%\) on average. These results suggest that structured knowledge and robust prompt design are key to clinically reliable radiology-facing VLMs. Code will be released at https://github.com/Roypic/KEPIL.
Authors: Jingdong Zhang, Yizhou Wang, Zhengzhong Tu, Xin Li, Wenping Wang, Xiaohang Zhan
Abstract: Humanoid Visual Search (HVS) requires agents to actively explore immersive 360$^\circ$ environments. While prior methods treat this as a monolithic task relying on cumulative, multi-turn Chain-of-Thought (CoT) reasoning, they impose heavy cognitive burdens and require expensive trajectory-level annotations. In this paper, we propose Imagining in 360$^\circ$, a novel framework that decouples the exploration process into a specialized Imaginator and an Actor. The Imaginator functions as a probabilistic predictor of spatial priors; instead of maintaining a cumulative reasoning chain, it infers the semantic layout of both observed and unobserved regions in a single step. By sampling multiple hypotheses within this semantic space, we provide the Actor with a distribution of effective spatial information, offering robust guidance that hedges against uncertainty during active search. This decoupled architecture significantly lowers data engineering costs by eliminating the need for full-trajectory CoT annotations, enabling the generation of over 1.96 million curated training samples. Extensive experiments demonstrate that explicitly modeling semantic spatial priors drastically improves search efficiency and success rates in complex, in-the-wild environments.
Authors: Frank Li, Bardia Khosravi, Mohammadreza Chavoshi, Young Seok Jeon, Theo Dapamede, Hari Trivedi, Janice Newsome, Judy Gichoya
Abstract: Multi-modal medical imaging enables comprehensive diagnostics, yet current foundation models process 2D (e.g. X-ray) and 3D (e.g. CT) data with separate, dimensionality-specific architectures. We present MultiMedVision, a unified framework for joint 2D/3D representation learning built on a Sparse Vision Transformer. Our model uses 3D Rotary Positional Embeddings and variable-length sequence packing to process mixed-modality batches natively within a shared latent space, without modality-specific adapters or treating 3D volumes as 2D slice sequences. Trained with a self-supervised objective on chest X-rays (MIMIC-CXR) and CT scans (CT-RATE), and using a single shared encoder with 5x less data, MultiMedVision achieves competitive performance on both 2D benchmarks (Macro AUROC 0.82 on MIMIC, 0.84 on CheXpert) and 3D tasks (0.85 on CT-RATE). Analysis of the learned representations reveals coexisting modality-specific and shared feature subspaces, demonstrating that unified cross-dimensional representation learning is feasible without sacrificing modality-specific performance.
Authors: Bo Wen, Dillon Lohr, Yatong An, Pushkar Anand, Alexander Fix, Ruobing Qian, Catherine A. Fromm, Yimin Ding, Truong Nguyen, Mohamed El-Haddad, Francesco La Rocca
Abstract: Retinal image-based eye tracking is widely used in ophthalmic imaging and vision science, and is a promising path to deliver higher gaze accuracy than the pupil- and cornea-based approaches commonly used in modern AR/VR devices. Nevertheless, existing retinal tracking algorithms still primarily rely on classical template-matching registration, which can be insufficiently robust to retinal feature variability and real-world imaging conditions. In this work, we propose a novel weakly-supervised, learning-based framework for robust retinal eye tracking. Initial studies demonstrate high accuracy, achieving the 95th-percentile gaze error < 0.45 deg across a cohort of 6 participants.
Authors: Franco Cerino, Emmanuel Tassone, Manuel Tiglio
Abstract: We present AQMP, a novel image codec combining Adaptive Quadtree Refinement with Matching Pursuit. Unlike conventional Matching Pursuit methods that operate on fixed-size sub-images, AQMP dynamically adapts block sizes to local image structure, allocating finer partitions where the image is complex and coarser ones where it is smooth. This adaptivity yields superior compression ratios compared to fixed-size block Matching Pursuit at equivalent image quality, while offering significant parallelization opportunities at both the tree-leaf level and during compression of individual nodes. The algorithm is governed by user-specified accuracy and sparsity parameters alongside a small set of additional hyperparameters. To navigate the trade-off between compression efficiency and visual quality, we perform multi-objective hyperparameter optimization using the Tree-Structured Parzen Estimator, producing comprehensive Pareto fronts. Experimental results show that AQMP achieves up to $4\times$ higher compression rates than JPEG at comparable SSIM values, while maintaining competitive quality across a broad range of compression regimes. Performance evaluation is provided using a representative set of test images. To ensure reproducibility and promote adoption, we have made our implementation publicly available on GitHub under the MIT license.
Authors: Zhiyang Dou, Minghao Guo, Haixu Wu, Doug Roble, Tuur Stuyck, Wojciech Matusik
Abstract: Learning-based simulation of multi-object rigid-body dynamics remains difficult because contact is discontinuous and errors compound over long horizons. Most existing methods remain tied to mesh connectivity and vertex-level message passing, which limits their applicability to mesh-free inputs such as point clouds and leads to high computational cost. Efficiently modeling high-fidelity rigid-body dynamics from mesh-free representations, therefore, remains challenging. We introduce RigidFormer, an object-centric Transformer-based model that learns mesh-free rigid-body dynamics with controllable integration step sizes. RigidFormer reasons at the object level and advances each object through compact anchors; Anchor-Vertex Pooling enriches these anchors with local vertex features, retaining contact-relevant geometry without dense vertex-level interaction. We propose Anchor-based RoPE to inject anchor geometry into attention while respecting the unordered nature of objects and anchors: object-token processing is permutation-equivariant, and the mean-pooled anchor descriptor is invariant to anchor reindexing while preserving shape extent. RigidFormer further enforces rigidity by projecting updates onto the rigid-body manifold using differentiable Kabsch alignment. On standard benchmarks, RigidFormer outperforms or matches mesh-based baselines using point inputs, runs faster, generalizes to unseen point resolutions and across datasets, and scales to 200+ objects; we also show a preliminary extension to command-conditioned articulated bodies by treating body parts as interacting object-level components.
Authors: Sagar Bharadwaj, Ziyong Ma, Anurag Ghosh, Srinivasan Seshan, Anthony Rowe
Abstract: 3D scene understanding spans reasoning about free space, object grounding, hypothetical object insertions, complex geometric relationships, and integrating all of these with external tools and data sources. Existing 3D understanding methods typically rely on large-scale 3D-language training or focus on object grounding and simple spatial relationships. We argue that the broad generalization that motivates 3D-language training can be achieved at inference time, without 3D-specific training. We propose Flame3D, a training-free framework that represents scenes as editable visual-textual 3D memories and exposes them to an off-the-shelf MLLM through composable spatial tools. Flame3D also lets the agent synthesize custom spatial programs at inference time, enabling open-ended reasoning over layouts, empty space, and objects not yet present in the scene. External data and corrections can be added to the memory without retraining. In addition to showing competitive performance to finetuned 3D-LMM methods on ScanQA, we study multi-hop 3D reasoning capabilities of Flame3D by evaluating it on a curated compositional spatial-reasoning benchmark, Compose3D. We find that fixed tools fall short and that the agent's ability to synthesize spatial operations at inference time is essential. These results invite the question: should future progress in 3D scene understanding focus on richer scene memories and expressive compositional abstractions?
Authors: Mehrajul Abadin Miraj, Abdul Mohaimen Al Radi, Shariful Islam Rayhan, Md. Tanvir Alam, Ismat Rahman, Yu Tian, Md Mosaddek Khan
Abstract: Understanding long videos with multimodal large language models (MLLMs) requires selecting a small subset of informative frames under strict computational budgets, where exhaustive processing is infeasible and optimal selection is combinatorial. We propose CATS, a curvature-aware frame selection method that explicitly models the temporal geometry of query-frame relevance to identify salient events and their surrounding context. By leveraging temporal curvature to adapt selection density, CATS captures both abrupt transitions and gradually evolving content while suppressing redundant frames. Under a fixed backbone and frame budget, CATS consistently outperforms prior lightweight approaches such as AKS on LongVideoBench and VideoMME. While multi-stage methods such as MIRA achieve higher absolute accuracy, they incur substantial computational overhead; in contrast, CATS retains approximately 93-95% of MIRA's performance while requiring only 3-4% of its preprocessing cost, yielding a favorable efficiency-accuracy trade-off. Beyond answer accuracy, we evaluate description generation using an LLM-as-a-judge protocol, and the obtained results show that CATS produces more coherent and informative outputs, indicating improved grounding in visual evidence. These results position CATS as a computationally efficient and principled approach to long-video understanding.
Authors: Arafat Rahman, Shashwat Kumar, Laura E. Barnes, Anuj Srivastava
Abstract: Deep generative models provide flexible frameworks for modeling complex, structured data such as images, videos, 3D objects, and texts. However, when applied to sequences of human skeletons, standard variational autoencoders (VAEs) often allocate substantial capacity to nuisance factors-such as camera orientation, subject scale, viewpoint, and execution speed-rather than the intrinsic geometry of shapes and their motion. We propose the Elastic Shape - Variational Autoencoder (ES-VAE), a geometry-aware generative model for skeletal trajectories that leverages the transported square-root velocity field (TSRVF) representation on Kendall's shape manifold. This representation inherently removes rigid translations, rotations, and global scaling of shapes, and temporal rate variability of sequences, isolating the underlying shape dynamics. The ES-VAE encoder maps skeletal sequences to a low-dimensional latent space incorporating the Riemannian logarithm map, while the decoder reconstructs sequences using the corresponding exponential map. We demonstrate the effectiveness of ES-VAE on two datasets. First, we analyze skeletal gait cycles to predict clinical mobility scores and classify subjects into healthy and post-stroke groups. Second, we evaluate action recognition on the NTU RGB+D dataset. Across both settings, ES-VAE consistently outperforms standard VAEs and a range of sequence modeling baselines, including temporal convolutional networks, transformers, and graph convolutional networks. More broadly, ES-VAE provides a principled framework for learning generative models of longitudinal data on pose shape manifolds, offering improved latent representation and downstream performance compared to existing deep learning approaches.
Authors: Zilai Zeng, Mingdeng Cao, Zijie Li, Xiaochen Lian, Yichun Shi, Peihao Zhu, Chen Sun, Peng Wang
Abstract: Recent advances in visual generative models have enabled high-fidelity image editing guided by human instructions. However, these models often struggle with complex instructions involving combinatorial editing operations or inter-step dependencies. This difficulty stems from the limitations of two canonical paradigms: (1) single-turn editing, which attempts to apply all instructed edits in one pass, often fails to parse the complex instruction accurately and causes undesired edits; and (2) sequential editing can decompose the task into simpler steps but suffers from compounding errors introduced by the sequential execution, leading to low-fidelity results. To derive a robust solution for complex image editing, we examine editing behaviors of different paradigms under a unified in-context editing framework, and study how the benefits of sequential decomposition can be balanced against its error-accumulation drawbacks. We further develop a synthetic data pipeline that constructs editing tasks of varying instruction complexity, allowing us to curate a large-scale editing dataset with high-quality decomposed sequences. By finetuning on synthetic data, we discovered that with properly designed editing paradigms, sequential decomposition yields robust improvements even as task complexity increases. Furthermore, the decomposition skills learned from synthetic tasks can transfer to real images by co-training with real-world editing data, demonstrating the promise of sim-to-real generalization for tackling complex image editing across broader domains.
Authors: Ruiqi Xian, Deep Patel, Iain Melvin, Sanjoy Kundu, Martin Renqiang Min, Dinesh Manocha
Abstract: Multi-camera multi-object tracking (MCMOT) faces significant challenges in maintaining consistent object identities across varying camera perspectives, particularly when precise calibration and extensive annotations are required. In this paper, we present CalibFree, a self-supervised representation learning framework that does not need any calibration or manual labeling for the MCMOT task. By promoting feature separation between view-agnostic and view-specific representations through single-view distillation and cross-view reconstruction, our method adapts to complex, dynamic scenarios with minimal overhead. Experiments on the MMP-MvMHAT dataset show a 3% improvement in overall accuracy and a 7.5% increase in the average F1 score over state-of-the-art approaches, confirming the effectiveness of our calibration-free design. Moreover, on the more diverse MvMHAT dataset, our approach demonstrates superior over-time tracking and strong cross-view performance, highlighting its adaptability to a wide range of camera configurations. Code will be publicly available upon acceptance.
Authors: R. James Cotton, Pouyan Firouzabadi, Wendy Murray
Abstract: Accurate hand and finger tracking from video has significant clinical applications for monitoring activities of daily living and measuring range of motion, yet monocular video approaches for obtaining hand biomechanics remain under-developed. We present a method that combines the SAM 3D Body foundation model with inverse kinematics optimization in a full-body biomechanical model to extract anatomically-constrained finger joint angles from single-view video. We port SAM 3D Body from PyTorch to JAX for integration with MuJoCo-MJX, enabling GPU-accelerated optimization, and develop a novel mapping between the Momentum Human Rig (MHR) outputs and biomechanical model markers. Validation against 8-camera multiview reconstruction on 4,590 frames from 7 participants performing a variety of hand poses and object manipulation tasks shows finger joint angle errors of approximately 10 degrees and hand position errors of approximately 6 mm, after Procrustes alignment. Results were consistent across camera viewpoints and robust to different methods for producing reference values from multiview video. This work extends monocular biomechanical analysis to detailed finger tracking, expanding access to quantitative characterization of hand movement from readily available video.
Authors: Rui Liu, Dian Yu, Haolin Liu, Yucheng Shi, Tong Zheng, Runpeng Dai, Haitao Mi, Pratap Tokekar, Leoweiliang
Abstract: Reinforcement Learning has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet the resulting policies remain brittle against real-world visual degradations such as blur, compression artifacts, and low-resolution scans. Prior robustness techniques from vision and deep RL rely on static data augmentation or value-based regularization, neither of which transfers cleanly to critic-free RL fine-tuning of autoregressive MLLMs. Reinforcing reasoning against such corruptions is non-trivial: naively injecting degraded views during rollout induces reward poisoning, where perceptual occlusions trigger hallucinated trajectories and destabilize optimization. We propose ROMA, an RL fine-tuning framework that modifies the optimization dynamics to reinforce reasoning against visual degradation while preserving clean-input performance. A dual-forward-pass strategy uses teacher forcing to evaluate corrupted views against clean-image trajectories, avoiding new rollouts on degraded inputs. For distributional consistency, we apply a token-level surrogate KL penalty against the worst-case augmentation; to prevent policy collapse under regularization, an auxiliary policy gradient loss anchored to clean-image advantages preserves a reliable reward signal; and to avoid systematically incorrect invariance, correctness-conditioned regularization restricts enforcement to successful trajectories. On Qwen3-VL 4B/8B across seven multimodal reasoning benchmarks, our method improves robustness by +2.4% on seen and +2.3% on unseen corruptions over GRPO while matching clean accuracy.
Authors: Boxuan Zhang, Jianing Zhu, Qifan Wang, Jiang Liu, Ruixiang Tang
Abstract: Recent generative models can produce images that appear highly realistic, raising challenges in distinguishing real and AI-generated images. Yet existing detectors based on pre-trained feature extractors tend to over-rely on global semantics, limiting sensitivity to the critical micro-defects. In this work, we propose Micro-Defects expose Macro-Fakes (MDMF), a local distribution-aware detection framework that amplifies micro-scale statistical irregularities into macro-level distributional discrepancies. To avoid localized forensic cues being diluted by plain aggregation, we introduce a learnable Patch Forensic Signature that projects semantic patch embeddings into a compact forensic latent space. We then use Maximum Mean Discrepancy (MMD) to quantify distributional discrepancies between generated and real images. Our theory-grounded analysis shows that patch-wise modeling yields provably larger discrepancies when localized forensic signals are present in generated images, enabling more reliable separation from real images. Extensive experiments demonstrate that MDMF consistently outperforms baseline detectors across multiple benchmarks, validating its general effectiveness. Project page: https://zbox1005.github.io/MDMF-project/
Authors: Alice Huang, Prathamesh Sonawane, Yashdeep Thorat, Yug Rao
Abstract: Neural Radiance Fields (NeRF) achieve high-quality novel-view synthesis, but their long training times and reliance on dense input views limit accessibility. We present a comparative study of three accelerated NeRF variants - DS-NeRF, TensoRF, and HashNeRF and explore extensions targeted at the low-compute, low-data regime. First, we add a depth-supervision loss derived from COLMAP keypoints to TensoRF (TensoRF-DS) and evaluate it on the LLFF dataset under reduced view counts. Second, we ablate the feature-decoding MLP of TensoRF and study the effect of input downsampling on PSNR and runtime on the synthetic Lego scene. Third, we propose four architectural variants of the HashNeRF color and density networks, including residual and convolutional designs, and report PSNR/training-time tradeoffs under matched iteration budgets. Under iso-time evaluation, none of our extensions conclusively outperform the published baselines, but the experiments characterize which extensions transfer to constrained settings and surface design questions for future work.
Authors: Fangzheng Wu, Brian Summa
Abstract: Attention sinks -- tokens that receive disproportionate attention mass -- are assumed to be functionally important in autoregressive language models, but their role in diffusion transformers remains unclear. We present a causal analysis in text-to-image diffusion, dynamically identifying dominant attention recipients per timestep and suppressing them via paired, training-free interventions on the score and value paths. Across 553 GenEval prompts on Stable Diffusion~3 (with SDXL corroboration), removing these sinks does not degrade text-image alignment (CLIP-T) or preference proxies (ImageReward, HPS-v2) at $k{=}1$; only under stronger interventions ($k\!\geq\!10$) does HPS-v2 exhibit a metric-dependent boundary, while CLIP-T remains robust throughout. The perceptual shifts induced by suppression are nonetheless \emph{sink-specific} -- $\sim\!6\times$ larger than equal-budget random masking -- revealing an empirical dissociation between trajectory-level perturbation and \emph{semantic alignment} in diffusion transformers. \footnote{Code available at https://github.com/wfz666/ICML26-attention-sink.}
Authors: Minh Quoc Duong, Chun Tong Lei, Chun Pong Lau
Abstract: With the proliferation of AI-generated images, digital watermarking has become an essential safeguard for protecting intellectual property and mitigating malicious exploitation. Recent works on semantic watermarking have enabled efficient copyright protection for diffusion models. However, the dependence of semantic watermarking on diffusion inversion for watermark detection creates a critical vulnerability. Imprint removal and forgery attacks exploit this weakness to produce deceptive results. Our analysis reveals that these attacks succeed by displacing watermarked latents into the unwatermarked region, while guiding unwatermarked latents into the watermarked region. Based on that, we propose Progressive Guided Inversion and Denoising (PGID), the first plug-and-play, training-free noise extraction framework designed to defend against both attack strategies. PGID effectively defends by projecting perturbed latents back to the region where they originally belong. The projection is achieved by eliminating intermediate latent deflections and mitigating adversarial perturbations through progressive inversion-denoising cycles. Comprehensive evaluations across multiple schemes demonstrate that PGID successfully restores detection reliability by recovering removed watermarks and identifying forged instances.
Authors: Wei Zhu, Kai Zhang, Yu Zheng, Lei Luo, Yong Guo, Jian Yang
Abstract: Pre-trained text-to-image (T2I) diffusion models have shown strong potential for real-world image super-resolution (Real-ISR), owing to their noise-started generation process that enables realistic texture synthesis and captures the one-to-many nature of super-resolution. However, diffusion-based Real-ISR methods still face a fundamental efficiency-quality trade-off. Multi-step methods generate high-quality results by iteratively denoising random Gaussian noise under LR conditioning, but suffer from slow sampling. Recent one-step methods greatly improve efficiency, yet they typically replace noise-started generation with direct LR-to-HR restoration, which weakens stochasticity and limits realistic detail synthesis. To address this issue, we propose SMFSR, a noise-started one-step Real-ISR framework via LR-conditioned SplitMeanFlow and GAN refinement. SMFSR preserves the random-noise starting point of diffusion models and learns a direct noise-to-HR mapping conditioned on the LR image. To this end, Interval Splitting Consistency distills the multi-step generative trajectory into a single average-velocity prediction, enabling efficient one-step generation. To compensate for the reduced opportunity for progressive refinement, we further introduce a GAN refinement stage, where a DINOv3-based discriminator enhances realistic texture synthesis and variational score distillation aligns the generated outputs with the natural image distribution under a frozen diffusion teacher. Extensive experiments demonstrate that SMFSR achieves state-of-the-art perceptual quality among one-step diffusion-based Real-ISR methods while retaining fast single-step inference.
Authors: Elnara Kadyrgali, Nuray Toganas, Muragul Muratbekova, Pakizar Shamoi
Abstract: Human color categories are not uniformly distributed in perceptual space, yet most computational color models still assume fixed and evenly structured representations. In this paper, we present a focused analytical extension of the COLIBRI fuzzy color model by investigating perceptual asymmetry between hue categories. Using previously collected large-scale human color categorization data, we introduce quantitative measures of category extent and boundary uncertainty, namely Wideness and Boundary Width, derived from fuzzy membership functions at the {\alpha} = 0.5 level. The analysis reveals a strong imbalance between the two categories: yellow occupies a compact and sharply constrained region of the hue space, whereas green spans a substantially broader interval and exhibits a more extended transition structure. The results show that perceptual color categories are not only fuzzy, but also highly non-uniform in their geometric organization. This asymmetry suggests that some categories behave as narrow, highly specific perceptual labels, while others function as broad, tolerant regions of human color naming. These findings provide a new perspective on linguistic color categorization and extend the interpretability of the COLIBRI framework for perceptually grounded color modeling.
Authors: Xinyi Wu, Jayant Teotia, Shuai Zhao, Erik Cambria
Abstract: Long-horizon video generation has advanced in visual quality, yet existing methods still struggle to maintain knowledge consistency and coherent pedagogical narratives across multi-shot instructional videos, especially in STEM domains. To address these challenges, we propose EduStory, a unified framework for reliable instructional video generation. EduStory integrates pedagogical state modeling to track persistent knowledge states, script-guided structured control to organize multi-shot narratives, and learning-oriented evaluation metrics to assess knowledge fidelity and constraint satisfaction. To support rigorous evaluation, we further introduce EduVideoBench, a diagnostic benchmark with multi-granularity annotations, including pedagogical storyboards, shot-level semantics, and knowledge state transitions, together with baseline tasks for controllable instructional video generation. Extensive experiments demonstrate that domain-aware state modeling and structured control substantially reduce narrative breakdown and improve alignment with instructional intent. These results highlight the significance of domain-specific structural constraints and tailored benchmarks for advancing reliable, controllable, and also trustworthy long-horizon video generation.
Authors: Runze Ma, Shunbo Jia, Haonan Lyu, Guo Liu, Caizhi Liao
Abstract: The reasoning gap between large and compact vision-language models (VLMs) limits the deployment of medical AI on portable clinical devices. Compact VLMs of 2--4B parameters can run on resource-constrained hardware but lack the multi-step reasoning capacity needed for interpretable clinical decision support. Existing knowledge distillation methods transfer answers without the reasoning process behind them. Medical visual question answering (VQA) serves as a testbed for this problem, as it requires models to integrate visual evidence with clinical knowledge through structured reasoning chains. We introduce LiteMedCoT-VL, a pipeline that transfers chain-of-thought reasoning from a 235B teacher model to 2B student models through LoRA-based fine-tuning on explanation-enriched training data. All inference is conducted without image captions by default, simulating the clinical scenario in which a physician interprets a medical image directly without an accompanying radiology report. On the PMC-VQA benchmark, LiteMedCoT-VL achieves 64.9% accuracy, exceeding the zero-shot Qwen3-VL-4B baseline of 53.9% by 11.0 percentage points and outperforming all published baselines. This result indicates that a 2B model with reasoning distillation can match or exceed models with twice the parameters. Visual grounding analysis shows that the model relies on image content rather than exploiting textual priors. Our code is publicly available at https://anonymous.4open.science/r/LiteMedCoT-VL.
Authors: Zihan Ma, Tian Xia, Kexin Wang, Xiao Li, Xiaowei He, Yudan Ren
Abstract: Understanding the intricate mappings between visual stimuli and neural responses is a fundamental challenge in cognitive neuroscience. While current approaches predominantly align images and functional magnetic resonance imaging (fMRI) responses in Euclidean space, this geometry often struggles to preserve fine-grained semantic relationships and latent hierarchical structures across visual and neural modalities. To overcome this, we propose HyNeuralMap, a framework that employ hyperbolic Lorentz model to map visual semantics into a shared, cross-subject neural hierarchy. By leveraging the negative curvature of hyperbolic space as an inductive bias, the proposed framework better captures hierarchical semantic organization and cross-subject neural similarities. Specifically, visual and neural embeddings are jointly optimized through hyperbolic geometric alignment, where geodesic distances preserve semantic proximity and hierarchical relationships more effectively than Euclidean embeddings. Experiments demonstrate that HyNeuralMap consistently outperforms state-of-the-art Euclidean baselines in both multi-label semantic prediction and cross-modal retrieval tasks. This confirms hyperbolic geometry's superiority for cross-modal semantic alignment and hierarchical modeling, providing a new avenue for vision-neural representation learning.
Authors: Woochul Kang, Hyungseop Lee, Jiho Lee
Abstract: Modern object detectors are static, fixed-depth networks optimized for a single operating point, requiring separate models for different deployment scenarios. We present an any-depth detection framework that enables a single network to span a continuous range of accuracy--efficiency trade-offs by controlling depth at inference time without retraining. Each backbone and neck stage is divided into an essential path, which always executes, and a skippable refinement path; this decomposition preserves the full multi-scale feature hierarchy at every depth configuration, unlike conventional early exiting that discards entire stages. To train such a network, jointly optimizing many sub-networks of varying depth introduces conflicting gradient signals. We address this via self-distillation between only the two extremes, with prediction-level and feature-level alignment losses that enforce stage-wise modularity, ensuring the outputs of each stage remain compatible regardless of the paths taken. Instantiated on RT-DETR and YOLOv12, our full-depth configurations match or surpass their respective SOTA baselines with negligible parameter overhead, while the most efficient configurations achieve up to $1.82\times$ speedup at a cost of only 2.0 AP, all from a single set of weights.
Authors: Yanchao Wang, Dawei Zhang, Chengzhuan Yang, Wei Liu, Minglu Li, Hua Wang, Zhonglong Zheng, Ming-Hsuan Yang
Abstract: Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent identities across frames. However, most existing approaches primarily rely on instance-level object features for trajectory association, which often leads to degraded performance under challenging conditions such as object deformation, nonlinear motion, and occlusion. In this work, we propose SAMOFT, a robust tracker that leverages pixel-level cues to improve robustness under complex motion scenarios. Specifically, we introduce a Pixel Motion Matching (PMM) module that integrates the Segment Anything Model (SAM) with dense optical flow to refine Kalman filter-based motion prediction using instantaneous foreground pixel motion. To further enhance robustness under unreliable detections, we design a Centroid Distance Matching (CDM) module that performs flexible mask-based centroid matching for low-confidence or partially occluded observations. Moreover, a Distribution-Based Correction (DBC) module models long-tailed motion patterns in a training-free manner using historical optical flow statistics and dynamically corrects trajectory states online. We also incorporate a Cluster-Aware ReID (CA-ReID) strategy to improve the stability and discriminative power of trajectory appearance features. Extensive experiments on the DanceTrack and MOTChallenge benchmarks demonstrate that SAMOFT consistently improves baseline trackers and achieves competitive performance compared with recent state-of-the-art methods, validating the effectiveness of leveraging pixel-level cues for robust multi-object tracking.
Authors: Zhengyi Xu, Yuhang Ming, Zhihao Zhan, Hanyu Zhu, Javier Civera, Wanzeng Kong
Abstract: Multi-modal cross-view place recognition remains a fundamental challenge in computer vision and robotics due to the severe viewpoint, modality, and spatial-structure discrepancies between ground observations and aerial references. To address this challenge, we present MAG-VLAQ, a foundation-model-enhanced query aggregation framework for multi-modal aerial-ground cross-view place recognition. Specifically, our approach leverages pre-trained foundation models to extract dense visual tokens from both ground and aerial images, as well as expressive geometric tokens from ground LiDAR observations. These heterogeneous tokens are then projected into a shared embedding space for cross-modal alignment and fusion. As our main contribution, we propose ODE-conditioned VLAQ, which tightly couples neural ordinary differential equations (ODE)-based RGB-LiDAR fusion with vectors of locally aggregated queries (VLAQ). In this design, the VLAQ query centers are dynamically adapted according to the fused multi-modal state. This mechanism allows the final global descriptor to preserve globally learned retrieval prototypes while remaining responsive to scene-specific visual and geometric evidence, significantly improving aerial-ground matching. Extensive experiments on KITTI360-AG and nuScenes-AG validate the effectiveness of our proposed MAG-VLAQ. Notably, on KITTI360-AG, our MAG-VLAQ nearly doubles the state-of-the-art performance, achieving 61.1 Recall@1 in the satellite setting, compared with 34.5 from the closest competing approach.
Authors: Yulin Xu, Chunqi Guo, Yuanzhen Shuai, Jianyuan Ni
Abstract: In this study, we tackle Generalized Category Discovery (GCD) via a Relational Retrieval perspective, explicitly coupling labeled and unlabeled data through bidirectional knowledge transfer. While existing methods treat these sources separately, missing valuable interaction opportunities, we propose Relational Pattern Consistency (RPC) that enables mutual enhancement. RPC employs One-vs-All classifiers for soft ID/OOD decomposition, then introduces two mechanisms: (i) for known-class preservation, we transfer semantic behavioral alignment; (ii) for category discovery, we leverage the insight that samples from the same category maintain invariant relationships with known-class prototypes, transforming unreliable pseudo-labeling into well-defined relational pattern matching. This bidirectional design allows labeled data to guide unlabeled learning while discovering novel categories through their collective relational signatures. Extensive experiments demonstrate RPC achieves state-of-the-art performance on both generic and fine-grained benchmarks.
Authors: Shogo Noguchi
Abstract: Recent conditional image generation methods can improve controllability by generating images that are faithful to conditions such as sketches, human poses, segmentation maps, and depth. By applying these techniques to image augmentation while preserving annotations, generated images can be used as additional training data and can improve recognition performance. However, for high-level driving tasks such as traffic-rule extraction and driving-behavior understanding, simply using annotations as conditions is insufficient. Instead, images must be augmented while preserving the detailed high-level structure of the original scene. One possible solution is to use multiple conditions so that generated images retain diverse structural cues after generation. However, when multiple conditions are used, conflicts among conditions can prevent reliable structure preservation. In this work, we input semantic segmentation, depth, and edges extracted from the original image into a multi-condition image generation model, thereby providing rich structural information as conditions. We further propose a modeling approach for handling conflicts among multiple conditions and show that it enables image generation with stronger structural preservation. We also build a generation framework and evaluation protocol for driving tasks, establishing a basis for comparison with prior and future models. As a result, this work contributes to image generation research by addressing condition conflicts in multi-condition generation and provides an important step toward mitigating data scarcity in high-level autonomous-driving tasks.
Authors: Jie Ma, Yihang Liu, Zhike Qiu, Jiayi Ji, Xiaoshuai Sun
Abstract: Are low-attention visual tokens truly redundant in vision-language reasoning? Existing pruning methods often assume so, ranking visual tokens by shallow text-to-image attention and discarding low-scoring patches to accelerate LVLM inference. We show that this scalar criterion is unreliable for compositional reasoning: tokens ignored in early layers can later become essential for resolving secondary objects, spatial relations, and contextual cues. Premature pruning can therefore induce Visual Aphasia, a failure mode in which the model loses visual grounding and falls back on language priors. We introduce COAST (COntrastive Adaptive Semantic Token Pruning), a training-free pruning framework that casts compression as adaptive semantic routing. COAST uses native cross-modal attention to identify query-specific anchors and estimate contextual dispersion via attention entropy, then adapts the retention trade-off between semantic evidence and spatial context. It further uses a contrastive routing score to preserve both anchor-aligned evidence and complementary spatial context. Across seven benchmarks, COAST reduces visual tokens by 77.8% and achieves a 2.15x latency speedup while retaining 98.64% of the original average performance. Beyond a single backbone or compression setting, COAST consistently outperforms strong pruning baselines across token budgets and generalizes across multiple LVLM families, showing that adaptive semantic routing is a robust alternative to one-shot scalar pruning
Authors: Junkang Zhou, Yefei He, Feng Chen, Weijie Wang, Bohan Zhuang
Abstract: Large-scale autoregressive models have demonstrated remarkable capabilities in image generation. However, their sequential raster-scan decoding relies on strictly next-token prediction, making inference prohibitively expensive. Existing acceleration methods typically either introduce entirely new generation paradigms that necessitate costly pre-training from scratch, or enable parallel generation at the expense of a training-inference gap or altered prediction objectives. In this paper, we introduce FlashAR, a lightweight post-training adaptation framework that efficiently adapts a pre-trained raster-scan autoregressive model into a highly parallel generator based on two-way next-token prediction. Our key insight is that effective adaptation should minimize modifications to the pre-trained model's original training objective to preserve its learned prior. Accordingly, we retain the original AR head as a horizontal head for row-wise prediction and introduce a complementary, lightweight vertical head for column-wise prediction. To facilitate efficient adaptation, we branch the vertical head from an intermediate layer rather than the final layer, bypassing the inherent horizontal head bias. Moreover, since horizontal and vertical predictions capture complementary dependencies whose relative importance varies across target positions, we employ a learnable fusion gate to dynamically combine the two predictions at each position. To further reduce adaptation cost, we propose a two-stage adaptation pipeline: the vertical head is first initialized through adaptation from the pre-trained autoregressive model before jointly fine-tuned with backbone to adapt to the new decoding paradigm. Extensive experiments on LlamaGen and Emu3.5 show that FlashAR achieves up to a 22.9x speedup for 512x512 image generation through a lightweight post-training with merely 0.05% of the original training data.
Authors: Yunhong Lu, Qichao Wang, Hengyuan Cao, Xiaoyin Xu, Min Zhang
Abstract: Existing preference datasets for text-to-image models typically store only the final winner/loser images. This representation is insufficient for rectified flow (RF) models, whose generation is naturally indexed by a specific prior noise sample and follows a nearly straight denoising trajectory. In contrast, prior DPO-style alignment for diffusion models commonly estimates trajectories using an independent forward noising process, which can be mismatched to the true reverse dynamics and introduces unnecessary variance. We propose Prior Noise-Aware Preference Optimization (PNAPO), an off-policy alignment framework specialized for rectified flow. PNAPO augments preference data by retaining the paired prior noises used to generate each winner/loser image, turning the standard (prompt, winner, loser) triplet into a sextuple. Leveraging the straight-line property of RF, we estimate intermediate states via noise-image interpolation, which constrains the trajectory estimation space and yields a tighter surrogate objective for preference optimization. In addition, we introduce a dynamic regularization strategy that adapts the DPO regularization based on (i) the reward gap between winner and loser and (ii) training progress, improving stability and sample efficiency. Experiments on state-of-the-art RF T2I backbones show that PNAPO consistently improves preference metrics while substantially reducing training compute.
Authors: Shanwen Tan, Hao Li, Jingtao Zhang, Xiaosong Jia, Xue Yang, Shaofeng Zhang, Yanyong Zhang
Abstract: Streaming long-video generation faces a central challenge in continuous semantic switching, requiring adaptive memory to preserve coherent visual evolution. Current approaches rely on cache rebuilding at prompt boundaries or fixed memory budgets, but they introduce redundant computation and limit flexible semantic adaptation. This limitation arises from a mismatch between cached video history and prompt updates, as memory preserves visual continuity while prompt switches demand rapid semantic adaptation. Motivated by this observation, we present SWIFT, Semantic Windowing and Injection for Flexible Transitions, a training-free framework for multi-prompt long-video generation that enables efficient semantic switching while preserving temporal coherence in causal video diffusion models. SWIFT introduces a lightweight Semantic Injection Cache that augments cached video memory rather than reconstructing it from scratch at every prompt boundary. To avoid uniformly perturbing all attention channels, we further perform head-wise semantic injection, so that each attention head receives a prompt update proportional to its alignment with the current video state. In addition, we introduce an Adaptive Dynamic Window that allocates temporal memory according to prompt phase, using larger local context near switching boundaries and smaller windows during stable segments to reduce average inference cost. To preserve long-range semantic consistency under compressed local attention, we further maintain segment-level semantic anchors that summarize prompt-conditioned video history and reintroduce it as compact memory tokens. Compared with current state-of-the-art methods, SWIFT preserves generation quality while achieving 22.6 FPS on a single H100 GPU, establishing a substantially more efficient solution for multi-prompt long-video generation. Our code is available at https://github.com/ShanwenTan/SWIFT.
Authors: Yihong Tang, Kehai Chen, Xuefeng Bai, Min Zhang
Abstract: The advancement of Multimodal Large Language Models (MLLMs) has expanded Role-Playing Agents (RPAs) into visually grounded environments. However, human vision is inherently subjective and identity-driven, whereas existing MLLMs extract objective, character-agnostic features for general tasks. In RPAs, this generic visual noise overpowers fragile character traits, causing Modality-Role Interference (MRI), where agents struggle to integrate visual grounding and character consistency. To address this, we introduce the training-free Character-Aware Visual Intervention (CAVI) framework, enabling agents to perceive the world through the lens of character. CAVI systematically targets MRI: macroscopically, Character-Guided Token Pruning (CTP) restricts the visual receptive field to role-relevant entities; microscopically, Orthogonal Feature Modulation (OFM) projects tokens onto a character-context subspace to extract aligned facts; and during decoding, Modality-Adaptive Role Steering (MARS) dynamically optimizes steering intensity based on visual reliance. Extensive experiments show CAVI effectively alleviates MRI, significantly enhancing character-consistent multimodal interactions.
Authors: Bo Gu, Zhikang Zhang, Zizhuang Wei, Zhenyuan Chen, Lingyun Li, Zhuoyi Song
Abstract: Recent multimodal large language models (MLLMs) have made remarkable progress in visual understanding and language-based reasoning, yet they lack a persistent world-centered representation for spatially consistent reasoning in 3D environments. Inspired by the mammalian dual-stream system, where semantic and spatial cues are processed separately and integrated into an allocentric cognitive map, we propose SpaceMind++, a video MLLM architecture that explicitly builds a voxelized cognitive map from RGB videos. This map reorganizes fragmented egocentric observations into a shared 3D metric representation, enabling the model to preserve object permanence and spatial topology across changing viewpoints. To make this allocentric representation usable by a pretrained video MLLM without disrupting its native visual-token interface, we introduce Coordinate-Guided Deep Iterative Fusion, a new mechanism that relays map-level spatial knowledge back into the original 2D visual features. This fusion is explicitly guided by coordinate embeddings and 3D Rotary Positional Encoding, which ground semantic interactions in metric 3D space, resembling the entorhinal binding of sensory features to metric space. Extensive experiments show that SpaceMind++ achieves new state-of-the-art performance on VSI-Bench. Furthermore, it demonstrates superior out-of-distribution generalization on SPBench, SITE-Bench, and SPAR-Bench, underscoring its robustness in unseen 3D environments.
Authors: Siran Peng, Xiangyu Zhu, Shang-Qi Deng, Liang-Jian Deng, Zhen Lei
Abstract: Remote sensing image fusion aims to create a high-resolution multi/hyper-spectral image from a high-resolution image with limited spectral information and a low-resolution image with abundant spectral data. Recently, deep learning (DL) techniques have shown significant effectiveness in this area. Most DL-based methods approach image fusion as a 2D problem by encoding spectral information into feature map channels. However, our research suggests that this strategy introduces notable spectral distortions. In contrast, some methods consider spectral data as an additional dimension, utilizing standard 3D convolutions to preserve spectral information. Nevertheless, in a standard 3D convolutional layer, the same set of kernels is applied across all input regions, which we have found to be sub-optimal for image fusion. Furthermore, standard 3D convolutions necessitate substantial computational resources. To address these challenges, we propose a novel convolutional paradigm called Adaptive 3D Convolution (Ada3D) for remote sensing image fusion. Ada3D applies a unique set of 3D kernels to each input voxel, enabling the capture of fine-grained details. These adaptive kernels are generated through a two-step process: (i) spatial and spectral kernels are derived from their respective image sources; (ii) these two types of kernels are then combined to form content-aware 3D kernels that effectively integrate spatial and spectral information. Additionally, adaptive biases are introduced to enhance the convolutional outcome at the voxel level. Furthermore, we incorporate the group convolution technique to reduce computational complexity. As a result, Ada3D offers full adaptivity in an efficient manner. Evaluation results across five datasets demonstrate that our method achieves SOTA performance, underscoring the superiority of Ada3D. The code is available at https://github.com/PSRben/Ada3D.
Authors: Dongqi Zheng
Abstract: Identity-preserved image generation is typically built on many-step diffusion backbones, making personalized generation expensive at deployment time. We show that this cost is often unnecessary for identity-conditioned FLUX generation. A frozen InfuseNet identity adapter trained with dev transfers directly to the distilled schnell backbone without retraining. This two-line replacement -- changing the backbone path and disabling classifier-free guidance -- reduces latency by 5.9x while improving ArcFace identity similarity by +0.028 and lpips by -0.016 over the standard 28-step dev baseline. To explain why this works, we analyze the denoising trajectory and find that identity fidelity enters an early effective regime, often within 4-8 steps, while later steps primarily refine visual detail, sharpness, and contrast. Adapter ablations confirm that identity formation depends on the identity adapter, while attention-stream norm probes suggest that the relative conditioning contribution decreases as sampling proceeds. Preliminary style-adapter and object-adapter sweeps on SDXL and SD1.5 show similar diminishing returns after intermediate steps. These results position distilled backbone replacement as a simple, training-free strategy for improving the efficiency-fidelity tradeoff of identity-preserved generation.
Authors: Yang Zheng, Jiahua Liu, Tongyao Pang, Wen Li, Zhaoqiang Liu
Abstract: Methods based on diffusion models (DMs) for solving inverse problems (IPs) have recently achieved remarkable performance. However, DM-based methods typically struggle against outliers, which are common in real-world measurements. In this work, to tackle IPs with outliers, we first refine the measurement via explicit noise estimation to mitigate the effect of noise. Subsequently, we formulate an iteratively reweighted least squares objective based on the Huber loss to address the outliers. We propose a method utilizing gradient descent to approximately solve the corresponding optimization problem for the robust objective. To avoid delicate tuning of the learning rate required by the gradient descent method, we further employ the conjugate gradient method with an efficient strategy for updating. Extensive experiments on multiple image datasets for linear and nonlinear tasks under various conditions demonstrate that our proposed methods exhibit robustness to outliers and outperform recent DM-based methods in most cases.
Authors: Yongsen Cheng, Kai Liu, Kaiwen Tao, Junxian Li, Zhixin Wang, Zhikai Chen, Renjing Pei, Yulun Zhang
Abstract: Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challenging in resource-constrained scenarios, such as interactive applications and personal single-GPU usage. Post-training quantization (PTQ) offers a practical solution by compressing pretrained models without expensive retraining. However, existing PTQ methods still suffer from severe quality degradation under extremely low-bit settings. In this paper, we identify channel ordering as an important but underexplored factor in per-group quantization. In this setting, each contiguous group shares one quantization scale. When channels with very different statistics are placed in the same group, the scale can be dominated by outliers and cause large quantization errors. Based on this observation, we propose PermuQuant, a simple and effective PTQ framework for low-bit diffusion models. PermuQuant sorts channels by a joint second-moment criterion before per-group quantization, placing channels with similar activation and weight statistics into the same group. It further uses a calibration-based acceptance rule to apply reordering only when the selected permutation reduces quantization error on calibration data. The selected permutations are absorbed into adjacent modules or applied to weights offline, avoiding explicit runtime permutation operations. Extensive experiments on multiple large diffusion models show that PermuQuant consistently reduces quantization error and outperforms existing PTQ baselines. On FLUX.1-dev with an RTX 5090, PermuQuant achieves up to a 1.8$\times$ single step speedup and reduces the DiT memory footprint by 3.5$\times$ under W4A4 NVFP4 quantization. Code will be available at https://github.com/yscheng04/PermuQuant.
Authors: Omer Tariq, Syed Muhammad Raza, Jeongbae Son
Abstract: Video summarization aims to produce a compact representation of a long video by selecting a subset of temporally important segments that best reflect human preferences. This task is inherently difficult due to strong annotation subjectivity and the reliance on discrete decoding procedures, such as temporal segmentation and knapsack-based selection, during evaluation. Most existing approaches either learn deterministic importance scores that overlook these characteristics or adopt complex generative models that increase training and inference cost. In this paper, we propose VASTSum, an uncertainty-aware and decoder-aligned learning framework for video summarization that addresses both challenges within a single-pass model. The proposed method predicts probabilistic frame-level importance scores using a variational formulation, enabling explicit modeling of uncertainty arising from multi-annotator supervision. To account for subjectivity, particularly under binary annotations, we employ a supervision strategy that encourages alignment with plausible human annotation modes rather than enforcing a single consensus target. Furthermore, we introduce a decoder-aligned regularization that promotes stability of knapsack-based summary selection, reducing sensitivity to small perturbations in predicted scores. We evaluate the proposed framework on the SumMe and TVSum benchmarks using standard rank-based metrics. Experimental results show consistent and competitive Kendall and Spearman correlations across multiple data splits, demonstrating improved robustness under annotation disagreement while maintaining efficient single-forward inference. These results indicate that explicitly modeling uncertainty and aligning learning objectives with the decoding stage provide a principled alternative to both deterministic and diffusion-based video summarization methods.
Authors: Mayank Anand, Mohammad Saqlain, Kyan Mahajan, Priya Shukla, Gora Chand Nandi, Andrew Melnik
Abstract: Tracking points in videos is typically formulated as frame-to-frame correspondence, where each point is matched locally to the next frame. While this works over short horizons, errors accumulate under articulation, occlusion, and viewpoint change, leading to silent semantic drift that existing trackers cannot detect or correct. In this work, we revisit long-horizon tracking from a monitoring perspective and introduce QueST, a monitoring-by-design framework that treats interaction-relevant entities as persistent semantic queries rather than transient point tracks. Instead of local propagation, each query attends globally over spatio-temporal video features at every time-step, providing a stable semantic anchor across time. We further constrain query trajectories with lightweight 3D physical grounding, using geometric plausibility to suppress unbounded drift under occlusion. We evaluate QueST on long-horizon articulated sequences from PartNet-Mobility in SAPIEN and compare against RAFT-3D, CoTracker, and TAP-Net. QueST substantially reduces terminal drift achieving a 67.7% Absolute Point Error (APE) improvement over TAP-Net while better preserving identity over extended horizons. Our results show that embedding semantic monitoring directly into perception enables more reliable long-horizon tracking under distribution shift.
Authors: Jihyun Lee, Changmin Lee, Donghwan Kim, Tae-Kyun Kim
Abstract: While existing methods for reconstructing hand-object interactions have made impressive progress, they either focus on rigid or part-wise rigid objects-limiting their ability to model real-world objects (e.g., cloth, stuffed animals) that exhibit highly non-rigid deformations-or model deformable objects without full 3D hand reconstruction. To bridge this gap, we present PhysHanDI (Physics-based Reconstruction of Hand and Deformable Object Interactions), a framework that enables full 3D reconstruction of both interacting hands and non-rigid objects. Our key idea is to physically simulate object deformations driven by forces induced from densely reconstructed 3D hand motions, ensuring that the reconstructed object dynamics are both physically plausible and coherent with the interacting hand movements. Furthermore, we demonstrate that such simulation of object deformations can, in turn, refine and improve hand reconstruction via inverse physics. In experiments, PhysHanDI outperforms the state-of-the-art baseline across reconstruction and future prediction.
Authors: Tianyi Lu, Wenxue Cui, Shaohui Liu
Abstract: Recent Deep Unfolding Networks (DUNs) have significantly advanced Compressive Sensing (CS) by integrating iterative optimization with deep networks. However, existing DUNs still suffer from two challenges: 1) Reliance on a single measurement stream, which limits effective information interaction across distinct measurement subsets. 2) Uniform processing of all image regions, which overlooks varying reconstruction difficulties induced by diverse textures. To address these limitations, a novel Dual-Path Hyperprior Informed Deep Unfolding Network (DPH-DUN) is proposed, which partitions measurements into double subsets to enable hyperprior-guided reconstruction via a dual-path architecture. In the Deep Hyperprior Learning branch, a series of lightweight neural modules are designed to efficiently generate hyperprior knowledge of different domains, enabling collaborative guidance for the CS reconstruction. In the Hyperprior Informed Reconstruction branch, a deep unfolding framework with hyperprior guidance is constructed to iteratively refine reconstruction. Specifically, i) in the gradient descent step, a Hyperprior Informed Step Size Generation network is designed to dynamically generate spatially varying step maps, enabling adaptive fine-grained gradient updates. ii) In the proximal mapping step, two well-designed hyperprior informed attention mechanisms are introduced to dynamically focus on challenging regions via gradient-based hard and soft attentions, facilitating CS reconstruction accuracy. Extensive experiments demonstrate that the proposed DPH-DUN outperforms existing CS methods.
Authors: Guanyi Du, Lintao Wang, Kun Hu, Ziyang Wang
Abstract: Sign language production from symbolic notation offers a scalable route to accessible sign animation. We present KANMultiSign, a multi-scale sequence generator that translates HamNoSys notation into two-dimensional human pose sequences. Our framework makes two complementary contributions. First, we introduce a coarse-to-fine generation strategy with multi-scale supervision: the model is first guided by an intermediate body--hand--face scaffold to encourage global structural coherence, and then refines fine-grained hand articulation to improve finger-level detail. Second, we investigate integrating Kolmogorov--Arnold Network modules into a Transformer backbone, using learnable univariate function primitives to model the highly non-linear mapping from discrete phonological symbols to continuous body kinematics with a compact parameterization. Experiments on multiple public corpora spanning Polish, German, Greek, and French sign languages show consistent reductions in dynamic time warping based joint error compared with a strong notation-to-pose baseline, while using substantially fewer parameters. Controlled ablations further indicate that KAN-based variants substantially reduce parameter count while maintaining competitive performance when coupled with multi-scale supervision, rather than serving as the main driver of accuracy gains. These findings position multi-scale supervision as the key mechanism for improving notation-conditioned pose generation, with KAN offering a compact alternative for efficient modeling. Our code will be publicly available.
Authors: Michal Filipkowski, Marcin Kowalczyk, Tomasz Kryjak
Abstract: This paper presents a hardware architecture that implements the Contrast Maximization (CM) algorithm in Field-Programmable Gate Array (FPGA) resources for event-based vision systems. CM estimates motion parameters by maximizing the contrast of an Image of Warped Events (IWE) reconstructed from asynchronous event streams. Event-based vision sensors generate sparse data with high temporal resolution and low spatial redundancy, which makes them well suited for hardware processing. The deterministic, massively parallel structure of the FPGA is leveraged to design a deeply pipelined architecture capable of high-throughput, energy-efficient processing suitable for real-time embedded applications. This paper details the hardware modules responsible for event warping, contrast computation, and iterative optimization, discusses key implementation decisions, and presents the hardware-aware optimization method used in the design. Experimental results demonstrate a substantial speed and efficiency improvement over CPU- and GPU-based implementations, with motion parameter estimation executing over 200 times faster. To the best of our knowledge, this is the first hardware architecture enabling acceleration of CM algorithm computations. Its performance is evaluated in terms of processing speed, energy efficiency, and hardware resource utilization. The proposed design is validated using an event-based object tracking application. The results confirm that the architecture provides a solid foundation for real-time motion estimation in high-speed, low-power embedded systems.
Authors: Can Li, Zhoujian Li, Ren Li, Jie Gu, Lei Lei, Jingmin Chen, Lei Sun
Abstract: World models for deformable objects should recover not only geometry and appearance, but also underlying physical dynamics, interaction grounding, and material behavior. Learning such a model from real videos is challenging because deformable linear, planar, and volumetric objects evolve under high-dimensional deformation, noisy interactions, and complex material response. The model must therefore infer a physical state from visual observations, roll it forward under new interactions, and render the resulting dynamics with high visual fidelity. We present DeformMaster, a video-derived interactive physics--neural world model that turns real interaction videos into an online interactive model of deformable objects within a unified dynamics-and-appearance framework. DeformMaster preserves structured physical rollout while using a neural residual to compensate for unmodeled effects, grounds sparse hand motion as distributed compliant actuator for hand--continuum interaction, represents material response with spatially varying constitutive experts, and drives high-fidelity 4D appearance from the predicted physical evolution. Experiments on real-world deformable-object sequences demonstrate DeformMaster's ability to roll out future dynamics and render dynamic appearance, outperforming state-of-the-art baselines while supporting novel action rollout, material-parameter variation, and dynamic novel-view synthesis.
Authors: Shuang Liang, Zeqing Wang, Yuxian Li, Xihui Liu, Han Wang
Abstract: Segmentation is a fundamental vision task underlying numerous downstream applications. Recent promptable segmentation models, such as Segment Anything Model 3 (SAM3), extend segmentation from category-agnostic mask prediction to concept-guided localization conditioned on high-level textual prompts. However, existing benchmarks primarily evaluate mask accuracy or object presence, leaving unclear whether these models faithfully ground the queried concept or instead rely on visually salient but semantically misleading cues. We introduce CAFE: \textbf{C}ounterfactual \textbf{A}ttribute \textbf{F}actuality \textbf{E}valuation, a novel benchmark for evaluating concept-faithful segmentation in promptable segmentation models. Our \textbf{CAFE} is built on attribute-level counterfactual manipulation: the target region and ground-truth mask are preserved, while attributes such as surface appearance, context, or material composition are modified to introduce misleading semantic cues. The benchmark contains 2,146 paired test samples, each consisting of a target image, a ground-truth mask, a positive prompt, and a misleading negative prompt. These samples cover three counterfactual categories: Superficial Mimicry (\textbf{SM}), Context Conflict (\textbf{CC}), and Ontological Conflict (\textbf{OC}). We evaluate various model types and sizes on our CAFE. Experiments reveal a systematic gap between localization quality and concept discrimination: models often generate accurate masks even for misleading prompts, suggesting that strong mask prediction does not necessarily imply faithful semantic grounding. Our CAFE provides a controlled benchmark for diagnosing whether promptable segmentation models perform concept-faithful grounding rather than shortcut-driven mask retrieval.
Authors: Ismael Elsharkawi, Ahmed Sait, Silvio Giancola, Bernard Ghanem, Hossam Sharara, Abdelrahman Eldesokey
Abstract: Vision-language models (VLMs) have recently shown strong potential in soccer video understanding. However, given the high complexity of soccer videos due to large viewpoint variations, rapid shot transitions, and cluttered scenes, it remains unclear on whether VLMs rely on meaningful visual evidence or exploit spurious correlations and shortcut learning. Existing evaluation protocols focus primarily on classification accuracy and do not assess visual grounding. To address this limitation, we introduce SoccerLens, a benchmark for grounded soccer video understanding. The benchmark contains annotated video segments spanning $13$ common soccer events, with structured visual cues organized into three levels of semantic relevance. We further extend the attribution method of Chefer [arXiv:2103.15679] to jointly model spatial and temporal attention, and introduce evaluation metrics that measure whether model attention aligns with annotated cues or drifts toward spurious regions. Our evaluation of state-of-the-art soccer VLMs shows that, despite strong classification accuracy, current models fail to exceed $50\%$ grounding performance even under the loosest cue definitions and consistently underutilize temporal information. These results reveal a substantial gap between predictive performance and true visual grounding, highlighting the need for grounded evaluation in complex spatio-temporal domains such as soccer.
Authors: Jiaying Lin, Shiman Wu, Jinfu Liu, Can Wang, Mengyuan Liu
Abstract: Millimeter-wave (mmWave) radar provides privacy-preserving sensing and is valuable for human action recognition (HAR). Existing mmWave point cloud datasets are limited in scale and mostly collected under homogeneous single-source settings, preventing current methods from handling real-world distribution shifts caused by heterogeneous radar sources, such as different devices and frequency bands. To address this, we introduce UniMM-HAR, the largest and first mmWave point cloud HAR dataset for heterogeneous multi-source scenarios, standardizing three distinct radar configurations to realistically evaluate cross-source generalization. We further propose the Doppler-aware Point Cloud Network (DAP-Net) to tackle heterogeneity challenges. DAP-Net enhances intra-modal representations and performs cross-modal alignment to learn source-invariant action semantics. Leveraging action-consistent spatio-temporal Doppler patterns as anchors, the Dual-space Doppler Reparameterization (D2R) module performs sample-adaptive geometric densification and Doppler-guided feature recalibration, while the Text Alignment Module (TAM) provides stable semantic anchors via a pretrained textual space. Experiments show that DAP-Net significantly outperforms existing methods under heterogeneous radar settings, achieving state-of-the-art accuracy and strong cross-source robustness.
Authors: Xuan Gong, Hanbo Huang, Hao Zheng, Yiran Zhang, Wenbin Dai, Weishu Zhao, Shiyu Liang
Abstract: Long chain-of-thought (CoT) reasoning improves large vision--language models, but visual information often fades during generation, limiting long-horizon multimodal reasoning. Existing methods either re-inject vision at inference or train policies for stronger grounding, but where to intervene relies on perception heuristics rather than principled gain analysis, and how local visual influence propagates remains implicit. We study this problem from an information-theoretic standpoint and derive a lower bound on the downstream visual gain of a one-step intervention, which suggests two factors: local branching room (token entropy) and downstream visual propagation potential (suffix divergence from a vision-marginalized reference). Guided by this analysis, we propose reflection-anchor policy optimization (RAPO), a GRPO-based policy optimization method that selects high-entropy reflection anchors and optimizes a chain-masked finite-window KL surrogate for downstream visual dependence. Experiments on reasoning-intensive and general-domain benchmarks show that RAPO delivers substantial gains over strong baselines across multiple LVLM backbones. Mechanism analyses further indicate that reflection anchors are enriched for visually sensitive decision points and that RAPO increases contrastive visual-dependence signals along generated trajectories.
Authors: Zhenxuan Zeng, Sheng Yang, Lingxuan Wang, Yanan He, Mingxia Chen, Wei Suo, Peng Wang
Abstract: Accurate High-Definition (HD) map construction is critical for autonomous driving, yet existing methods face a fundamental trade-off: vectorization-based approaches preserve topology but struggle with geometric fidelity, while rasterization-based approaches enable precise geometric supervision but produce unstructured outputs. To bridge this gap, we propose GSMap, a novel framework that unifies both paradigms via a learnable 2D Gaussian representation. Each map element is modeled as an ordered sequence of 2D Gaussians, whose centers correspond to the vertices of the vectorized polyline/polygon. This formulation enables simultaneous optimization through: (1) Differentiable rasterization that enforces pixel-level geometric constraints, and (2) Topology-aware vectorization that maintains structural regularity. Experiments on both nuScenes and Argoverse2 demonstrate that our Gaussian-based representation effectively unifies geometric and topological learning, achieving significant performance improvements and demonstrating strong compatibility with existing HD mapping architectures. Code will be available at https://github.com/peakpang/GSMap
Authors: Yuhan Wang, Zihan Li, Han Liu, Simon Arberet, Martin Kraus, Yuyin Zhou, Florin-Cristian Ghesu, Dorin Comaniciu, Ali Kamen, Riqiang Gao
Abstract: Voxel-wise dose prediction is a critical yet challenging task in practical radiotherapy (RT) planning, as bespoke models trained from scratch often struggle to generalize across diverse clinical settings. Meanwhile, generative models trained on billion-scale datasets from vision domains have achieved impressive performance. Herein, we propose DiffKT3D, a unified Any2Any 3D diffusion framework that leverages prior knowledge from pretrained video diffusion models for efficient and clinically meaningful dose prediction. To enable flexible conditioning across multiple clinical modalities (CT, anatomical structures, body, beam settings, etc.), we introduce an Any2Any conditional paradigm utilizing modality-specific embeddings without cross-attention overhead. Further, we design a novel reinforcement learning (RL) post-training mechanism guided by a clinically-informed Scorecard explicitly tailored to institutional treatment preferences. Compared with winner of GDP-HMM challenge, DiffKT3D sets a new state-of-the-art in dose prediction by reducing voxel-level MAE from 2.07 to 1.93. In addition, DiffKT3D achieves superior image quality and preference match. These results demonstrate that transferring diffusion priors via modality-aware conditioning and clinically aligned RL post-training can provide a robust and generalizable solution for RT planning across various clinical scenarios.
Authors: Zhiqiang Yan, Zhengxue Wang, Jian Yang, Gim Hee Lee
Abstract: Depth super-resolution (DSR) aims to recover a high-resolution (HR) depth map from its low-resolution (LR) counterpart. With color image guidance, this task is typically formulated as learning the residual between HR and LR in a low-dimensional feature space. However, this additive formulation is insufficient to accurately capture the complex relationship between HR and LR, especially under spatially varying degradations. In this paper, we introduce DegBins, a novel DSR framework that leverages degradation-driven binning to adaptively enhance residual modeling. Specifically, DegBins reformulates the regression-based DSR as a hybrid classification-regression problem, where the residual depth is represented as a linear combination of discrete depth bins weighted by their learned probability distribution, yielding more flexible and expressive representations. Furthermore, DegBins models the degradation relationship between HR and LR in a high-dimensional feature space, enabling adaptive bin range adjustment and probability optimization conditioned on local degradation characteristics. To progressively improve reconstruction quality, DegBins adopts a multi-stage refinement scheme, where each stage performs finer-grained bin partitioning and probability updating based on the former estimation. This coarse-to-fine design facilitates more accurate depth recovery, particularly in regions with severe degradations or complex structural variations. Extensive experiments across five benchmarks demonstrate that DegBins consistently outperforms existing state-of-the-art methods in terms of accuracy, robustness, and generalization.
Authors: Meng Lou, Hanzhong Guo, Linwei Chen, Yizhou Yu
Abstract: Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). However, whether RFT (e.g., GRPO) can effectively overcome forgetting in challenging visual continual learning settings, such as class-incremental learning (CIL) and domain-incremental learning (DIL), remains an open problem. Through a pilot study, we confirm that while RFT consistently outperforms SFT, it still suffers from non-negligible forgetting. We empirically trace this bottleneck to Trajectory-level Drift Agnosticism: among candidate rollouts achieving identical task rewards, the KL divergence from the preceding-task policy varies substantially, which strongly correlates with catastrophic forgetting across sequential tasks. Motivated by this insight, we propose Retention-aware Policy Optimization (RaPO), a simple yet effective RFT method that explicitly mitigates forgetting through trajectory-level reward shaping. Specifically, RaPO comprises two core components: (1) Retention Reward that converts trajectory-level distribution drift into a continuous reward signal, preferentially reinforcing knowledge-preserving rollouts within each group; (2) Cross-Task Advantage Normalization (CTAN), which maintains a persistent exponential moving average of reward statistics across task boundaries to stabilize the optimization progress during continual learning. Leveraging the free-form textual generalization of MLLMs, we comprehensively evaluate RaPO across five visual continual learning settings. Extensive experiments demonstrate that RaPO achieves leading performance, substantially reducing catastrophic forgetting while preserving strong plasticity. To the best of our knowledge, this work represents the first systematic exploration of RFT in visual continual learning, offering insights that we hope will inspire future research.
Authors: Zichen Zou, Xiaosong Jia, Zuxuan Wu, Yu-Gang Jiang
Abstract: Visual Geometry Grounded Transformer (VGGT) advances 3D reconstruction via scalable Transformer architecture, but the quadratic complexity of global attention prevents long context application. StreamVGGT enables streaming with causal attention, yet its KV cache grows linearly with frames, causing memory overflow and quality degradation. We present RetrieveVGGT, a training-free framework, which formulates context construction for VGGT as a retrieval problem. By retrieving a fixed number of relevant frames at each step, VGGT maintains a controllable memory budget, which is close to its training context length. Interestingly, we find that the similarity between current frame queries and cached history frame keys at the first global attention layer of VGGT is already a strong indicator of relevance, eliminating the need for additional learned scoring. To enhance information diversity similar to a recommender system, we propose Segment Sampling so that the retrieval spans distinct relevant segments rather than a single high-similarity region. We design a pose-aware spatial memory mechanism that organizes history frames according to their already estimated camera poses, enabling location-aware retrieval. Extensive experiments demonstrate that RetrieveVGGT achieves state-of-the-art performance, outperforming StreamVGGT, TTT3R, and InfiniteVGGT while maintaining constant memory usage regardless of sequence length. Code is available at https://github.com/zzctmd/RetrieveVGGT.
Authors: Alessio Mazzucchelli, Maria Naranjo-Almeida, Jorge Bustos-Sanchez, Mariella Dimiccoli, Francesc Moreno-Noguer, Jordi Sanchez-Riera, Adrian Penate-Sanchez
Abstract: Most Gaussian Splatting techniques that provide a 3D semantic representation of the scene do not optimize the underlying 3D geometry, making object-level editing or asset extraction challenging. Recent methods, such as COBGS, Trace3D, ObjectGS, acknowledge this limitation and propose approaches that modify the scene's geometry to represent the underlying semantics. We advance this concept further by proposing a novel solution that provides near perfect boundaries in object extraction. We do so by introducing two new losses in the optimization that take care of: 1) a loss that modifies the geometry of visible Gaussians to respect semantic boundaries, and 2) a loss that adjusts the geometry of non-visible Gaussians that appear once the object is extracted. Our first loss propagates gradients directly through the rasterization, allowing for seamless integration within the optimization of the Gaussian parameters. The second loss also propagates gradients to Gaussian parameters but does so without passing through the rasterization, enabling modification of the scene's geometry even when little transmittance reaches a Gaussian (partial or non-visible). Exhaustive comparisons with 12 state of the art methods across 4 datasets, using six metrics, demonstrate that our approach produces overall the best boundary segmentation to date.
Authors: Abdul Basit, Ashir Rashid, Muhammad Abdullah Hanif, Muhammad Shafique
Abstract: Multiple Sclerosis (MS) is a chronic autoimmune disease that can significantly reduce the quality of life of a patient. Existing treatment options can only help slow down the progression of the disease. Therefore, early detection and precise monitoring of disease progression are important. Deep learning offers state-of-the-art models for detecting and segmenting MS lesions in brain MRI scans. However, most of these models are evaluated using the Dice score, without accounting for lesion-wise detection and segmentation performance or other metrics that quantify model performance in cases that are complex or confusing for human annotators, or in cases that are essential for disease detection and progression monitoring. In this paper, we highlight the need to rethink the evaluation of MS lesion segmentation models. In this context, we first present problem fingerprinting in detail to highlight what neurologists look for in brain MRI scans for MS detection and progression monitoring, and which metrics are required to properly quantify model performance in these contexts. Additionally, we present an analysis of state-of-the-art models on two open-source datasets using these metrics to highlight their usability for real-world deployment in hospitals.
Authors: Albert Heruth
Abstract: We present S2P-Net (Spectral-Spatial Polar Network), a compact deep learning architecture that achieves mathematically guaranteed rotation invariance without data augmentation. In this Paper, we also made a comparison to other neural network architectures (CNN`s). Have a look at the results and feel free to contact me for any questions. This is my first paper:) Made by Hackbert
Authors: Qingyu Xian, Hao Cheng, Berend Jan van der Zwaag, Rolands Kromanis, Ozlem Durmaz Incel
Abstract: Reliable displacement measurement is fundamental for structural health monitoring and digital engineering workflows, as it provides direct structural response information. Vision-based measurement has emerged as a promising approach for low-cost, non-contact displacement monitoring. However, its deployment often remains constrained by task-specific model training or on-site preparation, such as marker installation or manual camera calibration. This study presents a Vision Foundation Model-based framework for Structural Displacement Measurement (VFM-SDM) that integrates VFM-inferred camera parameter estimation and point tracking to reconstruct multi-directional structural displacements via triangulation without task-specific training or on-site preparation, enabling efficient non-contact deployment in real-world applications. Structural geometry constraints are incorporated to suppress physically implausible deviations and improve estimation consistency. A multi-modal field dataset collected from an in-service pedestrian bridge is introduced alongside a unified benchmarking protocol to support reproducible evaluation. Representative results show low amplitude errors (NRMSE$_{\text{range}}$: 0.11/0.12), strong temporal agreement (correlation coefficient: 0.86/0.88), and small peak-to-peak amplitude errors (RPPAE: 0.01/0.02) for vertical and lateral displacements, indicating robust performance under real-world conditions. The proposed framework advances automated, scalable displacement monitoring and lays the groundwork for VFM-enabled structural response measurements in digital twin and data-centric construction workflows.
Authors: Yixiong Chen, Wenjie Xiao, Pedro R. A. S. Bassi, Boyan Wang, Liang He, Xinze Zhou, Sezgin Er, Ibrahim Ethem Hamamci, Zongwei Zhou, Alan Yuille
Abstract: Medical vision-language models (VLMs) and AI agents have made significant progress in learning to analyze and reason about clinical images. However, existing medical visual question answering (VQA) benchmarks collapse model capabilities into a single accuracy score, obscuring where and why models fail. We propose DeepTumorVQA, a hierarchical benchmark that follows the multi-stage evidence chain in tumor diagnosis and decomposes 3D CT reasoning into four stages: recognition, measurement, visual reasoning, and medical reasoning. Higher-level questions remain independently scorable, while their ground-truth evidence chains are defined over lower-level primitives. The benchmark contains 476K questions across 42 clinical subtypes on 9,262 3D CT volumes. In addition to a direct reasoning mode for VLMs, DeepTumorVQA provides tool-interaction environments for agent evaluation, where a model can call external tools, including segmentation models, measurement programs, and medical knowledge modules, before answering the question. Evaluating over 30 model configurations, we find that reliable quantitative measurement is the primary bottleneck, making later-stage visual and medical reasoning harder for VLMs, while tool augmentation substantially mitigates this issue. When tools are available, leveraging medical knowledge and tools to reason about medical images becomes a new challenge. We further show that ground-truth step-by-step tool-use traces from DeepTumorVQA can supervise agents and reduce tool-use and reasoning failures. This stage-wise progression from recognition to measurement to visual and medical reasoning provides a concrete roadmap for future medical VLM and AI agent studies. All data and code are released at https://github.com/Schuture/DeepTumorVQA.
Authors: Yicheng Ji, Zhizhou Zhong, Jun Zhang, Qin Yang, XiTai Jin, Ying Qin, Wenhan Luo, Shuiyang Mao, Wei Liu, Huan Li
Abstract: Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video diffusion models still suffer from significant attention complexity and severe memory overhead due to the redundant key-value (KV) caches across historical frames, which limits scalability. In this paper, we tackle this challenge by introducing KV cache compression into autoregressive video diffusion. We observe that attention heads in mainstream AR diffusion models exhibit markedly distinct attention patterns and functional roles that remain stable across samples and denoising steps. Building on our empirical study of head-wise functional specialization, we divide the attention heads into two categories: static heads, which focus on transitions across autoregressive chunks and intra-frame fidelity, and dynamic heads, which govern inter-frame motion and consistency. We then propose Forcing-KV, a hybrid KV cache compression strategy that performs structured static pruning for static heads and dynamic pruning based on segment-wise similarity for dynamic heads. While maintaining output quality, our method achieves a generation speed of over 29 frames per second on a single NVIDIA H200 GPU along with 30% cache memory reduction, delivering up to 1.35x and 1.50x speedups on LongLive and Self Forcing at 480P resolution, and further scaling to 2.82x speedup at 1080P resolution. Code and demo videos are provided at https://zju-jiyicheng.github.io/Forcing-KV-Page.
Authors: Md Aminur Hossain, Parekh Valkesh, Ayush V. Patel, Yogesh Jethani, Sanjay K. Singh, Biplab Banerjee
Abstract: Remote Sensing (RS) single-image super-resolution aims to reconstruct high-resolution imagery from low-resolution observations while preserving fine spatial structures. Recent Swin Transformer-based models, including Swin2SR, provide strong spatial context modeling throughshifted-window self-attention, but their feed-forward networks remain generic channel-mixing modules and do not separate low-frequency structural content from high-frequency residual detail. To address this limitation, we propose SFG-SwinSR, a Spatial-Frequency Gated Swin Transformer for single-image super-resolution in remote sensing. SFG-SwinSR modifies the original Swin2SR attention block by replacing each transformer block's standard feed-forward network with a lightweight Spatial-Frequency Gated Feed-Forward Network (SFG-FFN). The module estimates low-frequency content via a depthwise-blur branch, extracts high-frequency residuals by subtraction, refines them with a lightweight spatial branch, and adaptively injects detail through a bottleneck gate. Experiments on SpaceNet and SEN2VEN{\mu}S show that SFG-SwinSR improves reconstruction quality under the evaluated settings. On SpaceNet, it achieves 45.19 dB PSNR and 0.9852 SSIM, indicating effective enhancement of high-frequency details. This demonstrates that spatial-frequency transformation within the transformer feed-forward network improves detail reconstruction in RS super-resolution.
Authors: Rui Song, Tianhui Cai, Markus Gross, Xingcheng Zhou, Zewei Zhou, Zhiyu Huang, Olaf Wysocki, Jiaqi Ma
Abstract: Feedforward 3D Gaussian Splatting (3DGS) often struggles in trajectory-based sparse-view driving scenes. Existing Gaussian repair methods mainly target optimization-based 3DGS, while diffusion-based repair is typically restricted to iterative refinement near observed viewpoints, leaving feedforward 3DGS repair underexplored. We propose ConFixGS, a plug-and-play method that learns to fix feedforward 3DGS with confidence-aware diffusion priors. Starting from a pretrained feedforward model, ConFixGS generates diffusion-enhanced local pseudo-targets and validates them through reprojection-based cross-checking against support views. The resulting dense confidence maps guide refinement, enhancing reliable details while suppressing hallucinated or inconsistent evidence. On Waymo, nuScenes, and KITTI, ConFixGS improves challenging novel view synthesis, with PSNR gains of up to 3.68 dB and FID reduced by nearly half. Our results highlight confidence-aware fusion of generative priors and support-view consistency as a key principle for robust feedforward 3D driving scene reconstruction.
Authors: Santhosh Kumar Ramakrishnan, Carl Vondrick, Raja Giryes, Philipp Kr\"ahenb\"uhl, Vladlen Koltun
Abstract: Yes. We find that large multimodal models develop mental imagery when solving spatial puzzles, and they do imagine sheep when solving sheep puzzles. We fine-tune a Qwen3.5 VLM to solve twelve diverse visual reasoning tasks -- including tangram, jigsaw, sokoban, 3D mental rotation, and rush hour -- that require understanding geometry, spatial relationships, and the consequences of actions. By supervising the model to predict the open-loop sequence of actions to solve a puzzle from an initial state, we show that the model's activations after each action encode meaningful visual information about the intermediate state. This finding suggests that an imperfect visual world model begins to form as a byproduct of learning to select correct actions, in the absence of any explicit visual supervision. Building on this observation, we propose two ways to sharpen and use the mental images formed by the model. We find that integrating as few as sixteen visual tokens per step into the chain of thought improves the average solve rate from 83% to 89%, with particularly strong gains on reasoning-heavy tasks such as jigsaw and 3D mental rotation.
Authors: Radhika Amar Desai, Modigari Narendra
Abstract: In many real-world computer vision applications, including medical imaging and industrial inspection, binary classification tasks are characterized by a severe scarcity of positive samples. A widely adopted solution is to generate synthetic positive data using image-to-image transformations applied to negative samples. However, a fundamental challenge remains: how can we reliably assess whether such synthetic data will improve downstream model performance? In this work, we propose a geometry-driven metric that predicts the utility of synthetic data without requiring model training. Our approach operates in the embedding space of a pre-trained foundation model and represents the dataset through difference vectors between samples. We evaluate whether the weight vector of a linear classifier can be expressed within the subspace spanned by these variations by measuring the relative projection error. Intuitively, if the variations induced by synthetic data capture task-relevant directions, their span can approximate the classifier, resulting in low projection error. Conversely, poor synthetic data fails to span these directions, leading to higher error. Across multiple datasets and architectures, we show that this metric exhibits strong correlation with downstream classification performance of CNNs trained on mixtures of real negative and synthetic positive data. These findings suggest that the proposed metric serves as a practical and informative tool for evaluating synthetic data quality in data-scarce settings.
Authors: Yufeng Hong, Xiaotian Zhou, Yingyan Li, Xiangpo Zhou, Lin Liu, Yadan Luo, Shaoqing Xu, Lei Yang, Ziying Song
Abstract: Existing latent world models for autonomous driving have opened a promising path toward future-aware driving intelligence. However, they typically treat future latent states as prediction targets or auxiliary signals, rather than directly conditioning trajectory planning. This can entangle current and future features in latent space. In this work, we propose DriveFuture, a future-aware latent world modeling framework for autonomous driving that explicitly learns planning-oriented foresight by conditioning the current latent state modeling process on future world states. Specifically, during training, the model first predicts future latent world states from the current latent state and ego action, and then refines the prediction against the ground-truth future latent state via cross-attention. The resulting future-aware latent serves as an explicit condition for a diffusion-based trajectory planner. During inference, DriveFuture conditions on the predicted future latent state instead of the ground-truth future state. DriveFuture achieves SOTA performance on the public NAVSIM benchmarks, reaching \textbf{55.5} EPDMS on NAVSIM-v2 {\textcolor{blue}{\textit{navhard}}}, \textbf{89.9} EPDMS on NAVSIM-v2 {\textcolor{blue}{\textit{navtest}}}, and \textbf{90.7} PDMS on NAVSIM-v1 {\textcolor{blue}{\textit{navtest}}}, respectively. These results suggest that the key to latent world modeling lies not merely in simulating future states, but more importantly in conditioning current decision-making on future states. Notably, as of April 2026, DriveFuture ranks \textbf{1st} on the \href{https://huggingface.co/spaces/AGC2025/e2e-driving-navhard}{NAVSIM-v2 {\textcolor{blue}{\textit{navhard}}}} leaderboard and achieves SOTA performance on \href{https://huggingface.co/spaces/AGC2024-P/e2e-driving-navtest}{NAVSIM-v1 {\textcolor{blue}{\textit{navtest}}}}.
URLs: https://huggingface.co/spaces/AGC2025/e2e-driving-navhard, https://huggingface.co/spaces/AGC2024-P/e2e-driving-navtest
Authors: Xiaoyu Yuan, Niklas Heikkala, Tiina T\"orm\"anen, Hanna J\"arvenoja, Guoying Zhao, Haoyu Chen
Abstract: Understanding human mental states from natural behavior is crucial for intelligent systems in the real world. However, most current research focuses on predicting isolated mental state labels, lacking structured annotations of complex interpersonal interactions. To support structured analysis, we introduce MOTOR-Bench, a carefully-designed benchmark with a real-world dataset MOTOR-dataset, containing 1,440 multimodal video clips in collaborative learning scenarios, reflecting key real-world data challenges including natural class imbalance, visual noise, and domain-specific language. Each sample is labeled by educational experts based on self-regulated learning theory. We further evaluate several state-of-the-art multimodal large language models and multi-agent systems in a zero-shot setting on our MOTOR-Bench. However, their performance on this task remains limited, suggesting that existing methods still struggle with structured reasoning from observable behavior to deeper mental states. To address this challenge, we propose a reasoning multi-agent framework, named MOTOR-MAS. It coordinates multiple agents through a structured agent coordination mechanism to infer explicit behaviors, internal cognitions, and psychological emotions. Experimental results show that our MOTOR-MAS outperforms the best single-model benchmark by 15.93 points in Macro-F1 scores for the three labels of behavior, cognition, and emotion, and outperforms the general multi-agent benchmark by 10.2 points in internal cognition prediction.
Authors: Alaa Asfour, Christopher Indris, Leihan Chen, Tejas Vyas, Guanghui Wang
Abstract: Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial reasoning from a 7B teacher to a 2.29B student model. Our approach achieves 8.7x lower inference latency and a 3x reduction in model size while retaining 54-72% of the teacher's performance. The framework utilizes VGGT as the vision encoder and a multi-task distillation pipeline with uncertainty-aware loss weighting. To improve reasoning without chain-of-thought (CoT) data, we introduce "Hidden CoT": learnable latent tokens that serve as an internal scratchpad before answer generation. This is the first use of latent scratchpad reasoning in distilled 3D VLMs. The student model jointly performs spatial description, depth estimation, and object detection. Experiments on ScanNet and 3D-FRONT show strong spatial understanding, reaching 68-72% accuracy on proximity and contact tasks. Our framework enables efficient 3D scene QA on resource-constrained platforms.
Authors: Ke Zhang, Yunjie Tian, DongDi Zhao, Yijiang Li, Yuanye Liu, Vishal M Patel, Di Fu
Abstract: On-policy distillation (OPD), which supervises a student on its own sampled trajectories, has emerged as a data-efficient post-training method for improving reasoning while avoiding the reward dependence of reinforcement learning and the catastrophic forgetting often observed in standard supervised fine-tuning. However, standard OPD typically computes teacher supervision under noisy student-generated contexts and often relies on a single stochastic teacher rollout per prompt. As a result, the supervision signal can be high-variance: the sampled teacher trajectory can be incorrect, uninformative, or poorly matched to the student's current reasoning behavior. To address this limitation, we propose BRTS, a Best-of-N Rollout Teacher Selection framework for on-policy distillation. BRTS augments standard student-context OPD with a teacher-context supervision branch constructed from the curated teacher trajectory. Rather than distilling from the first sampled teacher rollout, BRTS samples a small pool of teacher trajectories and selects the auxiliary trajectory using a simple priority rule: correctness first, student alignment second. When multiple correct teacher trajectories are available, BRTS chooses the one most aligned with the student's current behavior; when unconditioned teacher samples fail on harder prompts, it invokes a ground-truth-conditioned recovery step to elicit a natural derivation. The selected trajectory is then used to provide reliable teacher-context supervision inside the OPD loop, augmented with an auxiliary loss on the teacher trajectory. Experiments on AIME 2024, AIME 2025, and AMC 2023 show that BRTS improves over standard OPD on challenging reasoning benchmarks, with the largest gains on harder datasets. Our code is available at https://github.com/BWGZK-keke/BRTS.
Authors: Aleksander Zamojski, Kacper Jarczak, Radoslaw Roszczyk
Abstract: This article presents a novel approach to keyframe detection in ultrasound videos, with a particular focus on fetal brain imaging. The proposed model is a composite neural network architecture that combines a Convolutional Neural Network (CNN) with a Recurrent Neural Network (RNN). The CNN extracts spatial features from individual video frames, while the RNN captures temporal dependencies between consecutive frames within each video sequence. The proposed model may improve the efficiency and accuracy of fetal brain ultrasound analysis, thereby supporting earlier detection, diagnosis, and treatment planning for selected fetal brain conditions.
Authors: Shiva Aher
Abstract: DRIVE-C is a controlled corruption dataset designed to evaluate visual perception robustness in autonomous driving systems. It is built from real-world forward-facing driving videos collected across daytime, nighttime, urban, rural, freeway, and parking environments. Clean clips are anonymized via localized face and license plate blurring, then transformed with physics-inspired synthetic degradations. The dataset contains 10 clean clips and 600 corrupted clips spanning 12 camera degradation types across five severity levels, with per-clip metadata and Global Sensor Health Index (GSHI) annotations. DRIVE-C supports robustness benchmarking, degradation-aware modeling, uncertainty estimation, out-of-distribution (OOD) detection, and sensor health monitoring for Advanced Driver Assistance Systems (ADAS). By providing pixel-aligned clean and degraded video clips with fully reproducible corruption parameters, DRIVE-C offers a structured testbed for studying perception reliability under controlled camera degradation.
Authors: Zhipeng Liu, Chunbo Luo
Abstract: Vision-language models (VLMs) enable text-guided object detection but degrade severely under cross-view scenarios where ground and aerial viewpoints differ in altitude, scale, and spatial layout. These geometric changes introduce systematic complexity variations between viewpoints, e.g., ground view images contain dense and highly occluded structures, while aerial images are sparse and globally organized. Fixed VLM fusion mechanisms cannot handle this discrepancy. We propose CrossVL, a framework combining Complexity-Aware Pathway Aggregation (CPA) and Paired Curriculum Learning (PCL) for enhanced cross-view detection for VLM. CPA estimates scene complexity from multimodal statistics and routes visual features through multiple pathways to obtain view-specific representations. PCL leverages semantic consistency of synchronized ground-aerial pairs to provide stable early supervision and then gradually shifts toward randomized sampling. On MAVREC, CrossVL improves Florence-2's aerial mAP from 58.66% to 61.03% and reduces the ground-aerial performance gap from 8.63pp to 6.65pp, while also achieving a 3.3x reduction in variance across random seeds. CPA provides stable complexity-aware feature aggregation, and PCL enhances optimization dynamics. Together, they demonstrate that coordinated architectural and training adaptations are crucial for robust cross-view VLM detection.
Authors: Anushree Berlia
Abstract: We present Fashion Florence, a Florence-2 vision-language model fine-tuned with LoRA to extract structured fashion attributes from clothing images. Given a single photograph, the model generates a JSON object containing category, color, material, style tags, and occasion tags, structured output suitable for direct programmatic consumption by downstream recommendation and retrieval systems. Fine-tuning data is derived from the iMaterialist Fashion dataset (228 labels), where we collapse fine-grained annotations into a compact 6-category, 16-color, 19-style schema via rule-based label engineering. We apply LoRA (r=16, alpha=32) to all decoder linear layers, training for 3 epochs on 3,688 examples. On a held-out test set of 461 images, Fashion Florence achieves 94.6% category accuracy and 63.0% material accuracy, compared to 89.3% / 43.3% for GPT-4o-mini and 87.4% for Gemini 2.5 Flash. Fashion Florence produces valid JSON in 99.8% of outputs while running at 0.77B parameters on a single GPU at zero marginal inference cost. Style tag F1 reaches 0.753 vs. 0.612 (Gemini) and 0.398 (GPT-4o-mini). The model is deployed as a Hugging Face Space and integrated into Loom, an open-source outfit recommendation system.
Authors: Wenhao Liang, Lin Yue, Wei Emma Zhang, Miao Xu, Mingyu Guo, Olaf Maennel, Weitong Chen
Abstract: Post-hoc calibration is usually evaluated as a function of logits or softmax confidence alone, even as routing-augmented architectures increasingly accompany predictions with sample-specific internal routing traces and pair them with claims of calibration-relevant uncertainty. We ask a basic question: do these traces provide stable routing-specific evidence for post-hoc calibration beyond confidence? We study this in Attention-Residual transformers (Kimi Team, 2026) through a matched-confidence diagnostic suite that stratifies examples by routing-derived state, compares subgroup gaps against within-bin routing-permutation nulls, and evaluates matched post-hoc probes differing only in their auxiliary feature. Across our completed AR runs, scalar routing summaries do not provide stable evidence of routing-conditional miscalibration: weighted gaps remain small or seed-sensitive, and only $1$ of $30$ within-bin permutation tests rejects the conditional-null at $\alpha=0.05$ (only on one seed; not stable across seeds in that cell). AR-CondCal, a minimal $2$-D Nadaraya--Watson probe on confidence and routing-depth variance, lies within the seed-variance band of matched confidence-only and predictive-entropy controls and does not reliably improve worst-routing-tertile ECE; bandwidth-sensitivity checks (Scott multiples, CV-NLL, global-ECE oracle) do not change this. A full-vector MLP over $(c, H_1, \ldots, H_L)$ can appear to improve over a linear confidence baseline, but the apparent gain disappears once a capacity-matched confidence-only MLP is included as a control, and shuffled routing profiles achieve comparable performance. Apparent routing-aware calibration gains in this AR setting should not be read as internal-state calibration until matched-confidence, bandwidth, capacity, and permutation controls rule out common confounds.
Authors: Tao Tang, Hong Liu, Xinshun Wang, Wanruo Zhang
Abstract: Although recent studies have made remarkable progress in human mesh recovery, they still exhibit limited robustness to occlusions and often produce inaccurate poses and severe motion jitter due to the insufficient spatial features for occluded body parts. Inspired by the rapid advancements in human motion prediction, we discover that compared to occluded image features, pose sequence inherently contains reliable motion prior for estimating occluded body parts. In this paper, we incorporate Motion Prior for Occluded human mesh recovery, called MoPO. Our MoPO mainly consists of two components: 1) The motion de-occlusion module, where we propose a spatial-temporal occlusion detector to detect joint visibility, and then we propose a lightweight motion predictor to complete the occluded body parts by predicting the most plausible joint positions based on history poses. 2) The motion-aware fusion and refinement module, which fuses the completed joint sequence with image features to estimate human shape and initial human pose. Moreover, the completed joint sequence is further used to refine the final human pose through inverse kinematics, which provides the occlusion-free motion prior for regressing human poses. Extensive experiments demonstrate that MoPO achieves state-of-the-art performance on both occlusion-specific and standard benchmarks, significantly enhancing the accuracy and temporal consistency of occluded human mesh recovery. Our code and demo can be found in the supplementary material.
Authors: Riku Inoue, Shogo Sato, Kazuhiko Murasaki, Tomoyasu Shimada, Toshihiko Nishimura, Ryuichi Tanida
Abstract: Multi-Object Tracking (MOT) in dynamic environments relies on robust temporal reasoning to maintain consistent object identities over time. Transformer-based end-to-end MOT models achieve strong performance by explicitly modeling temporal dependencies, yet training them requires extensive bounding-box and identity annotations. Given the high labeling cost and strong redundancy in videos, Active Learning (AL) is an effective approach to improve annotation efficiency. However, existing AL methods for MOT primarily operate at the frame level, which is structurally misaligned with modern end-to-end trackers whose inference and training rely on multi-frame clips. To bridge this gap, we formulate clip-level active learning and propose Clip-level Uncertainty and Temporal-aware Active Learning (CUTAL). In contrast to frame-based approaches, CUTAL scores each clip using uncertainty metrics derived from multi-frame predictions to capture inter-frame correspondence ambiguities, while enforcing temporal diversity to select an informative and non-redundant subset. Experiments show that CUTAL achieves stronger overall performance than baselines at the same label budgets across MeMOTR and SambaMOTR. Notably, CUTAL achieves performance comparable to full supervision for MeMOTR on both datasets using only 50% of the labeled training data.
Authors: Shijie Wang, Yadan Luo, Zijian Wang, Xin Yu, Zi Huang
Abstract: Fine-grained image retrieval (FGIR) typically relies on supervision from seen categories to learn discriminative embeddings for retrieving unseen categories. However, such supervision often biases retrieval models toward the semantics of seen categories rather than the underlying appearance characteristics that generalize across categories, thereby limiting retrieval performance on unseen categories. To tackle this, we propose GAPan, a Generative Appearance Prior alignment network that reformulates the learning objective from category prediction toward appearance modeling. Technically, GAPan treats retrieval features with an invertible density model based on normalizing flows. In the forward direction, the flow maps all instance features into a latent density space, where each seen category is modeled by a class-conditional Gaussian prior and optimized via exact likelihood estimation. This formulation preserves richer appearance details by leveraging the invertible property of the flows. In the reverse direction, samples from the high-density regions of these learned priors are mapped back to the feature space to produce appearance-aware anchors that reflect intra-category variation. These anchors supervise a prior-driven alignment objective that aligns retrieval embeddings with category-specific appearance distributions, thereby improving generalization to unseen categories. Evaluations demonstrate that our GAPan achieves state-of-the-art performance on both widely-used fine- and coarse-grained benchmarks.
Authors: Kevin Zhu, William Tang, Raphael Hay Tene, Zesheng Liu, Nhut Le, Maryam Rahnemoonfar
Abstract: Rapid and accurate damage assessment following natural disasters is critical for effective emergency response. However, identifying fine-grained damage levels (e.g., distinguishing minor from major roof damage) in UAV imagery remains challenging due to the degradation of texture cues during resizing and extreme class imbalance. We propose DA-SegFormer, a damage-aware adaptation of the SegFormer architecture optimized for high-resolution disaster imagery. Our method introduces a Class-Aware Sampling strategy to guarantee exposure to rare damage features, and it integrates Online Hard Example Mining (OHEM) with Dice Loss to dynamically focus on underrepresented classes. In addition, we employ a resolution-preserving inference protocol that maintains native texture details. Evaluated on the RescueNet dataset, DA-SegFormer achieves 74.61\% mIoU, outperforming the baseline by 2.55\%. Notably, our improvements yield double-digit gains in critical damage classes: Minor Damage (+11.7%) and Major Damage (+21.3%).
Authors: Ziyang Wang, Yue Zhang, Shoubin Yu, Ce Zhang, Zengqi Zhao, Jaehong Yoon, Hyunji Lee, Gedas Bertasius, Mohit Bansal
Abstract: Next-generation visual assistants, such as smart glasses, embodied agents, and always-on life-logging systems, must reason over an entire day or more of continuous visual experience. In ultra-long video settings, relevant information is sparsely distributed across hours or days, making memory a fundamental challenge: models must accumulate information over time, recall prior states, track temporal order, and abstract recurring patterns. However, existing week-long video benchmarks are primarily designed for perception and recognition, such as moment localization or global summarization, rather than reasoning that requires integrating evidence across multiple days. To address this gap, we introduce EgoMemReason, a comprehensive benchmark that systematically evaluates week-long egocentric video understanding through memory-driven reasoning. EgoMemReason evaluates three complementary memory types: entity memory, tracking how object states evolve and change across days; event memory, recalling and ordering activities separated by hours or days; and behavior memory, abstracting recurring patterns from sparse, repeated observations over the whole week period. EgoMemReason comprises 500 questions across three memory types and six core challenges, with an average of 5.1 video segments of evidence per question and 25.9 hours of memory backtracking. We evaluate EgoMemReason on 17 methods across MLLMs and agentic frameworks, revealing that even the best model achieves only 39.6% overall accuracy. Further analysis shows that the three memory types fail for distinct reasons and that performance degrades as evidence spans longer temporal horizons, revealing that long-horizon memory remains far from solved. We believe EgoMemReason establishes a strong foundation for evaluating and advancing long-context, memory-aware multimodal systems.
Authors: Xia Hu, Zhenrui Yue, Brian Potetz, Howard Zhou, Leonidas Guibas, Chun-Ta Lu, Zhicheng Wang
Abstract: As current Multimodal Large Language Models rapidly saturate canonical visual reasoning benchmarks, a key question emerges: do these strong scores genuinely reflect robust visual understanding? We identify a pervasive vulnerability, the \textbf{Cartesian Shortcut}: visual reasoning benchmarks prevalently build on orthogonal grid-based layouts that can be readily discretized into explicit textual coordinates. Models systematically exploit this property, heavily leveraging text-based deductive reasoning to assist visual problem-solving. To systematically dismantle this shortcut, we introduce \textbf{Polaris-Bench}, which re-formulates 53 visual reasoning tasks in Polar coordinate space with paired Cartesian counterparts as reference, while preserving consistent logical constraints and task semantics -- thus fundamentally breaking the orthogonal prior that models exploit. Comprehensive evaluation across $14$ state-of-the-art MLLMs reveals that frontier models achieving $70$--$83\%$ on Cartesian layouts collapse to $31$--$39\%$ on Polar equivalents, with degradation persisting even under complete logical equivalence. Moreover, reasoning gains observed on Cartesian layouts are severely diminished on Polar equivalents. These findings expose a critical deficiency in current MLLMs: the lack of topology-invariant visual reasoning.
Authors: Kanglin Ning, Wenrui Li, Houde Quan, Qifan Li, Xingtao Wang, Xiaopeng Fan
Abstract: Cross-modal knowledge distillation has emerged as an effective strategy for integrating point cloud and image features in 3D perception tasks. However, the modality heterogeneity, spatial misalignment, and the representation crisis of multiple modalities often limit the efficient of these cross-modal distillation methods. To address these limitations in existing approaches, we propose a hyperbolic constrained cross-modal distillation method for multimodal 3D object detection (HGC-Det). The proposed HGC-Det framework includes an image branch and a point cloud branch to extract semantic features from two different modalities. The point cloud branch comprises three core components: a 2D semantic-guided voxel optimization component (SGVO), a hyperbolic geometry constrained cross-modal feature transfer component (HFT), and a feature aggregation-based geometry optimization component (FAGO). Specifically, the SGVO component adaptively refines the spatial representation of the 3D branch by leveraging semantic cues from the image branch, thereby mitigating the issue of inadequate representation fusion. The HFT component exploits the intrinsic geometric properties of hyperbolic space to alleviate semantic loss during the fusion of high-dimensional image features and low-dimensional point cloud features. Finally, the FAGO compensates for potential spatial feature degradation introduced by the 2D semantic-guided voxel optimization component. Extensive experiments on indoor datasets (SUN RGB-D, ARKitScenes) and outdoor datasets (KITTI, nuScenes) demonstrate that our method achieves a better trade-off between detection accuracy and computational cost.
Authors: Haobo Wang, Xiaorong Ma, Weiqi Luo, Xiaojun Jia, Jiwu Huang
Abstract: Adversarial perturbations can mislead Multimodal Large Language Models (MLLMs) recognize a benign image as a specific target object, posing serious risks in safety-critical scenarios such as autonomous driving and medical diagnosis. This makes transfer-based targeted attacks crucial for understanding and improving black-box MLLM robustness. Existing transfer-based targeted attack methods typically rely on the final global features of the surrogate encoder and anchor optimization to original-resolution target crops, leading to their limited transferability and robustness. To address these challenges, we propose Progressive Resolution Processing and Adaptive Feature Alignment (PRAF-Attack), a targeted transfer-based attack framework that integrates multi-scale global semantic guidance with robust intermediate-layer local alignment. Unlike prior methods that align only the surrogate encoder's final layer, we design an adaptive feature alignment strategy that leverages intermediate representations to enhance transferability. Specifically, we introduce an adaptive intermediate layer selection mechanism to identify transferable hierarchical features across surrogate ensembles via gradient consistency, along with an adaptive patch-level optimization strategy that preserves highly correlated local regions through efficient patch filtering. To overcome the reliance on fixed original-resolution target crops, we propose a progressive resolution processing strategy that gradually refines optimization from coarse to fine, enabling the attack to better exploit target information at multiple scales and achieve stronger transferability. We evaluate PRAF-Attack on a diverse suite of black-box MLLMs, including six open-source models and six closed-source commercial APIs. Compared with seven state-of-the-art targeted attack baselines, the proposed PRAF-Attack consistently achieves superior transferability.
Authors: Junzhe Chen, Siyuan Meng, Yuxi Chen, Man Zhao, Wenyao Gui, Xiaojie Guo
Abstract: Video large language models (Video-LLMs) have made strong progress in general video understanding, but their ability to maintain temporal object consistency remains underexplored. Existing benchmarks often emphasize event recognition, action understanding, or coarse temporal reasoning, while rarely testing whether models can preserve the identity, state, and continuity of the same object across occlusion, disappearance, reappearance, state transitions, and cross-object interactions. We introduce TOC-Bench, a diagnostic benchmark for evaluating temporal object consistency in Video-LLMs. TOC-Bench is object-track grounded: each queried subject is linked to a per-frame trajectory and a structured temporal event timeline. To ensure that questions require temporally ordered visual evidence rather than language priors, single-frame shortcuts, or unordered frame cues, we design a three-layer temporal-necessity filtering protocol, which removes 60.7% of candidate QA pairs and retains 17,900 temporally dependent items across 10 diagnostic dimensions. From this pool, we construct a human-verified benchmark with 2,323 high-quality QA pairs over 1,951 videos. Experiments on representative Video-LLMs show that temporal object consistency remains a major unsolved challenge, with notable weaknesses in event counting, event ordering, identity-sensitive reasoning, and hallucination-aware verification, even when models perform well on general video understanding benchmarks. These results suggest that object-centric temporal coherence is a key bottleneck for current Video-LLMs, and that TOC-Bench provides a focused platform for diagnosing and improving object-aware temporal reasoning. The resource is available at https://github.com/cjzcjz666/toc_bench.git.
Authors: Phuoc-Nguyen Bui, Van-Nguyen Pham, Duc-Tai Le, Junghyun Bum, Hyunseung Choo
Abstract: Medical image segmentation is a critical task in computer-aided diagnosis and treatment planning. However, deep learning models often struggle to generalize across datasets due to domain shifts arising from variations in imaging protocols, scanner types, and patient populations. Traditional domain generalization (DG) methods utilize causal feature learning, adversarial consistency, and style augmentation to improve segmentation robustness. While effective, these approaches rely on explicit feature alignment, adversarial objectives, or handcrafted augmentations, which may not fully exploit the capabilities of foundation models. Recently, the Segment Anything Model (SAM) has demonstrated strong generalization capabilities in segmentation tasks. SAM-based DG methods attempt to improve medical image segmentation. However, these approaches primarily operate in the spatial domain and overlook frequency-based discrepancies that significantly affect model robustness. In this work, we propose Frequency-based Domain Generalization with SAM (FSAM), a novel framework that integrates Low-Rank Adaptation (LoRA) for efficient fine-tuning and a frequency adapter to incorporate frequency-domain representations for single-source domain generalization. FSAM enhances SAM's segmentation robustness by extracting domain-invariant high-frequency features, mitigating frequency-related domain shifts. Experimental results on fundus and prostate datasets demonstrate that FSAM outperforms existing traditional DG and SAM-based DG approaches in domain generalization. Codes and pre-trained models will be made available on GitHub.
Authors: Qingchao Jiang, Zhenxuan Hou, Zhiying Zhu, Zhenxing Qian, Xinpeng Zhang, Zaiwang Gu
Abstract: With the rapid development of deep generative models, forged facial images are massively exploited for illegal activities. Although existing synthetic face detection methods have achieved significant progress, they suffer from the inherent limitation of overconfidence due to their reliance on the Softmax activation function. Thus, these methods often lead to unreliable predictions when encountering unknown Out-of-Distribution (OOD) images, and cannot ascertain the model's uncertainty in its prediction. Meanwhile, most existing methods require massive high-quality annotated data, which greatly limits their practicability across diverse scenarios. To address these limitations, we propose EMSFD (Evidence-based decision Modeling for Synthetic Face Detection with uncertainty-driven active learning), an approach designed to enhance detection reliability and generalizability. Specifically, EMSFD models class evidence using the Dirichlet distribution and explicitly incorporates model uncertainty into the prediction process. Furthermore, during training, the estimated uncertainty is exploited to prioritize more informative samples from the unlabeled pool for annotation, thereby reducing labeling cost and improving model generalization. Extensive experimental evaluations demonstrate that our method enhances the interpretability of synthetic face detection. Meanwhile, our method yields a 15\% increase in accuracy compared to existing state-of-the-art (SOTA) baselines, which demonstrates the superior detection performance and generalizability of our approach. Our code is available at: https://github.com/hzx111621/EMSFD.
Authors: Yiwei Ou, Chung Ching Cheung, Jun Yang Ang, Xiaobin Ren, Ronggui Sun, Guansong Gao, Kaiqi Zhao, Manfredo Manfredini
Abstract: We present Urban-ImageNet, a large-scale multi-modal dataset and evaluation benchmark for urban space perception from user-generated social media imagery. The corpus contains over 2 Million public social media images and paired textual posts collected from Weibo across 61 urban sites in 24 Chinese cities across 2019-2025, with controlled benchmark subsets at 1K, 10K, and 100K scale and a full 2M corpus for large-scale training and evaluation. Urban-ImageNet is organized by HUSIC, a Hierarchical Urban Space Image Classification framework that defines a 10-class taxonomy grounded in urban theory. The taxonomy is designed to distinguish activated and non-activated public spaces, exterior and interior urban environments, accommodation spaces, consumption content, portraits, and non-spatial social-media content. Rather than treating urban imagery as generic scene data, Urban-ImageNet evaluates whether machine perception models can capture spatial, social, and functional distinctions that are central to urban studies. The benchmark supports three tasks within one standardized library: (T1) urban scene semantic classification, (T2) cross-modal image-text retrieval, and (T3) instance segmentation. Our experiments evaluate representative vision, vision-language, and segmentation models, revealing strong performance on supervised scene classification but more challenging behavior in cross-modal retrieval and instance-level urban object segmentation. A multi-scale study further examines how model performance changes as balanced training data increases from 1K, 10K to 100K images. Urban-ImageNet provides a unified, theory-grounded, multi-city benchmark for evaluating how AI systems perceive and interpret contemporary urban spaces across modalities, scales, and task formulations. Dataset and benchmark are available at: huggingface.co/datasets/Yiwei-Ou/Urban-ImageNet and github.com/yiasun/dataset-2.
Authors: Peng Jia, Zhen Xiao, Jia Li, Xueliang Liu, Zhenzhen Hu, Lingyun Yu
Abstract: High-quality, real-time talking head synthesis remains a fundamental challenge in computer vision. Existing reconstruction- and rendering-based methods typically rely on identity-specific models, limiting cross-identity generalization. To address this issue, we propose SDTalk, a one-shot 3D Gaussian Splatting (3DGS)-based framework that generalizes to unseen identities without personalized training or fine-tuning. Our framework comprises two modules with a two-stage training strategy. In the first stage, we incorporate structured facial priors into the reconstruction module and separately predict 3DGS parameters for visible and occluded regions, enabling complete head reconstruction from a single image. In the second stage, we introduce a dual-branch motion field to model coarse and fine facial dynamics, improving detail fidelity and lip synchronization. Experiments demonstrate that SDTalk surpasses existing methods in both visual quality and inference efficiency.
Authors: Yang Shen, Yusen Cai, Weronika Hryniewska-Guzik, Qing Lin, Mengmi Zhang
Abstract: Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP), a spatially aware pretext regression task that predicts the relative position and scale between a pair of disentangled local views from the same image. By modeling part-to-part relationships in a continuous geometric space, SP encourages representations to capture fine-grained spatial dependencies beyond invariant categorical semantics, thereby learning the compositional structure of visual scenes. SP is implemented as a decoupled plug-in and can be seamlessly integrated into diverse SSL frameworks. Extensive experiments show consistent improvements across image recognition, fine-grained classification, semantic segmentation, and depth estimation, as well as substantial gains in out-of-distribution robustness for object recognition. To evaluate spatial reasoning, we introduce (1) a position and scale prediction task on image patch pairs and (2) a jigsaw understanding task requiring patch reordering and recognition after reconstruction. Strong performance on these tasks indicates improved spatial structure and geometric awareness. Overall, explicitly modeling spatial information provides an effective inductive bias for SSL, leading to more structured representations and better generalization. Code and models will be released.
Authors: Kuan Zhang, Dongchen Liu, Qiyue Zhao, Tianyu Xin, Yue Su, Haisheng Wang, Han Yin, Hongbo Ma, Peize Li, Tianjun Gu, Xiangnan Wu, Xinran Zhang, Yongxuan Li, Zirong Chen, Yiming Li
Abstract: The real world unfolds along a single set of physics laws, yet human intelligence demonstrates a remarkable capacity to generalize experiences from this singular physical existence into a multiverse of games, each governed by entirely different rules, aesthetics, physics, and objectives. This omni-reality adaptability is a hallmark of general intelligence. As Artificial Intelligence progresses towards Artificial General Intelligence, the multiverse of games has evolved from mere entertainment into the ultimate ground for training and evaluating AGI. The pursuit of this generality has unfolded across four eras: from environment-specific symbolic and reinforcement learning agents, to current large foundation models acting as generalist players, and toward a future creator stage where agent both creates new game worlds and continually evolves within them. We trace the full lifecycle of a generalist game player along four interdependent pillars: Dataset, Model, Harness, and Benchmark. Every advance across these pillars can be read as an attempt to break one of five fundamental trade-offs that currently bound the whole system. Building on this end-to-end view, we chart a five-level roadmap, progressing from single-game mastery to the ultimate creator stage in which the agent simultaneously creates and evolves within theoretical game multiverse. Taken together, our work offers a unified lens onto a rapidly shifting field,and a principled path toward the omnipotent generalist agent capable of seamlessly mastering any challenge within the multiverse of games, thereby paving the way for AGI.
Authors: Chaolei Han, Hongsong Wang, Xin Gong, Jie Gui
Abstract: Online Temporal Action Localization (On-TAL) aims to detect the occurrence time and category of actions in untrimmed streaming videos immediately upon their completion. Recent advancements in this field focus on developing more sophisticated frameworks, shifting from Online Action Detection (OAD)-based aggregation paradigm to instance-level understanding. However, existing approaches are typically trained on specific domains and often exhibit limited generalization capabilities when applied to arbitrary videos, particularly in the presence of previously unseen actions. In this paper, we introduce a new task called Online Zero-shot Temporal Action Localization (OZ-TAL), which aims to detect previously unseen actions in an online fashion. Furthermore, we propose a training-free framework that leverages off-the-shelf Vision-Language Models (VLMs) while introducing additional mechanisms to enhance visual representations and mitigate their inherent biases. We establish new benchmarks and representative baselines for OZ-TAL on THUMOS14 and ActivityNet-1.3, and extensive experiments demonstrate that our method substantially outperforms existing state-of-the-art approaches under both offline and online zero-shot settings.
Authors: Xiaotian Hu, Mingxuan Liu, Hongjia Yang, Juncheng Zhu, Yijin Li, Yifei Chen, Haoxiang Li, Tongxi Song, Zihan Li, Yingqi Hao, Ziyu Li, Yujin Zhang, Gang Ning, Yi Liao, Haibo Qu, Qiyuan Tian
Abstract: Spatio-temporal fetal brain atlases are important for characterizing normative neurodevelopment and identifying congenital anomalies. However, existing atlas construction pipelines necessitate days for slice-to-volume reconstruction (SVR) to generate high-resolution 3D brain volumes and several additional days for iterative volume registration, thereby rendering atlas construction from large-scale cohorts prohibitively impractical. We address these limitations with INFANiTE, an Implicit Neural Representation (INR) framework for high-resolution Fetal brain spatio-temporal Atlas learNing from clinical Thick-slicE MRI scans, bypassing both the costly SVR and the iterative non-rigid registration steps entirely, thereby substantially accelerating atlas construction. Extensive experiments demonstrate that INFANiTE outperforms existing baselines in subject consistency, reference fidelity, intrinsic quality and biological plausibility, even under challenging sparse-data settings. Additionally, INFANiTE reduces the end-to-end processing time (i.e., from raw scans to the final atlas) from days to hours compared to the traditional 3D volume-based pipeline (e.g., SyGN), facilitating large-scale population-level fetal brain analysis. Our code is publicly available at: https://anonymous.4open.science/r/INFANiTE-5D74
Authors: Yuna Lee, Kyoungho Min, Yulhwa Kim
Abstract: Recent advancements in Vision-Language Models (VLMs) enable large language models (LLMs) to process high-resolution images, significantly improving real-world multimodal understanding. However, this capability introduces a large number of vision tokens, resulting in substantial computational overhead. To mitigate this issue, various vision token pruning methods have been proposed. Nevertheless, existing approaches predominantly rely on learned semantic features within the model to capture visual redundancy. Moreover, they lack adaptive mechanisms to adjust pruning strategies according to the complexity of the input image. In this paper, we propose ERASE, a two-stage vision token pruning framework that identifies and retains salient tokens through pruning strategies adaptive to image complexity. Experiment results demonstrate that ERASE significantly reduces vision tokens while preserving accuracy. For Qwen2.5-VL-7B, at a token pruning ratio of 85\%, ERASE retains 89.46% of the original model accuracy, whereas the best prior method retains only 78.1%. Our code is available at https://github.com/Tuna-Luna/ERASE.
Authors: Sunwoo Park, Taesung Kwon, Jong Chul Ye
Abstract: Recent 4D generation methods complete scene-level missing information using generative models and reconstruct the scene into radiance-based representations. However, these pipelines often present geometric inconsistencies in the generated content, and the radiance-based reconstruction requires expensive optimization. Furthermore, radiance-based representations often absorb these geometric inconsistencies into their view-dependent nature, failing to enforce the grounded geometric consistency. To address these issues, we propose Geometric 4D Stitching, an efficient framework that explicitly identifies missing geometric regions and complements them with geometrically grounded 4D stitches. As a result, our method constructs 4D scene representations in under 10 minutes on a single NVIDIA RTX 5090 GPU per one-step scene expansion, while improving geometric consistency. Moreover, we demonstrate that our explicit 4D stitching supports interative expansion of 4D mesh as well as 4D scene editing.
Authors: Yeongtak Oh, Dongwook Lee, Sangkwon Park, Heeseung Kim, Sungroh Yoon
Abstract: While multimodal large language models have advanced across text, image, and audio, personalization research has remained primarily vision-language, with unified omnimodal benchmarking that jointly covers text, image, and audio still limited, and lacking the methodological rigor to account for absent-persona scenarios or systematic grounding studies. We introduce Omni-Persona, the first comprehensive benchmark for omnimodal personalization. We formalize the task as cross-modal routing over the \emph{Persona Modality Graph}, encompassing 4 task groups and 18 fine-grained tasks across ${\sim}750$ items. To rigorously diagnose grounding behavior, we propose \emph{Calibrated Accuracy ($\mathrm{Cal}$)}, which jointly rewards correct grounding and appropriate abstention, incorporating absent-persona queries within a unified evaluation framework. On our dedicated experiments, three diagnostic findings emerge: (i) open-source models show a consistent audio-vs-visual grounding gap that RLVR partially narrows via dense rule-based supervision; (ii) answerable recall and parameter scale are incomplete diagnostics, since strong recall can coexist with absent-persona hallucination and larger models do not always achieve higher $\mathrm{Cal}$, exposing calibration as a separate evaluation axis; and (iii) SFT is bounded by the difficulty of constructing annotated ground-truth supervision at scale, while RLVR generalizes more consistently through outcome-level verifiable feedback yet drifts toward conservative behavior and lower generation quality under our reward design. Omni-Persona thus serves as a diagnostic framework that surfaces the pitfalls of omnimodal personalization, guiding future post-training and reward design.
Authors: Minh Khoi Nguyen, Dai Lam Le, Amir Reza Jafari, Tuan Dung Nguyen, Mai Hong Son, Mai Huy Thong, Quang Huy Nguyen, Thanh Trung Nguyen, Reza Farahbakhsh, Noel Crespi, Phi Le Nguyen
Abstract: Large vision-language models (VLMs) demonstrate strong performance in medical image understanding, but frequently generate clinically plausible yet incorrect statements, raising significant safety concerns. Existing medical hallucination benchmarks primarily focus on 2D imaging with one-shot diagnostic questions, offering limited insight into whether predictions are grounded in correct localization and abnormality identification, allowing critical reasoning errors to remain hidden behind seemingly correct diagnoses. We introduce Med-StepBench, the first large-scale benchmark for step-wise hallucination detection in 3D oncological PET/CT, comprising over 12,000 images and more than 1,000,000 image-statement pairs across volumetric and multi-view 2D data, which decomposes clinical reasoning into four expert-designed diagnostic stages. Using clinician-verified annotations, we perform the first step-level evaluation of general-purpose and medical VLMs, revealing systematic failure modes obscured by aggregate accuracy metrics. Furthermore, we show that current VLMs are highly susceptible to adversarial yet clinically plausible intermediate explanations, which significantly amplify hallucinations despite contradictory visual evidence. Together, our findings highlight fundamental limitations in grounding multi-step clinical reasoning and establish Med-StepBench as a rigorous benchmark for developing safer and more reliable medical VLMs.
Authors: Yujia Cai, Boxuan Li, Chenghao Xu, Jiexi Yan
Abstract: Query-based image retrieval (QBIR) requires retrieving relevant images given diverse and often stylistically heterogeneous queries, such as sketches, artworks, or low-resolution previews. While large-scale vision--language representation models (VLRMs) like CLIP offer strong zero-shot retrieval performance, they struggle with distribution shifts caused by unseen query styles. In this paper, we propose the Hypernetwork-driven Style-adaptive Retrieval (Hystar), a lightweight framework that dynamically adapts model weights to each query's style. Hystar employs a hypernetwork to generate singular-value perturbations ($\Delta S$) for attention layers, enabling flexible per-input adaptation, while static singular-value offsets on MLP layers ensure cross-style stability. To better handle semantic confusions across styles, we design StyleNCE as part of Hystar, an optimal-transport-weighted contrastive loss that emphasizes hard cross-style negatives. Extensive experiments on multi-style retrieval and cross-style classification benchmarks demonstrate that Hystar consistently outperforms strong baselines, achieving state-of-the-art performance while being parameter-efficient and stable across styles.
Authors: Xiaohu Lu, Hamed Khatounabadi, Hayder Radha
Abstract: With the advancement of autonomous driving, numerous annotated multi-modality datasets have become available. This presents an opportunity to develop domain-adaptive 3D object detectors for new environments without relying on labor-intensive manual annotations. However, traditional domain adaptation methods typically focus on a single source domain or a single modality, limiting their effectiveness in multi-source, multi-modality scenarios. In this paper, we propose a novel framework for multi-source, multi-modality unsupervised domain adaptation in 3D object detection for autonomous driving. Given multiple labeled source domains and one unlabeled target domain, our framework first introduces hierarchical spatially-conditioned (HSC) domain classifiers, which jointly align features from both camera and LiDAR modalities at two distinct levels for each source-target domain pair. To effectively leverage information from multiple source domains, we construct a prototype graph between each pair of domains. Based on this, we develop a prototype graph weighted (PGW) multi-source fusion strategy to aggregate predictions from multiple source detection heads. Experimental results on three widely used 3D object detection datasets - Waymo, nuScenes, and Lyft - demonstrate that our proposed framework effectively integrates information across both modalities and source domains, consistently outperforming state-of-the-art methods.
Authors: Shuyang Hou, Ziqi Liu, Haoyue Jiao, Zhangyan Xu, Xiaopu Zhang, Lutong Xie, Yaxian Qing, Jianyuan Liang, Xuefeng Guan, Huayi Wua
Abstract: Pixel-level slum mapping has long been constrained by limited cross-city generalisation, the absence of continuous density estimation, and weak global comparability. AlphaEarth Foundations (AEF), a globally consistent 64-dimensional annual surface embedding at 10 m, offers a new analysis-ready basis for lightweight slum monitoring, but its applicability to slum detection - an indirectly coupled task shaped by both built form and socio-economic processes - remains untested. We evaluate AEF on slum classification and sub-pixel density estimation across 12 cities and 69 city-year pairs (2017-2024), using GRAM pseudo-masks as supervisory labels. The evaluation spans four training strategies, two protocols (random split and 3x3 spatial block cross-validation), six auxiliary feature configurations, and five baseline models, complemented by representation-level analyses (PCA, SHAP) and full-AOI mapping. Five findings emerge. (1) Same-city cross-year training is optimal under both protocols (median spatial F1 = 0.616, R^2 = 0.466); temporal expansion outperforms cross-city transfer, indicating city-scale representational drift. (2) Regression R^2 is driven primarily by zero/non-zero boundary discrimination: positive-pixel R^2 is consistently negative across all cities, revealing limited capacity to model intra-pixel density gradients at 10 m. (3) PC36 is consistently top-ranked across tasks; classification saturates at k = 32 while regression remains unsaturated at k = 64. (4) POI features yield the largest density gain (Delta R^2 = +0.064). (5) For six cities meeting dual-task usability thresholds, full-AOI inference across 2017-2024 preserves slum cluster structure (mean SSIM = 0.926). The study delineates the capabilities and complementarity needs of foundation-model embeddings for slum monitoring.
Authors: Qingchao Jiang, Zhenxuan Hou, Zhiying Zhu, Zhenxing Qian, Xinpeng Zhang, Zaiwang Gu
Abstract: The rapid evolution of generative paradigms has enabled the creation of highly realistic imagery, which escalating the risks of identity fraud and the dissemination of disinformation. Most existing approaches frame face forgery detection as a fully supervised binary classification problem. Consequently, these models typically exhibit significant performance decay when tasked with detecting forgeries from previously unseen generative paradigms. Furthermore, these methods focus exclusively on either DeepFakes or fully synthesized faces, thereby failing to provide a generalized framework for universal face forgery detection. In this paper, we address this challenge by introducing FADNet (Face Authenticity Detector Net), % a self-supervised framework that which reformulates face forgery detection as a one-class classification (OCC) task. By training exclusively on authentic facial data to capture their intrinsic representations, FADNet flags any image whose feature embedding deviates significantly from the learned distribution of real faces as a forgery. The framework incorporates Evidential Deep Learning (EDL) to quantify predictive uncertainty and utilizes a plug-and-play pseudo-forgery image generator (PFIG) to tighten decision boundaries around authentic data. Extensive experimental evaluations on the DF40 and ASFD benchmarks demonstrate that FADNet achieves superior performance and generalization capabilities. Specifically, FADNet substantially outperforms existing state-of-the-art (SOTA) methods, yielding a remarkable average accuracy of 96.63\% and an average precision of 98.83\%.
Authors: Feihong Yan, Shaoyu Liu, Haixuan Wang, Shuai Lu, Linfeng Zhang, Huiqi Li, Xiangyang Ji
Abstract: Visual Autoregressive (VAR) models have emerged as a strong alternative to diffusion for image synthesis, yet their fixed training resolution prevents direct generation at higher resolutions. Naively transferring training-free extrapolation methods from LLMs or diffusion models to VAR yields three characteristic failure modes: global repetition, local repetition, and detail degradation. We trace them to a unified band-stage mismatch: VAR generates images in a coarse-to-fine, scale-wise process where each stage is driven by a distinct dominant RoPE frequency band, and each failure mode emerges when the dominant band of a particular stage is disrupted. Building on this insight, we propose Stage-Aware RoPE Remapping, a training-free strategy that assigns each frequency band a stage-specific remapping rule, jointly suppressing all three failure modes. We further observe that attention becomes systematically dispersed as the image resolution increases. Existing methods typically depend on predefined attention scaling factors, which are neither adaptive to the target resolution nor capable of faithfully capturing the actual extent of attention dispersion. We therefore propose Entropy-Driven Adaptive Attention Calibration, which quantifies dispersion via a resolution-invariant normalized entropy and yields a closed-form per-head scaling factor that realigns the extrapolated-resolution attention entropy with its training-resolution counterpart. Extensive experiments show that our method consistently outperforms prior resolution-extrapolation methods in both structural coherence and fine-detail fidelity. Our code is available at https://github.com/feihongyan1/ExtraVAR.
Authors: Yufeng Zhu, Chunlei Shi, Yongchao Feng, Dan Niu
Abstract: Precipitation nowcasting aims to forecast short-term radar echo sequences for extreme weather warning, where both prediction fidelity and inference efficiency are critical for real-world deployment. However, diffusion-based models, despite their strong generative capability, suffer from slow inference due to multi-step sampling trajectories, limiting their practical usability. Conditional Flow Matching (CFM) improves efficiency via straightened trajectories, but relies on latent space compression, which inevitably discards high-frequency physical details and degrades fine-grained prediction quality. To address these limitations, we propose PixelFlowCast, a two-stage probabilistic forecasting framework that achieves both high-efficiency and high-fidelity prediction without latent compression. Specifically, in the first stage, a deterministic model first produces coarse forecasts to capture global evolution trends. In the subsequent stage, the proposed KANCondNet extracts deep spatiotemporal evolution features to provide accurate conditional guidance. Based on this, a latent-free, few-step Pixel Mean Flows (PMF) predictor employs an $x$-prediction mechanism to generate high-quality predictions, effectively preserving fine-grained structures while maintaining fast inference. Experiments on the publicly available SEVIR dataset demonstrate that PixelFlowCast outperforms existing mainstream methods in both prediction accuracy and inference efficiency, particularly for long sequence forecasting, highlighting its strong potential for real-world operational deployment.
Authors: Jiameng Li, Minye Wu, Jiezhang Cao, Aleksei Tiulpin, Matthew B. Blaschko
Abstract: Long-form video understanding remains challenging for Video Large Language Models (VideoLLMs), as the dense frame sampling introduces massive visual tokens while sparse sampling risks missing critical temporal evidence and leading to LLM hallucination. Existing training-free token reduction methods either treat videos equally as static images or rely on segment-level merging heuristics, which weaken fine-grained spatiotemporal modeling and introduce additional overhead. In this paper, we propose EchoPrune, a lightweight and training-free token pruning method that improves temporal resolution under a fixed LLM-side visual token budget. Our core idea is to interpret redundant video tokens as temporal echoes: if a token is well reconstructed from the previous frame, it is merely a temporally redundant echo; otherwise, it may capture new events, motion, or query-relevant visual evidence. Based on this insight, EchoPrune scores visual tokens by (i) query-guided crossmodal relevance and (ii) temporal reconstruction error, measured by correspondence matching and echo matching across consecutive frames. The selected tokens preserve task-relevant cues and temporal novelty while suppressing predictable redundancy, allowing VideoLLMs to observe more frames without increasing the decoding budget. Extensive experiments on LLaVA-OV, Qwen2.5VL, and Qwen3VL across six video understanding benchmarks show that EchoPrune enables VideoLLMs to process up to 20x frames under the same token budget, yielding improved performance (+8.6%) and inference speedup (5.6x for prefilling) on Qwen2.5VL-7B.
Authors: Zubair Faruqui, Rahul Dubey
Abstract: Deep neural networks for medical image diagnosis often achieve high predictive accuracy while relying on spurious or clinically irrelevant visual cues, limiting their trustworthiness in practice. Post-hoc explanation methods are widely used to visualize model decisions in the form of saliency maps; however, these explanations do not influence how models learn during training, allowing non-causal or confounding features to persist. This motivates the incorporation of explanation supervision directly into the training objective to guide model attention toward clinically meaningful regions and promote clinically grounded decision-making. This paper presents a systematic approach to integrate explanation loss into model training and analyzes how different explanation loss designs and supervision strengths influence both predictive performance and spatial faithfulness of explanations. To quantitatively assess interpretability, two complementary explanation performance metrics-annotation coverage and saliency precision-are introduced, enabling rigorous evaluation beyond qualitative visualization. Our experimental results reveal a clear trade-off between explanation quality and explanation loss coefficients. Furthermore, quantitative statistical analysis yields consistently improved explanation alignment while maintaining comparable accuracy. Experiments were conducted on annotated chest X-ray datasets; however, the proposed framework is applicable to a broad range of annotated biomedical imaging modalities. Overall, these findings demonstrate that explanation supervision is not a monolithic design choice and provide practical guidance for incorporating explanation loss into training objectives under noisy clinical annotations.
Authors: Yaning Zhang, Tianyi Wang, Zan Gao, Yibo Zhao, Chunjie Ma, Meng Wang
Abstract: The swift advancement in photo-realistic face generation technology has sparked considerable concerns across society and academia, emphasizing the requirement of generalizable face forgery detection and localization methods. Prior works tend to capture face forgery patterns across multiple domains using image modality, other modalities like fine-grained texts are not comprehensively investigated, which restricts the generalization capability of models. Besides, they usually analyze facial images created by GAN, but struggle to identify and localize those synthesized by diffusion. To solve the problems, in this paper, we devise a novel multi-domain fine-grained vision-language reconstruction (MFVLR) model, which explores comprehensive and diverse visual forgery traces via language-guided face forgery representation learning, to achieve generalizable diffusion-synthesized face forgery detection and localization (DFFDL). Specifically, we devise a fine-grained language transformer that studies general fine-grained language embeddings using language reconstruction. We propose a multi-domain vision encoder to capture general and complementary visual forgery patterns across the image and residual domains. A vision decoder is designed to reconstruct image appearance and achieve forgery localization. Besides, we propose an innovative plug-and-play vision injection module to enhance the interaction between the vision and language embeddings. Extensive experiments and visualizations demonstrate that our network outperforms the state of the art on different settings like cross-generator, cross-forgery, and cross-dataset evaluations.
Authors: Liangyang Ouyang, Ruicong Liu, Caixin Kang, Yifei Huang, Yoichi Sato
Abstract: Video generation has advanced rapidly, producing photorealistic videos from text or image prompts. Meanwhile, film production and social robotics increasingly demand multi-person videos with rich social interactions, including conversations, gestures, and coordinated actions. However, existing models offer no explicit control over interactions, such as who performs which action, when it occurs, and toward whom it is directed. This often results in wrong person performing unintended actions (actor-action mismatch), disordered social dynamics, and wrong action targets. To address these challenges, we present SocialDirector, a training-free interaction controller that enhances the generation model by modulating cross-attention maps. SocialDirector contains two modules: Social Actor Masking and Directional Reweighting. Social Actor Masking constrains each person's visual tokens to attend only to their own textual descriptions via a spatiotemporal mask, avoiding actor-action mismatch and disordered social dynamics. Directional Reweighting amplifies attention to directional words (e.g., "leftward", "right"), leading each action towards its intended target. To evaluate generated social interactions, we annotate existing datasets with interaction descriptions and build a fully automated evaluation pipeline powered by open-source VLMs. Experiments on different video generation models show that SocialDirector significantly improves interaction fidelity and approaches the upper bound set by real videos.
Authors: Guhnoo Yun, Juhan Yoo, Kijung Kim, Dong Hwan Kim
Abstract: This paper describes an initiation of interaction(IoI) detection framework without keywords for human-robot interaction(HRI) based on audio and vision sensor fusion in a domestic environment. In the proposed framework, the robot has its own audio and vision sensors, and can employ external vision sensor for stable human detection and tracking. When the user starts to speak while looking at the robot, the robot can localize his or her position by its sound source localization together with human tracking information. Then the robot can detect the IoI if it perceives the face of the speaker faces the robot. In case that the user does not speak directly, the robot can also detect the IoI if he or she looks at the robot for more than predefined periods of time. A state transition model for the proposed IoI detection framework is designed and verified by experiments with a mobile robot. In order to implement and associate our model in a robot architecture, all the components are implemented and integrated in the Robot Operating System(ROS) environment.
Authors: Vinduja T., Ashish M., Ajay Waghumbare, Upasna Singh
Abstract: We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperbolic space $\mathbb{H}^d$ to natively preserve the hierarchical tree topology of the human skeleton. Current state-of-the-art pose estimators aim to capture complex joint dynamics by relying on transformers and graph convolutional networks. Since these architectures operate exclusively in Euclidean space which fundamentally mismatches the inherent tree structure of the human body, these methods inevitably suffer from exponential volume distortion and struggle to maintain structural coherence. To this end, we depart from flat spaces and aim to improve geometric fidelity with Hyperbolic Kinematic Phase-Space Attention (HKPSA), natively embedding complex joint relationships without distortion, alongside a multi-scale windowed hyperbolic attention mechanism that efficiently models temporal dynamics in $O(TW)$ complexity. Furthermore, to overcome the well-known instability of training non-Euclidean manifolds, HYPERPOSE introduces a novel Riemannian loss suite and an uncertainty-weighted curriculum, enforcing physical geodesic constraints like bone length and velocity consistency. Extensive evaluations on the Human3.6M and MPI-INF-3DHP datasets demonstrate that HYPERPOSE achieves state-of-the-art structural and temporal coherence, significantly reducing both volume distortion and velocity error, while establishing new state-of-the-art benchmarks in overall positional accuracy.
Authors: Tingshu Mou, Jiabo He, Renying Wang, Ce Liu, Hao Yang, Tiehua Zhang, Jingjing Chen, Xingjun Ma
Abstract: Recent advances in Multi-modal Large Language Models (MLLMs) target 3D spatial intelligence, yet the progress has been largely driven by post-training on curated benchmarks, leaving the inference-time approach relatively underexplored. In this paper, we take a training-free perspective and introduce ViSRA, a human-aligned Video-based Spatial Reasoning Agent, as a framework to probe the spatial reasoning mechanism of MLLMs. ViSRA elicits spatial reasoning in a modular and extensible manner by leveraging explicit spatial information from expert models, enabling a plug-and-play flexible paradigm. ViSRA offers two key advantages: (1) human-aligned and transferable 3D understanding rather than task-specific overfitting; and (2) no post-training computational cost along with heavy manual curation of spatial reasoning datasets. Experimental results demonstrate consistent improvement across a set of MLLMs on both existing benchmarks and unseen 3D spatial reasoning tasks, with ViSRA outperforming baselines by up to a 15.6% and 28.9% absolute margin respectively.
Authors: Donghyun Kim, Jaehyoung Park
Abstract: Autonomous driving scenes range from empty highways to dense intersections with dozens of interacting road users, yet current 3D detection models apply a fixed computation budget to every frame, wasting resources on simple scenes while lacking capacity for complex ones. Existing approaches compound this problem: Transformer-based interaction models scale quadratically with the number of detected objects, and frame-by-frame processing causes the system to immediately forget objects the moment they become occluded. We propose Enhanced HOPE, an adaptive perception architecture that measures the geometric complexity of each incoming LiDAR frame using an unsupervised statistical estimator and routes it through a shallow or deep processing path accordingly, requiring no manual scene labels. To keep interaction modeling efficient, we replace quadratic pairwise attention with a linear-time subspace-based network that groups nearby objects into clusters and processes them jointly. The computational savings from these two mechanisms free up resources for a persistent temporal memory module that retains previously detected objects and traffic rules across frames, enabling the system to recall occluded objects seconds after they disappear from view. On the nuScenes and CARLA benchmarks, Enhanced HOPE reduces latency by 38% on simple scenes with no accuracy loss, improves mean Average Precision by 2.7 points on rare long-tail scenarios, and tracks objects through occlusions lasting over 5 seconds, where all tested baselines fail.
Authors: Manyu Li, Ruian He, Chenxi Ma, Weimin Tan, Bo Yan
Abstract: Multimodal large language models (MLLMs) show remarkable potential for scientific reasoning, yet their performance in specialized domains such as microscopy remains limited by the scarcity of domain-specific training data and the difficulty of encoding fine-grained expert knowledge into model parameters. To bridge the gap, we introduce MicroWorld, a framework that constructs a multimodal attributed property graph (MAPG) from large-scale scientific image--caption corpora and leverages it to augment MLLM reasoning at inference time without any domain-specific fine-tuning. MicroWorld extracts biomedical entities and relations via scispaCy or LLM-based triplet mining, aligns images and entities in a shared embedding space using Qwen3-VL-Embedding, and assembles a knowledge graph comprising approximately 111K nodes and 346K typed edges spanning eight relation categories. At inference time, a graph-augmented retrieval pipeline matches query entities to the MAPG and injects structured knowledge context into the MLLM prompt. On the MicroVQA benchmark, MicroWorld improves the reasoning performance of Qwen3-VL-8B-Instruct by 37.5%, outperforming GPT-5 by 13.0% to achieve a new state-of-the-art. Furthermore, it yields a 6.0% performance gain on the MicroBench benchmark. Extensive experiments demonstrate the enhanced generalization capability introduced by MicroWorld. A qualitative case study further reveals both the mechanisms through which structured knowledge improves reasoning and the failure modes that point to promising future directions. Code and data are available at https://github.com/ieellee/MicroWorld.
Authors: Yu He, Ting Zhu, Yichun Liu, Lichen Ma, Xinyuan Shan, Jingling Fu, Yu Shi, Junshi Huang, Yan Li
Abstract: Recent research work on fashion outfit generation focuses on promoting visual consistency of garments by leveraging key information from reference image and text prompt. However, the potential of outfit generation remains underexplored, requiring comprehensive e-commercial dataset and elaborative utilization of multi-modal condition. In this paper, we propose a brand-new e-commerce dataset, named Fashion130k, with various occasions, models, and garment types. For the consistent generation of garment, we design a framework with Unified Multi-modal Condition (UMC) to align and integrate the text and visual prompts into generation model. Specifically, we explore an embedding refiner to extract the unified embeddings of multi-modal prompts, within which a Fusion Transformer is proposed to align the multi-modal embeddings by adjusting the modality gap between text and image. Based on unified embeddings, the attention in generation model is redesigned to emphasis the correlations between prompts and noise image, inducing that the noise image can select the pivotal tokens of prompts for consistent outfit generation. Our dataset and proposed framework offer a general and nuanced exploration of multi-modal prompts for generation models. Extensive experiments on real-world applications and benchmark demonstrate the effectiveness of UMC in visual consistency, achieving promising result than that of SoTA methods.
Authors: Yasiru Ranasinghe, Elim Schenck, Florence Yellin, Shuowen Hu, Christopher Funk, Vishal M. Patel
Abstract: Existing open-vocabulary detectors focus on RGB images and fail to generalize to thermal imagery, where low texture and emissivity variations challenge RGB-based semantics. We present Thermal-Det, the first large language model (LLM) supervised open-vocabulary detector tailored for thermal images. To enable large-scale training, we develop a synthetic dataset by converting GroundingCap-1M into the thermal domain and filtering captions to remove RGB-specific terms, yielding over one million thermally aligned samples with bounding boxes, grounding texts, and detailed captions. Thermal-Det jointly optimizes detection, captioning, and cross-modal distillation objectives. A frozen RGB teacher provides geometric and semantic pseudo-supervision for paired but unlabeled RGB-thermal data, transferring open-vocabulary knowledge without manual annotation. The model further employs a Thermal-Text Alignment Head for text calibration and a Modality-Fused Cross-Attention module for dual-modality reasoning. Unlike prior domain-adaptation methods, the detector is fully fine-tuned to internalize thermal contrast patterns while preserving language alignment. Experiments on public benchmarks show consistent 2-4% AP gains over existing open-vocabulary detectors, establishing a strong foundation for scalable, language-driven thermal perception.
Authors: Mateusz Cedro, Marcin Chlebus
Abstract: Artificial intelligence models are increasingly scaled to improve predictive accuracy, yet it remains unclear whether scale improves the quality of post-hoc explanations. We investigate this relationship by evaluating 11 computer vision models representing increasing levels of depth and complexity within the ResNet, DenseNet, and Vision Transformer families, trained from scratch or pretrained, across three image datasets with ground-truth segmentation masks. For each model, we generate explanations using five post-hoc explainable AI methods and quantify mask alignment using two localisation metrics: Relevance Rank Accuracy (Arras et al., 2022) and the proposed Dual-Polarity Precision, which measures positive attributions inside the class mask and negative attributions outside it. Across datasets and methods, increasing architectural depth and parameter count does not improve explanation quality in most statistical comparisons, and smaller models often match or exceed deeper variants. While pretraining typically improves predictive performance and increases the dependence of explanations on learned weights, it does not consistently increase localisation scores. We also observe scenarios in which models achieve strong predictive performance while localisation precision is near zero, suggesting that performance metrics alone may not indicate whether predictions are based on the annotated regions. These results indicate that larger models do not reliably provide higher-quality explanations, and that explainability should therefore be assessed explicitly during model selection for safety-sensitive deployments.
Authors: Novendra Setyawan, Chi-Chia Sun, Mao-Hsiu Hsu, Wen-Kai Kuo, Jun-Wei Hsieh
Abstract: The Vision Transformer (ViT) achieves remarkable accuracy across visual tasks but remains computationally expensive for edge deployment. This paper presents MicroViTv2, a lightweight Vision Transformer optimized for real-device efficiency. Built upon the original MicroViT, the proposed model is designed based on reparameterized design, specifically Reparameterized Patch Embedding (RepEmbed) and Reparameterized Depth-Wise convolution mixer (RepDW) for faster inference, and introduces the Single Depth-Wise Transposed Attention (SDTA) to capture long-range dependencies with minimal redundancy. Despite slightly higher FLOPs, MicroViTv2 improves accuracy up to 0.5% compared to its predecessor and surpassing MobileViTv2, EdgeNeXt, and EfficientViT while maintaining fast inference and high energy efficiency on Jetson AGX Orin. Experiments on ImageNet-1K and COCO demonstrate that hardware-aware design and structural re-parameterization are key to achieving high accuracy and low energy consumption, validating the need to evaluate efficiency beyond FLOPs. Code is available at https://github.com/novendrastywn/MicroViT.
Authors: Yeo Keat Ee, Debaditya Roy, Chen Li, Hao Zhang, Basura Fernando
Abstract: Temporal action segmentation (TAS) divides untrimmed videos into labeled action segments. While fully supervised methods have advanced the field, challenges such as action variability, ambiguous boundaries, and high annotation costs remain, especially in new or low-resource domains. Grammar-based approaches improve segmentation with structural priors but rely on complex parsing limiting scalability. In this work, we propose a lightweight, constraint-based refinement framework that enhances TAS predictions by integrating statistical structural priors such as transition confidence, action boundary sets, and per-class duration, that can be directly extracted from annotated data. These constraints are integrated into a modified Viterbi decoding algorithm, allowing inference-time refinement without retraining or added model complexity. Our approach improves both fully and semi-supervised TAS models by correcting structural prediction errors while maintaining high efficiency. Code is available at https://github.com/LUNAProject22/CAD
Authors: Aaditya Baranwal, Akshaj Gupta, Shruti Vyas, Yogesh S Rawat
Abstract: Every molecule ever synthesised can be drawn as a 2D skeletal diagram, yet in modern property prediction this universally available representation has received less focus in favour of molecular graphs, 3D conformers, or billion-parameter language models, each imposing its own computational and data-engineering overhead. We present $\textbf{MolSight}$, the first systematic large-scale study of vision-based Molecular Property Prediction (MPP). Using 10 vision architectures, 7 pre-training strategies, and $2\,M$ molecule images, we evaluate performance across 10 downstream tasks spanning physical-property regression, drug-discovery classification, and quantum-chemistry prediction. To account for the wide variation in structural complexity across pre-training molecules, we further propose a $\textbf{chemistry-informed curriculum}$: five structural complexity descriptors partition the corpus into five tiers of increasing chemical difficulty, consistently outperforming non-curriculum baselines. We show that a single rendered bond-line image, processed by a vision encoder, is sufficient for competitive molecular property prediction, i.e. $\textit{chemical insight from sight alone}$. The best curriculum-trained configuration achieves the top result on $\textbf{5 of 10}$ benchmarks and top two on $\textbf{all 10}$, at $\textbf{$\textit{80$\times$ lower}$}$ FLOPs than the nearest multi-modal competitor.
Authors: Yu Lin, Jianghang Lin, Kai Ye, Shengchuan Zhang, Liujuan Cao
Abstract: Reducing the annotation cost of oriented object detection in remote sensing remains a major challenge. Recently, sparse annotation has gained attention for effectively reducing annotation redundancy in densely remote sensing scenes. However, (1) the sparse data reliance on class-dependent sampling, and (2) the lack of in-depth investigation into the characteristics of sparse samples hinders its further development. This paper proposes an active learning-based sparsely annotated oriented object detection (SAOOD) method, termed Active-SAOOD. Based on a model state observation module, Active-SAOOD actively selects the most valuable sparse samples at the instance level that are best suited to the current model state, by jointly considering orientation, classification, and localization uncertainty, as well as inter- and intra-class diversity. This design enables SAOOD to operate stably under completely randomly initialized sparse annotations and extends its applicability to broader real-world. Experiments on multiple datasets demonstrate that Active-SAOOD significantly improves both performance and stability of existing SAOOD methods under various random sparse annotation. In particular, with only 1\% annotated ratios, it achieves a 9\% performance gain over the baseline, further enhancing the practical value of SAOOD in remote sensing. The code will be public.
Authors: Inhyuk Park, Doohyun Park
Abstract: Noisy labels are common in large-scale medical imaging datasets due to inter-observer variability and ambiguous cases. We propose a statistically grounded and task-agnostic framework, Standardized Loss Aggregation (SLA), for detecting noisy labels at the sample level. SLA quantifies label reliability by aggregating standardized fold-level validation losses across repeated cross-validation runs. This formulation generalizes discrete hard-counting schemes into a continuous estimator that captures both the frequency and magnitude of performance deviations, yielding interpretable and statistically stable noisiness scores. Experiments on a public fundus dataset demonstrate that SLA consistently outperforms the hard-counting baseline across all noise levels and converges substantially faster, especially under low noise ratios where subtle loss variations are informative. Samples with high SLA scores indicate potentially ambiguous or mislabeled cases, guiding efficient re-annotation and improving dataset reliability for any classification task.
Authors: Zhiwei Ning, Xuanang Gao, Jiaxi Cao, Gengming Zhang, Shengnan Ma, Wenwen Tong, Hanming Deng, Jie Yang, Wei Liu
Abstract: Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a persistent challenge. Although recent agentic approaches incorporate tool use, they often neglect critical execution feedback. Consequently, they suffer from the imagination-action-observer (IAO) bias, a misalignment between prior imagination and observer feedback that undermines reasoning stability and optimality. To bridge this gap, we introduce V-ABS, an action-observer driven beam search framework that enables deliberate reasoning through thinker-actor-observer iterations. We also propose an entropy-based adaptive weighting algorithm to mitigate the IAO bias by dynamically balancing the confidence scores between the policy priors and the observational feedback. Moreover, we construct a large-scale supervised fine-tuning (SFT) dataset comprising over 80k samples to guide the model to assign higher prior confidence to correct action paths. Extensive experiments across eight diverse benchmarks show that V-ABS achieves state-of-the-art performance, delivering an average improvement of 19.7% on the Qwen3-VL-8B baseline and consistent gains across both open-source and proprietary models.
Authors: Markus Brezovsky, Anatol G\"unthner, Frederik Schulte, Lukas Winiwarter, Boris Jutzi, Gottfried Mandlburger
Abstract: Through-water photogrammetry based on UAV imagery enables shallow-water bathymetry, but refraction at the air-water interface violates the straight-ray assumption of Structure-from-Motion and causes systematic depth bias. We present BathyFacto, a refraction-aware two-media extension of Nerfacto integrated into Nerfstudio that targets metrically precise underwater point clouds. BathyFacto uses a shared hash-grid-based density field with a medium-conditioned color head that receives a one-bit medium flag (air or water) and traces each camera ray as two segments: a straight segment in air up to a planar water surface and a refracted segment in water computed via Snell's law with known refractive indices. To allocate samples efficiently across the air-water boundary, we employ a single proposal-network sampler that operates on a virtual straight ray spanning both media, combined with a kinked density wrapper that transparently corrects water-segment positions along the refracted direction before density evaluation. A data adaptation pipeline converts photogrammetric reconstructions to a Nerfstudio-compatible format, estimates the water plane from boundary markers, and provides per-pixel medium masks to gate refraction. We also extend the point cloud export with refraction-corrected backprojection and reversible coordinate transforms to world and global frames. On a simulated two-media scene with known ground truth, BathyFacto with refraction achieves a Cloud-to-Mesh mean distance of 0.06 m and 87 % completeness, compared to 0.52 m / 29 % for the Nerfacto baseline and 0.36 m / 21% for conventional MVS without refraction correction.
Authors: Guangli Chen, Dianzhao Li, Wenjian Zhong, Bangquan Xie, Ostap Okhrin
Abstract: Robust urban autonomous driving requires reliable 3D scene understanding and stable decision-making under dense interactions. However, existing end-to-end models lack interpretability, while modular pipelines suffer from error propagation across brittle interfaces. This paper proposes MTA-RL, the first framework that bridges perception and control through Multi-modal Transformer-based 3D Affordances and Reinforcement Learning (RL). Unlike previous fusion models that directly regress actions, RGB images and LiDAR point clouds are fused using a transformer architecture to predict explicit, geometry-aware affordance representations. These structured representations serve as a compact observation space, enabling the RL policy to operate purely on predicted driving semantics, which significantly improves sample efficiency and stability. Extensive evaluations in CARLA Town01-03 across varying densities (20-60 background vehicles) show that MTA-RL consistently outperforms state-of-the-art baselines. Trained solely on Town03, our method demonstrates superior zero-shot generalization in unseen towns, achieving up to a 9.0% increase in Route Completion, an 11.0% increase in Total Distance, and an 83.7% improvement in Distance Per Violation. Furthermore, ablation studies confirm that our multi-modal fusion and reward shaping are critical, significantly outperforming image-only and unshaped variants, demonstrating the effectiveness of MTA-RL for robust urban autonomous driving.
Authors: Chenyu Zhang, Lanjun Wang, Yueyang Cheng, Ruidong Chen, Wenhui Li, An-an Liu
Abstract: The rise of text-to-image (T2I) models has increasingly raised concerns regarding the generation of risky content, such as sexual, violent, and copyright-protected images, highlighting the need for effective safeguards within the models themselves. Although existing methods have been proposed to eliminate risky concepts from T2I models, they are primarily developed for earlier U-Net architectures, leaving the state-of-the-art Diffusion-Transformer-based T2I models inadequately protected. This gap stems from a fundamental architectural shift: Diffusion Transformers (DiTs) entangle semantic injection and visual synthesis via joint attention, which makes it difficult to isolate and erase risky content within the generation. To bridge this gap, we investigate how semantic concepts are represented in DiTs and discover that attention heads exhibit concept-specific sensitivity. This property enables both the detection and suppression of risky content. Building on this discovery, we propose AHV-D\&S, a training-free inference-time safeguard for image generation in DiTs. Specifically, AHV-D\&S quantifies each textual token's sensitivity across all attention heads as an Attention Head Vector (AHV), which serves as a discriminative signature for detecting risky generation tendencies. In the inference stage, we propose a momentum-based strategy to dynamically track token-wise AHVs across denoising steps, and a sensitivity-guided adaptive suppression strategy that suppresses the attention weights of identified risky tokens based on head-specific risk scores. Extensive experiments demonstrate that AHV-D\&S effectively suppresses sexual, copyrighted-style, and various harmful content while preserving visual quality, and further exhibits strong robustness against adversarial prompts and transferability across different DiT-based T2I models.
Authors: Jihyeon Baek, Seunghoon Lee, Gitaek Kwon, Doohyun Park
Abstract: Out-of-distribution (OOD) detection is essential for building reliable AI systems, as models that produce outputs for invalid inputs cannot be trusted. Although deep learning (DL) is often assumed to outperform traditional machine learning (ML), medical imaging data are typically acquired under standardized protocols, leading to relatively constrained image variability in OOD detection tasks. This motivates a direct comparison between ML and DL approaches in this setting. The two approaches are evaluated on open datasets comprising over 60,000 fundus and non-fundus images across multiple resolutions. Both approaches achieved an AUROC of 1.000 and accuracies between 0.999 and 1.000 on internal and external validation sets, showing comparable detection performance. The ML approach, however, exhibited substantially lower end-to-end latency while maintaining equivalent accuracy, indicating greater computational efficiency. These results suggest that for OOD detection tasks of limited visual complexity, lightweight ML approaches can achieve DL-level performance with significantly reduced computational cost, supporting practical real-world deployment.
Authors: Paul Vermeeren, Heysem Kaya
Abstract: We develop a foundation model using 1.2m high resolution satellite images of the Netherlands. By combining a Convolutional Neural Network and a Vision Transformer, the model captures both low- and high-frequency landscape features, such as fine textures, edges, and small objects as well as large terrain structures, elevation patterns, and land-cover distributions. Leveraging temporal data as input, the model learns from broader contextual information across time, allowing the model to exploit the temporal dependencies, such as topographic features, land-cover changes, and seasonal dynamics. These additional constraints reduce feature ambiguity, improve representation learning, and enable better generalization with fewer labeled samples. The foundation model is evaluated on multiple downstream tasks, ranging from use cases within the Netherlands to global benchmarking datasets. On the vegetation monitoring dataset of the Netherlands, the model shows clear performance improvements by incorporating temporal information instead of relying on a single time point. Despite using a smaller model and less pretraining data limited to the Netherlands, it achieves competitive results on global benchmarks when compared to state-of-the-art models. These results demonstrate that the model can learn rich, generalizable representations from limited data, achieving competitive performance on global benchmarks while using a fraction of the parameters of larger state-of-the-art remote sensing models. To maximize reproducibility and reuse, we made the scripts and the model accessible on GitHub.
Authors: Vittorio Palladino, Ahmet Enis Cetin
Abstract: Ghost imaging reconstructs spatial information from a single-pixel bucket detector by correlating structured illumination patterns with scalar intensity measurements. While deep learning approaches have achieved promising results on static scenes, two critical limitations remain unaddressed: existing architectures fail to exploit temporal coherence across frames, leaving dynamic ghost imaging largely unsolved, and they assume additive Gaussian noise models that do not reflect the true Poissonian statistics of real single-photon hardware. We present DynGhost (Dynamic Ghost Imaging Transformer), a transformer architecture that addresses both limitations through alternating spatial and temporal attention blocks. Our quantum-aware training framework, based on physically accurate detector simulations (SNSPDs, SPADs, SiPMs) and Anscombe variance-stabilizing normalization, resolves the distribution shift that causes classical models to fail under realistic hardware constraints. Experiments across multiple benchmarks demonstrate that DynGhost outperforms both traditional reconstruction methods and existing deep learning architectures, with particular gains in dynamic and photon-starved settings.
Authors: Longteng Guo (Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences), Xuanxu Lin (Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences), Dongze Hao (OPPO AI Center), Tongtian Yue (Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences), Pengkang Huo (Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences), Jiatong Ma (Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences), Yuchen Liu (Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences), Jing Liu (Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences)
Abstract: Scientific reasoning is a key aspect of human intelligence, requiring the integration of multimodal inputs, domain expertise, and multi-step inference across various subjects. Existing benchmarks for multimodal large language models (MLLMs) often fail to capture the complexity and traceability of reasoning processes necessary for rigorous evaluation. To fill this gap, we introduce SciVQR, a multimodal benchmark covering 54 subfields in mathematics, physics, chemistry, geography, astronomy, and biology. SciVQR includes domain-specific visuals, such as equations, charts, and diagrams, and challenges models to combine visual comprehension with reasoning. The tasks range from basic factual recall to complex, multi-step inferences, with 46% including expert-authored solutions. SciVQR not only evaluates final answers but also examines the reasoning process, providing insights into how models reach their conclusions. Our evaluation of leading MLLMs, including both proprietary and open-source models, reveals significant limitations in handling complex multimodal reasoning tasks, underscoring the need for improved multi-step reasoning and better integration of interdisciplinary knowledge in advancing MLLMs toward true scientific intelligence. The dataset and evaluation code are publicly available at https://github.com/CASIA-IVA-Lab/SciVQR.
Authors: Soichiro Okazaki, Tatsuya Sasaki, Hiroki Ohashi
Abstract: Open-vocabulary object detection (OVOD) aims to detect both seen and unseen categories, yet existing methods often struggle to generalize to novel objects due to limited integration of global and local contextual cues. We propose DetRefiner, a simple yet effective plug-and-play framework that learns to fuse global and local features to refine open-vocabulary detection. DetRefiner processes global image features and patch-level image features from foundational models (e.g., DINOv3) through a lightweight Transformer encoder. The encoder produces a class vector capturing image-level attributes and patch vectors representing local region attributes, from which attribute reliability is inferred to recalibrate the base model's confidence. Notably, DetRefiner is trained independently of the base OVOD model, requiring neither access to its internal features nor retraining. At inference, it operates solely on the base detector's predictions, producing auxiliary calibration scores that are merged with the base detector's scores to yield the final refined confidence. Despite this simplicity, DetRefiner consistently enhances multiple OVOD models across COCO, LVIS, ODinW13, and Pascal VOC, achieving gains of up to +10.1 AP on novel categories. These results highlight that learning to fuse global and local representations offers a powerful and general mechanism for advancing open-world object detection. Our codes and models are available at https://github.com/hitachi-rd-cv/detrefiner.
Authors: Zhicheng Liang, Haoyi Yu, Boyan Li, Dayou Zhang, Zijian Cao, Tianyi Gong, Junhua Liu, Shuguang Cui, Fangxin Wang
Abstract: Accurate 3D reconstruction of objects with reflective, transparent, or low-texture surfaces still remains notoriously challenging. Such materials often violate key assumptions in multi-view reconstruction pipelines, such as photometric consistency and the availability on distinct geometric texture cues. Existing datasets primarily focus on diffuse, textured objects, and therefore provide limited insight into performance under real-world material complexities. We introduce 3DReflecNet, a large-scale hybrid dataset exceeding 22 TB that is specifically designed to benchmark and advance 3D vision methods for these challenging materials. 3DReflecNet combines two types of data: over 120,000 synthetic instances generated via physically-based rendering of more than 12,000 shapes, and over 1,000 real-world objects captured using consumer devices. Together, these data consist of more than 7 million multi-view frames. The dataset spans diverse materials, complex lighting conditions, and a wide range of geometric forms, including shapes generated from both real and LLM-synthesized 2D images using diffusion-based pipelines. To support robust evaluation, we design benchmarks for five core tasks: image matching, structure-from-motion, novel view synthesis, reflection removal, and relighting. Extensive experiments demonstrate that state-of-the-art methods struggle to maintain accuracy across these settings, highlighting the need for more resilient 3D vision models.
Authors: Xiaobin Hu, Enpu Zuo, Lanping Hu, Kaiwen Yang, Dianshu Liao, Tianyi Zhang, Bo Yin, Yinsi Zhou, Shidong Pan, Xiaoyu Sun
Abstract: Privacy protection has become a critical requirement in the era of ubiquitous visual data sharing, imposing higher demands on efficient and robust privacy detection algorithms. However, current robust detection models are severely hindered by the lack of comprehensive datasets. Existing privacy-oriented datasets often suffer from limited scale, coarse-grained annotations, and narrow domain coverage, failing to capture the intricate details of sensitive information in realworld environments. To bridge this gap, we present a large-scale, fine-grained Visual Privacy Dataset (VPD-100K), designed to facilitate generalized privacy detection. We establish a holistic taxonomy comprising four primary domains: Human Presence, On-Screen Personally Identifiable Information (PII), Physical Identifiers, and Location Indicators, containing 100,000 images annotated with 33 fine-grained classes and over 190,000 object instances. Statistical analysis reveals that our dataset features long-tailed distributions, small object scales, and high visual complexity. These characteristics make the dataset particularly valuable for demanding, unconstrained applications such as live streaming, where actors frequently face unintentional, realtime information leakage. Furthermore, we design an effective frequency-enhanced lightweight module consisting of frequency-domain attention fusion and adaptive spectral gating mechanism that breaks the limitations of spatial pixel intensity to better capture the subtle details of sensitive information. Extensive experiments conducted on both diverse image and streaming videos benchmarks consistently demonstrate the effectiveness of our VPD-100K dataset and the wellcurated frequency mechanism. The code and dataset are available at https://vpd-100k.github.io/.
Authors: Mingwei Xing, Xinliang Wang, Yifeng Shi
Abstract: This work explores a simple yet powerful lightweight adapter design for feed-forward 3D Gaussian Splatting (3DGS). Existing methods typically apply complex, architecture-specific designs on top of the generic pipeline of image feature extraction $\rightarrow$ multi-view interaction $\rightarrow$ feature decoding. However, constrained by the scale bottleneck of 3D training data and the low-pass filtering effect of deep networks, these methods still fall short in cross-domain generalization and high-frequency geometric fidelity. To address these problems, we propose AdaptSplat, which demonstrates that without complex component engineering, introducing a single adapter of only 1.5M parameters into the generic architecture is sufficient to achieve superior performance. Specifically, we design a lightweight Frequency-Preserving Adapter (FPA) that extracts direction-aware high-frequency structural priors from the shallow features of a powerful vision foundation model backbone, and seamlessly integrates them into the generic pipeline via high-frequency positional encodings and adaptive residual modulation. This effectively compensates for the high-frequency attenuation caused by over-smoothing in deep features, improving the fitting accuracy of Gaussian primitives on complex surfaces and sharp boundaries. Extensive experiments demonstrate that AdaptSplat achieves state-of-the-art feed-forward reconstruction performance on multiple standard benchmarks, with stable generalization across domains. Code available at: https://github.com/xmw666/AdaptSplat.
Authors: Ishan Narayan
Abstract: We present GraphDepth, a monocular depth estimation architecture that synergistically integrates Graph Neural Networks (GNNs) within a convolutional encoder-decoder framework. Our approach embeds efficient GraphSAGE layers at multiple scales of a ResNet-101 U-Net backbone, enabling explicit modeling of long-range spatial relationships that lie beyond the receptive field of local convolutions. Key technical contributions include: (1) batch-parallelized graph construction with configurable k-NN and grid-based adjacency for scalable training; (2) multi-scale GraphSAGE integration at bottleneck and decoder stages (1/32, 1/16, 1/8 resolution) to propagate global context throughout the feature hierarchy; (3) channel-attention gated skip connections that adaptively weight encoder features before fusion; and (4) heteroscedastic uncertainty estimation via a dedicated aleatoric uncertainty head, enabling confidence-aware loss weighting during optimization. Unlike transformer-based hybrids, which suffer from quadratic complexity in sequence length, GraphDepth scales linearly with spatial resolution while achieving comparable global receptive fields through iterative message passing. Experiments on NYU Depth V2, WHU Aerial, ETH3D, and Mid-Air benchmarks demonstrate competitive accuracy within 4.6\% of state-of-the-art transformers on indoor scenes with substantially lower computational cost (25 FPS vs 9 FPS, 3.8 GB vs 8.8 GB VRAM). GraphDepth achieves the best reported result on WHU Aerial (RMSE 8.24 m) and exhibits superior zero-shot cross-domain transfer to the Mid-Air synthetic aerial dataset, validating the generalization power of explicit relational reasoning for depth estimation.
Authors: Tinsae Yehuala, Hao Cheng, Ville Lehtola
Abstract: Maritime object detection is critical for the safe navigation of unmanned surface vessels (USVs), requiring accurate recognition of obstacles from small buoys to large vessels. Real-time detection is challenging due to long distances, small object sizes, large-scale variations, edge computing limitations, and the high memory demands of high-resolution imagery. Existing solutions, such as downsampling or image splitting, often reduce accuracy or require additional processing, while memory-efficient models typically handle only limited resolutions. To overcome these limitations, we leverage Vision Mamba (ViM) backbones, which build on State Space Models (SSMs) to capture long-range dependencies while scaling linearly with sequence length. Images are tokenized into sequences for efficient high-resolution processing. For further computational efficiency, we design a tailored Feature Pyramid Network with successive downsampling and SSM layers, as well as token pruning to reduce unnecessary computation on background regions. Compared to state-of-the-art methods like RT-DETR with ResNet50 backbone, our approach achieves a better balance between performance and computational efficiency in maritime object detection.
Authors: Chenggong Li, Yidong Luo, Junchao Zhang, Boxin Shi, Degui Yang
Abstract: Polarimetric imaging captures surface polarization characteristics, such as the Degree of Linear Polarization (DoLP) and the Angle of Polarization (AoP). In mainstream Division of-Focal-Plane (DoFP) color polarization imaging, recovering polarization parameters from captured mosaic arrays remains a challenging inverse problem. Existing DoFP cameras also face hardware bottlenecks and often cannot support high-frame-rate acquisition, limiting polarimetric imaging in dynamic video tasks. These limitations motivate joint spatial and temporal enhancement. To this end, we propose the first space-time polarization video reconstruction architecture. The method jointly models polarization directions in space and time and uses a polarization-aware implicit neural representation for continuous, high-fidelity upsampling. By analyzing temporal variations in polarization parameters, we further introduce a flow-guided polarization variation loss to supervise polarization dynamics. We also establish the first large-scale color DoFP polarization video benchmark to support this research direction. Extensive experiments on this benchmark demonstrate the effectiveness of the method.
Authors: Yinan Deng, Jianyu Dou, Jiahui Wang, Jingyu Zhao, Yi Yang, Yufeng Yue
Abstract: Dynamic scene reconstruction represents a fundamental yet demanding challenge in computer vision and robotics. While recent progress in 3DGS-based methods has advanced dynamic scene modeling, obtaining high-fidelity rendering and accurate tracking in scenarios with substantial, intricate motions remains significantly challenging. To address these challenges, we propose PaMoSplat, a novel dynamic Gaussian splatting framework incorporating part awareness and motion priors. Our approach is grounded in two key observations: 1) Parts serve as primitives for scene deformation, and 2) Motion cues from optical flow can effectively guide part motion. Specifically, PaMoSplat initializes by lifting multi-view segmentation masks into 3D space via graph clustering, establishing coherent Gaussian parts. For subsequent timestamps, we leverage a differential evolutionary algorithm to estimate the rigid motion of these parts using multi-view optical flow cues, providing a robust warm-start for further optimization. Additionally, PaMoSplat introduces an adaptive iteration count mechanism, internal learnable rigidity, and flow-supervised rendering loss to accelerate and optimize the training process. Comprehensive evaluations across diverse scenes, including real-world environments, demonstrate that PaMoSplat delivers superior rendering quality, improved tracking precision, and faster convergence compared to existing methods. Furthermore, it enables multiple part-level downstream applications, such as 4D scene editing.
Authors: Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser, Ko Watanabe, Riku Takahashi, Issey Sukeda, Andreas Dengel
Abstract: Layered image assets are widely used in real-world creative workflows, enabling non-destructive iteration and flexible re-composition. Recent advances in layered image generation and decomposition synthesize or recover layered representations, yet controllable editing of layered images remains challenging. Manual editing requires careful coordination across layers to maintain consistent illumination and contact, while AI-based pipelines collapse layers into a flattened image for editing, then decompose them again, introducing background-to-foreground leakage and unstable transparency. To address these limitations, we propose LimeCross, a training-free context-conditioned layered image editing framework that edits user-selected RGBA layers according to text while keeping the remaining layers unchanged. It leverages contextual cues from other layers using a bi-stream attention mechanism to preserve cross-layer consistency, while explicitly maintaining layer integrity to prevent the contamination of edited layers. To evaluate our approach, we introduce LayerEditBench, a benchmark of 1500 layered scenes with paired source/target prompts, along with evaluation protocols that assess both edit fidelity and alpha channel stability. Extensive experiments demonstrate that LimeCross improves layer purity and composite realism over strong editing baselines, establishing context-conditioned layered editing as a principled framework for controllable generative creation.
Authors: Andrii Yermakov, Jan Cech, Mario Fritz, Jiri Matas
Abstract: Recent deepfake detection methods demonstrate improved cross-dataset generalization, yet the underlying mechanisms remain underexplored. We introduce the Alpha Blending Hypothesis, positing that state-of-the-art frame-based detectors primarily function as alpha blending searchers; rather than learning semantic anomalies or specific generative neural fingerprints, they localize low-level compositing artifacts introduced during the integration of manipulated faces into target frames. We experimentally validate the hypothesis, demonstrating that deepfake detectors exhibit high sensitivity to the so-called self-blended images (SBI) and non-generative manipulations. We propose the method BlenD that leverages a large-scale, diverse dataset of real-only facial images augmented with SBI. This approach achieves the best average cross-dataset generalization on 15 compositional deepfake datasets released between 2019 and 2025 without utilizing explicitly generated deepfakes during training. Furthermore, we show that predictions from explicit blending searchers and models resilient to blending shortcuts are highly complementary, yielding a state-of-the-art AUROC of 94.0% in an ensemble configuration. The code with experiments and the trained model will be publicly released.
Authors: Zichen Wen, Boxue Yang, Junlong Ke, Jiajie Huang, Chenfei Liao, Junxi Wang, Xuyang Liu, Linfeng Zhang
Abstract: Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness against verbosity. Yet most video-language models (VideoLLMs) are trained for offline inference, and existing streaming benchmarks externalize this timing decision to the evaluator. We address this gap with RealStreamEval, a frame-level multi-turn evaluation protocol that exposes models to sequential observations and penalizes unnecessary responses. Under this protocol, we observed that strong offline VideoLLMs retain useful visual understanding but lack an interaction policy for deciding when to respond. Motivated by this observation, we propose EvoStreaming, a self-evolved streaming adaptation framework in which the base model itself acts as data generator, relevance annotator, and roll-out policy to synthesize streaming trajectories without external supervision. With only $1{,}000$ self-generated samples ($139\times$ less than the leading streaming instruction-tuning approach) and no architectural changes, EvoStreaming consistently improves the overall RealStreamEval score by up to $10.8$ points across five open VideoLLM backbones (Qwen2/2.5/3-VL, InternVL-3.5, MiniCPM-V4.5) while largely preserving offline video performance. These results suggest that data-efficient interaction tuning is a practical path for adapting existing VideoLLMs to streaming assistants.
Authors: Wei Wang, Dou Quan, Ning Huyan, Shuang Wang, Yi Li, Pei He, Licheng Jiao
Abstract: Geometric differences between cross-view images, such as drone and satellite views, significantly increase the challenge of Cross-View Geo-Localization (CVGL), which aims to acquire the geolocation of images by image retrieval. To further enhance the CVGL performance, this paper proposes a parameter-efficient adaptation framework for bridging the geometric gap across images based on the vision foundation model (VFM) (e.g., DINOv3), termed BGG. BGG not only effectively leverages the general visual representations of VFM and captures the robust and consistent features from cross-view images, but also utilizes the generalization capabilities of the VFM, significantly improving the CVGL performance. It mainly contains a Multi-granularity Feature Enhancement Adapter (MFEA) and a Frequency-Aware Structural Aggregation (FASA) module. Specifically, MFEA enhances the scale adaptability and viewpoint robustness of features by multi-level dilated convolutions, effectively bridging the cross-view geometric gap with small training costs. Additionally, considering the [CLS] token lacks spatial details for precise image retrieval and localization, the FASA module modulates patch tokens in the frequency domain and performs adaptive aggregation for local structural feature enhancement. Finally, BGG fuses the enhanced local features with the [CLS] token for more accurate CVGL. Extensive experiments on University-1652 and SUES-200 datasets demonstrate that BGG has significant advantages over other methods and achieves state-of-the-art localization performance with low training costs.
Authors: Rashi Sharma, Justin Timothy C. Bersamin, Karthikk Subramanian
Abstract: Annotating bounding boxes is costly and limits the scalability of object detection. This challenge is compounded by the need to preserve high accuracy while minimizing manual effort in real-world applications. Prior active learning methods often depend on model features or modify detector internals and training schedules, increasing integration overhead. Moreover, they rarely jointly exploit the benefits of image-level signals, class-imbalance cues, and instance-level uncertainty for comprehensive selection. We present Portable Active Learning (PAL), a detector-agnostic, easily portable framework that operates solely on inference outputs. PAL combines class-wise instance uncertainty with image-level diversity to guide data selection. At each round, PAL trains lightweight class-specific logistic classifiers to distinguish true from false positives, producing entropy-based uncertainty scores for proposals. Candidate images are then refined using global image entropy, class diversity, and image similarity, yielding batches that are both informative and diverse. PAL requires no changes to model internals or training pipelines, ensuring broad compatibility across detectors. Extensive experiments on COCO, PASCAL VOC, and BDD100K demonstrate that PAL consistently improves label efficiency and detection accuracy compared to existing active learning baselines, making it a practical solution for scalable and cost-effective deployment of object detection in real-world settings.
Authors: Minje Kim, Younghyun Noh, Jaesoon Kim, Tae-Kyun Kim
Abstract: While novel view synthesis (NVS) for dynamic scenes has seen significant progress, reconstructing temporally consistent geometric surfaces remains a challenge. Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) offer powerful dynamic scene rendering capabilities; however, relying solely on photometric optimization often leads to geometric ambiguities. This results in discontinuous surfaces, severe artifacts, and broken surfaces over time. To address these limitations, we present DySurface, a novel framework that bridges the effectiveness of explicit Gaussians with the geometric fidelity of implicit Signed Distance Functions (SDFs) in dynamic scenes. Our approach tackles the structural discrepancy between the forward deformation of 3DGS ($canonical \rightarrow dynamic$) and the backward deformation required for volumetric SDF rendering ($dynamic \rightarrow canonical$). Specifically, we propose the VoxGS-DSDF branch that leverages deformed Gaussians to construct a dynamic sparse voxel grid, providing explicit geometric guidance to the implicit SDF field. This explicit anchoring effectively regularizes the volumetric rendering process, significantly improving surface reconstruction quality, with watertight boundaries and detailed representations. Quantitative and qualitative experiments demonstrate that DySurface significantly outperforms state-of-the-art baselines in geometric accuracy metrics while maintaining competitive rendering performance.
Authors: Alexey Pchelnikov, Aleksei Pchelnikov
Abstract: Training AI models for computational pathology currently requires access to expensive whole-slide-image datasets, GPU infrastructure, deep expertise in machine learning, and substantial engineering effort. We present CellDX AI Autopilot, a platform that lets users -- from pathologists with no ML background to ML practitioners running many parallel experiments -- train, evaluate, and deploy whole-slide image classifiers through natural language interaction with an AI agent. The platform provides a structured set of agent skills that guide the user through dataset curation, automated hyperparameter tuning, multi-strategy model comparison, and human-in-the-loop deployment, all on a pre-built dataset of over 32,000 cases and 66,000 H&E-stained whole-slide images with pre-extracted features. We describe the agent skill architecture, the underlying Multiple Instance Learning (MIL) training framework supporting four classification strategies, and an iterative pairwise hyperparameter search (grid or seeded random) that reduces tuning cost by over 30x compared to exhaustive search. CellDX AI Autopilot is, to our knowledge, the first system to expose pathology-specialized agent skills and a pathology-specialized training platform to general-purpose AI agents (e.g. any LLM-based agent runtime), delivering end-to-end automated model training without requiring the agent itself to be domain-specific. The platform addresses both the ML-expertise bottleneck that limits adoption in diagnostic pathology and the engineering bottleneck that limits how many experiments a researcher can run cost-effectively.
Authors: Jiaxin Yang, Honglin Liu, Yongli Wang, Shuyi Cao, Chengcheng Jiang, Jiale Wang
Abstract: Underwater images captured by Autonomous Underwater Vehicles (AUVs) are inevitably affected by artificial light sources, which often produce halos in the foreground of the camera and seriously interfere with the quality of the image. The existing underwater image enhancement methods fail to fully consider this key problem, and the robustness of processing images under artificial light scenes is poor. In practical applications, since underwater image enhancement itself is a very challenging task, the influence of artificial light sources will lead to serious degradation of image performance and affect subsequent vision tasks. In order to effectively deal with this problem, this paper designs a single halo image correction method based on an iterative structure. The network is mainly divided into two sub-networks, one is the halo layer separation sub-network which aims to separate the halo by gradient minimization, and the other is the multi-scale recovery sub-network which aims to recover the image information masked by halo. The UIEB and EUVP synthetic datasets are used for training to ensure that the network can fully learn the characteristics and laws of underwater halo images. Then a large number of halo images taken in an underwater environment with real artificial light are collected for testing. In addition, the brightness distribution characteristics of underwater halo images are analyzed and the radial gradient is introduced to constraint eliminate halo to improve the effect of underwater image restoration.
Authors: Niyati Rawal, Sushant Ravva, Shah Alam Abir, Saksham Jain, Aman Chadha, Vinija Jain, Suranjana Trivedy, Amitava Das
Abstract: Vision-Language Models (VLMs) have advanced rapidly in multimodal perception and language understanding, yet it remains unclear whether they can reliably ground language into spatially coherent, plausibly executable actions in 3D digital environments. We introduce SleepWalk, a benchmark for evaluating instruction-grounded trajectory prediction in single-scene 3D worlds generated from textual scene descriptions and filtered for navigability. Unlike prior navigation benchmarks centered on long-range exploration across rooms, SleepWalk targets localized, interaction-centric embodied reasoning: given rendered visual observations and a natural-language instruction, a model must predict a trajectory that respects scene geometry, avoids collisions, and terminates at an action-compatible location. The benchmark covers diverse indoor and outdoor environments and organizes tasks into three tiers of spatial and temporal difficulty, enabling fine-grained analysis of grounding under increasing compositional complexity. Using a standardized pointwise judge-based evaluation protocol, we evaluate three frontier VLMs on 2,472 curated 3D environments with nine instructions per scene. Results reveal systematic failures in grounded spatial reasoning, especially under occlusion, interaction constraints, and multi-step instructions: performance drops as the difficulty level of the tasks increase. In general, current VLMs can somewhat produce trajectories that are simultaneously spatially coherent, plausibly executable, and aligned with intended actions. By exposing failures in a controlled yet scalable setting, SleepWalk provides a critical benchmark for advancing grounded multimodal reasoning, embodied planning, vision-language navigation, and action-capable agents in 3D environments.
Authors: Yumao Liu, Tao Liu, Xiangyu Li, Jiaxiang Li, Ke Ma
Abstract: End to end (E2E) autonomous driving trajectory prediction is often trained with camera frames sampled at the highest available temporal frequency, assuming that denser sampling improves performance. We question this assumption by treating temporal sampling frequency as an explicit training set design variable. Starting from high frequency E2E driving datasets, we construct frequency sweep training sets by temporally subsampling camera frames along each trajectory. For each model dataset pair, we train and evaluate the same model under a fixed protocol, so the frequency response reflects how prediction performance changes with sampling frequency. We analyze this response from a capacity aware perspective. Sparse sampling may miss driving relevant cues, while dense sampling may add redundant visual content and off manifold noise. For finite capacity models, this can create a driving irrelevant capacity burden. We evaluate three smaller E2E models and a larger VLA style AutoVLA model on Waymo, nuScenes, and PAVE. Results show model and dataset dependent frequency responses. Smaller E2E models often show non monotonic or near plateau trends and achieve their best 3 second ADE at lower or intermediate frequencies. In contrast, AutoVLA achieves its best 3 second ADE and FDE at the highest evaluated frequency on all three datasets. Iteration matched controls suggest that the advantage of lower or intermediate frequencies for smaller models is not explained only by unequal training update counts. These findings show that temporal sampling frequency should be reported and tuned, rather than fixed to the highest available value.
Authors: Andreas Goulas, Damianos Galanopoulos, Evlampios Apostolidis, Vasileios Mezaris
Abstract: The detection of sensational content in media items can be a critical filtering mechanism for identifying check-worthy content and flagging potential disinformation, since such content triggers physiological arousal that often bypasses critical evaluation and accelerates viral sharing. In this paper we introduce the task of sensational image detection, which aims to determine whether an image contains shocking, provocative, or emotionally charged features to grab attention and trigger strong emotional responses. To support research on this task, we create a new benchmark dataset (called Sens-VisualNews) that contains 9,576 images from news items, annotated based on the (in-)existence of various sensational concepts and events in their visual content. Finally, using Sens-VisualNews, we study the prompt sensitivity, performance and robustness of a wide range of open SotA Multimodal LLMs, across both zero-shot and fine-tuned settings.
Authors: Xi Jiang, Yinjie Zhao, Zesheng Yang, Feng Zheng
Abstract: Visual anomaly detection (VAD) is crucial in many real-world fields, such as industrial inspection, medical imaging, infrastructure monitoring, and remote sensing. However, the specific anomaly definitions, data modalities, and annotation standards across different domains make it difficult to transfer single-domain trained VAD models. Vision-language models (VLMs), pre-trained on large-scale cross-domain data, can perform visual perception under task instructions, offering a promising solution for cross-domain VAD. However, single-inference VLM judgments are unreliable, since they rely more on prior knowledge than on normal-sample references or fine-grained feature evidence. We therefore present AnomalyClaw, a training-free VAD agent that turns anomaly judgment into a multi-round refutation process. In each round, the agent proposes candidate anomalies and refutes each against normal-sample references, drawing on a 13-tool library for visual verification, reference parsing, and frozen expert probing. On the CrossDomainVAD-12 benchmark (12 datasets), AnomalyClaw achieves consistent macro-AUROC improvements over single-step direct inference with +6.23 pp on GPT-5.5, +7.93 pp on Seed2.0-lite, and +3.52 pp on Qwen3.5-VL-27B. We further introduce an optional verbalized self-evolution extension. It builds an online rulebook from internal-branch disagreement without oracle labels. On Qwen3.5-VL-27B, it delivers a +2.09 pp mean gain, comparable to a K = 10 oracle-label supervised baseline (+1.99 pp). These results show that agentic refutation improve anomaly understanding and reasoning of VLMs, rather than merely aggregating tool outputs.
Authors: Tianyuan Zou, Liang Yue, Yang Liu, Ya-Qin Zhang, Sijie Cheng
Abstract: With the growing prevalence of always-on hardware such as smart glasses, body cameras, and home security systems, life-logging visual sensing is becoming inevitable, forming the backbone of persistent, always-on AI systems. Meanwhile, recent advances in proactive agents and world models signal a fundamental shift from episodic, prompt-driven tools to next-generation AI systems that continuously perceive and react to the physical world. Although life-logging video streams can substantially improve utility of these promising systems, they also introduce significant privacy risks by revealing sensitive information, such as behavioral patterns, emotional states, and social interactions, beyond what isolated images expose. If unresolved, these risks may undermine public trust and hinder the sustainable development of always-on AI technologies. Existing privacy protections are either attack-specific or incur substantial utility loss, and fail to consider the entire data exploitation pipeline. We therefore posit that the privacy-utility trade-off in life-logging video streams is a foundational challenge for next-generation AI systems that demands further investigation. We call for novel pipeline-aware privacy-preserving designs that jointly optimize utility and privacy for long-horizon life-logging visual data. In parallel, formal privacy leakage metrics and standardized benchmarks remain important open directions for future research.
Authors: Adi Rosenthal, Dana Berman, Yedid Hoshen, Ariel Shamir
Abstract: Existing image simplification techniques often rely on Non-Photorealistic Rendering (NPR), transforming photographs into stylized sketches, cartoons, or paintings. While effective at reducing visual complexity, such approaches typically sacrifice photographic realism. In this work, we explore a complementary direction: simplifying images while preserving their photorealistic appearance. We introduce progressive semantic image simplification, a framework that iteratively reduces scene complexity by removing and inpainting elements in a controlled manner. At each step, the resulting image remains a plausible natural photograph. Our method combines semantic understanding with generative editing, leveraging Vision-Language Models (VLMs) to identify and prioritize elements for removal, and a learned verifier to ensure photorealism and coherence throughout the process. This is implemented via an iterative Select-Remove-Verify pipeline that produces high-quality simplification trajectories. To improve efficiency, we further distill this process into an image-to-video generation model that directly predicts coherent simplification sequences from a single input image. Beyond generating cleaner and more focused compositions, our approach enables applications such as content-aware decluttering, semantic layer decomposition, and interactive editing. More broadly, our work suggests that simplification through structured content removal can serve as a practical mechanism for guiding visual interpretation within the photorealistic domain, complementing traditional abstraction methods.
Authors: Minqing Huang, Yujiao Xiang, Zihan Liang, Jiajie Huang, Jingqi Wang, Zhi Xu, Feiyang Tan, Hangning Zhou, Mu Yang, Gong Che
Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing reasoning mechanisms still struggle to provide planning-oriented intermediate representations: textual Chain-of-Thought (CoT) fails to preserve continuous spatiotemporal structure, while latent world reasoning remains difficult to use as a direct condition for action generation. In this paper, we propose CoWorld-VLA, a multi-expert world reasoning framework for autonomous driving, where world representations serve as explicit conditions to guide action planning. CoWorld-VLA extracts complementary world information through multi-source supervision and encodes it into expert tokens within the VLA, thereby providing planner-accessible conditioning signals. Specifically, we construct four types of tokens: semantic interaction, geometric structure, dynamic evolution, and ego trajectory tokens, which respectively model interaction intent, spatial structure, future temporal dynamics, and behavioral goals. During action generation, CoWorld-VLA employs a diffusion-based hierarchical multi-expert fusion planner, which is coupled with scene context throughout the joint denoising process to generate continuous ego trajectories. Experiments show that CoWorld-VLA achieves competitive results in both future scene generation and planning on the NAVSIM v1 benchmark, demonstrating strong performance in collision avoidance and trajectory accuracy. Ablation studies further validate the complementarity of expert tokens and their effectiveness as planning conditions for action generation. Code will be available at https://github.com/potatochip1211/CoWorld-VLA.
Authors: Keming Wu, Yijing Cui, Wenhan Xue, Qijie Wang, Xuan Luo, Zhiyuan Feng, Zuhao Yang, Sudong Wang, Sicong Jiang, Haowei Zhu, Zihan Wang, Ping Nie, Wenhu Chen, Bin Wang
Abstract: Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet the community still lacks a benchmark that directly tests whether a model can reason about how an observed world should evolve over time. We introduce WorldReasonBench, which reframes video generation evaluation as world-state prediction: given an initial state and an action, can a model generate a future video whose state evolution remains physically, socially, logically, and informationally consistent? WorldReasonBench contains 436 curated test cases with structured ground-truth QA annotations spanning four reasoning dimensions and 22 subcategories. We evaluate generated videos with a human-aligned two-part methodology: Process-aware Reasoning Verification uses structured QA and reasoning-phase diagnostics to detect temporal and causal failures, while Multi-dimensional Quality Assessment scores reasoning quality, temporal consistency, and visual aesthetics for ranking and reward modeling. We further introduce WorldRewardBench, a preference benchmark with approximately 6K expert-annotated pairs over 1.4K videos, supporting pair-wise and point-wise reward-model evaluation. Across modern video generators, our results expose a persistent gap between visual plausibility and world reasoning: videos can look convincing while failing dynamics, causality, or information preservation. We will release our benchmarks and evaluation toolkit to support community research on genuinely world-aware video generation at https://github.com/UniX-AI-Lab/WorldReasonBench/.
Authors: Yu Zhe, Yang Jiayan, Wei Junhao, Yu-Lin Tsai, Wang Chen
Abstract: Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing diffusion models, enabling users to inject new visual concepts or styles through lightweight parameter updates. However, LoRAs can memorize training images, causing generated outputs to reproduce copyrighted or sensitive content. This risk is particularly concerning in LoRA-sharing ecosystems, where users distribute trained LoRAs without releasing the underlying training data. Existing approaches for mitigating memorization rely on access to the training pipeline, training data, or control over the inference process, making them difficult to apply when only the released LoRA weights are available. We propose \textbf{Base-Anchored Filtering (BAF)}, a training-free and data-free framework for post-hoc memorization mitigation in diffusion LoRAs. BAF decomposes LoRA updates into spectral channels and measures their alignment with the principal subspace of the pretrained backbone. Channels strongly aligned with this subspace are retained as generalizable adaptations, while weakly aligned channels are suppressed as potential carriers of memorized content. Experiments on multiple datasets and diffusion backbones demonstrate that BAF consistently reduces memorization while preserving or even improving generation quality. Our code is available in the supplementary material.
Authors: Zijun Shen, Sihan Yang, Ruichuan An, Ziyu Guo, Hao Liang, Ming Lu, Renrui Zhang, Wentao Zhang
Abstract: Unified Multimodal Models (UMMs) excel in general tasks but struggle to bridge the gap between personalized understanding and generation. Prior works largely rely on implicit token-level alignment via supervised fine-tuning, which fails to fully capture the potential synergy between comprehension and creation. In this work, we propose Sync-R1, an end-to-end reinforcement learning framework that jointly optimizes personalized understanding and generation within a single, explicit reasoning loop. Through this unified feedback process, Sync-R1 enables personalized comprehension to guide content creation, while the resulting generation quality reciprocally refines understanding within an integrated reward landscape. To efficiently orchestrate this dual-task synergy, we introduce Sync-GRPO, a reinforcement learning method utilizing an ensemble reward system. Furthermore, we propose Dynamic Group Scaling (DGS), which adaptively filters low-potential trajectories to reduce gradient variance and accelerate convergence. To better reflect real-world complexity, we introduce UnifyBench++, featuring denser textual descriptions and richer user contexts. Experimental results demonstrate that Sync-R1 achieves state-of-the-art performance, showcasing superior cross-task reasoning and robust personalization without requiring complex cold-start procedures. The code and the UnifyBench++ dataset will be released at: https://github.com/arctanxarc/UniCTokens.
Authors: Kota Ishikawa, Takuma Masui, Keita Koeda, Rickdane Gomez, Lucas Yutaka Kimura, Michio Kondoh
Abstract: Quantifying fish community structure is essential for understanding biodiversity and ecosystem responses in a changing environment, yet existing survey methods provide limited high-frequency, quantitative observations. Conventional approaches, including catch-based methods, underwater visual censuses, and environmental DNA metabarcoding, either require intensive labor or lack reliable estimates of abundance and biomass. Here, we develop an automated framework for quantifying fish communities from underwater video using computer vision. Using videos acquired with a custom-made stereo camera system, the framework integrates deep learning-based fish identification, multi-object tracking, and 3D reconstruction to estimate species-level abundance and biomass. We applied the approach to a reef fish community over a 20-day period with hourly daytime observations, revealing dynamic fluctuations in species richness, abundance, and biomass associated with changes in species composition. By comparing fish communities estimated from visual census and environmental DNA surveys, we demonstrate that our method provides complementary strengths for continuous, non-invasive, and quantitative monitoring of consistently observed species. This approach provides a scalable foundation for long-term monitoring and advances the capacity to resolve fine-scale temporal dynamics in fish communities.
Authors: Sarath Sivaprasad, Hui-Po Wang, Anna-Lisa J\"ackel, Jonas Baumann, Carole Baumann, Jennifer Herrmann, Mario Fritz
Abstract: Zebrafish embryos are a valuable model for drug discovery due to their optical transparency and genetic similarity to humans. However, current evaluations rely on manual inspection, which is costly and labor-intensive. While machine learning offers automation potential, progress is limited by the lack of comprehensive datasets. To address this, we introduce a large-scale dataset of high-resolution microscopic image sequences capturing zebrafish embryonic development under both control conditions and exposure to compounds (3,4-dichloroaniline). This dataset, with expert annotations at fine-grained temporal levels, supports two benchmarking tasks: (1) fertility classification, assessing zebrafish egg viability (130,368 images), and (2) toxicity assessment, detecting malformations induced by toxic exposure over time (55,296 images). Alongside the dataset, we present the first transformer-based baseline model that integrates spatiotemporal features to predict developmental abnormalities at early stages. Experimental results present the model's effectiveness, achieving 98% accuracy in fertility classification and 92% in toxicity assessment. These findings underscore the potential of automated approaches to enhance zebrafish-based toxicity analysis.
Authors: Jinyi Luo, Minghao Liu, Yifan Li, Zejia Fan, Jiaying Liu
Abstract: Super-resolution (SR) is a severely ill-posed problem with inherent ambiguity, as widely recognized in both empirical and theoretical studies. Although recent semantic-guided and multi-modal SR methods exploit large models or external priors to enhance semantic alignment, the fusion of heterogeneous modalities remains insufficiently understood in practice and theory. In this work, we provide the first theoretical modeling of multi-modal SR, revealing that prior methods are bottlenecked by sub-optimal modality utilization. Our analysis shows that the generalization risk bound can be improved by strengthening the alignment between modality weights and their effective contributions, while reducing representation complexity. This theoretical insight inspires us to propose the novel Multi-Modal Mixture-of-Experts Super-Resolution framework (M$^3$ESR) that employs generalization-oriented dynamic modality fusion for accurate risk control and modality contribution optimization. In detail, we propose a novel spatially dynamic modality weighting module and a temporally adaptive modality temperature scheduling mechanism, enabling flexible and adaptive spatial-temporal modality weighting for effective risk control. Extensive experiments demonstrate that our M$^3$ESR significantly boosts generalization and semantic consistency performances, which confirms our superiority.
Authors: Gang Chen, Sebasti\'an Barbas Laina, Stefan Leutenegger, Javier Alonso-Mora
Abstract: Scene graph alignment establishes object correspondences between two 3D scene graphs constructed from partially overlapping observations. This enables efficient scene understanding and object-level relocalization when a robot revisits a place, as well as global map fusion across multiple agents. Such capabilities are essential for robots that require long-term memory for long-horizon tasks involving interactions with the environment. Existing approaches mainly focus on subscan-to-subscan (S2S) alignment and depend heavily on geometric point-cloud features, leaving frame-to-scan (F2S) alignment and open-set vision-language features underexplored. In addition, existing datasets for scene graph alignment remain small-scale with limited object diversity, constraining systematic training and evaluation. We present a unified and efficient scene graph alignment framework that predicts object correspondences by fusing vision-language, textual, and geometric features with spatial context. The framework comprises modules such as a distance-gated spatial attention encoder, a minimum-cost-flow-based allocator, and a global scene embedding generator to achieve accurate alignment even under large coordinate discrepancies. We further introduce ScanNet-SG, a large-scale dataset generated via an automated annotation pipeline with over 700k samples, covering 509 object categories from ScanNet labels and over 3k categories from GPT-4o-based tagging. Experiments show that our method achieves the best overall performance on both F2S and S2S tasks, substantially outperforming existing scene graph alignment methods. Our code and dataset are released at: https://autonomousrobots.nl/paper_websites/opensga.
Authors: Weiqi Yan, Lixin Chen, Xiangrui Hou, Zhipeng Cai, Youbiao Wang, Yangyang Shi, Yu Zang, Cheng Wang
Abstract: Tiny UAV detection from an onboard event camera is difficult when the observer and target move at the same time. In this motion-on-motion regime, ego-motion activates background edges across buildings, vegetation, and horizon structures, while the UAV may appear as a sparse event cluster. To explore this practical problem, we present M$^2$E-UAV, a benchmark and analysis setup for onboard motion-on-motion event-based tiny UAV detection. The processed M$^2$E-UAV benchmark contains 87,223 training samples and 21,395 validation samples across four scene families: sunny building-forest, sunny farm-village, sunset building-forest, and sunset farm-village. We provide M$^2$E-Point, a point-based event baseline, and M$^2$E-Point + IMU, an IMU-conditioned variant, to analyze the role of inertial cues under onboard motion-on-motion detection. M$^2$E-Point encodes events as $[x,y,t,p]$ point sets, extracts local event structure with EdgeConv, and predicts event-level UAV foreground scores, from which bounding boxes are derived via DBSCAN. Our validation-stage analysis shows that point-based event modeling is a strong baseline, while simple IMU conditioning provides only marginal aggregate gains. Under the train/validation split, M$^2$E-Point achieves 0.9673 F1 and 0.5501 mAP50-95, while the IMU-conditioned variant reaches 0.5561 mAP50-95 with only marginal aggregate changes, serving as an initial baseline for future exploration in this domain. Code will be ready in https://github.com/Wickyan/M2E-UAV.
Authors: Heegeon Yoon, Heeyoung Kim
Abstract: Long-tailed distributions in class-imbalanced data present a fundamental challenge for deep learning models, which tend to be biased toward majority classes. While recent methods for long-tailed recognition have mitigated this issue, they are largely restricted to single-modal inputs and cannot fully exploit complementary information from diverse data sources. In this work, we introduce a new framework for long-tailed recognition that explicitly handles multi-modal inputs. Our approach extends multi-expert architectures to the multi-modal setting by fusing heterogeneous data into a unified representation while leveraging modality-specific networks to estimate the informativeness of each modality. These confidence-guided weights dynamically modulate the fusion process, ensuring that more informative modalities contribute more strongly to the final decision. To further enhance performance, we design specialized training and test procedures that accommodate diverse modality combinations, including images and tabular data. Extensive experiments on benchmark and real-world datasets demonstrate that the proposed approach not only effectively integrates multi-modal information but also outperforms existing methods in handling long-tailed, class-imbalanced scenarios, highlighting its robustness and generalization capability.
Authors: Yiqi Tian, Sangjoon Park, Bo Zeng, Pengfei Jin, Yujin Oh, Quanzheng Li
Abstract: Medical image segmentation models can perform unevenly across subgroups. Most existing fairness methods focus on improving average subgroup performance, implicitly treating each subgroup as internally homogeneous. However, this can hide difficult cases within a subgroup, where high-loss samples are obscured by the subgroup mean. We call this problem \textbf{intra-group hidden failure}. To solve this, we propose \textbf{DuetFair} mechanism, a dual-axis fairness framework that jointly considers inter-subgroup adaptation and intra-subgroup robustness. Based on DuetFair, we introduce \textbf{FairDRO}, which combines distribution-aware mixture-of-experts (dMoE) with subgroup-conditioned distributionally robust optimization (DRO) loss aggregation. This design allows the model to adapt across subgroups while also reducing hidden failures within each subgroup. We evaluate FairDRO on three medical image segmentation benchmarks with varying degrees of within-group heterogeneity. FairDRO achieves the best equity-scaled performance on Harvard-FairSeg and improves worst-case subgroup performance on HAM10000 under both age- and race-based grouping schemes. On the 3D radiotherapy target cohort, FairDRO further improves worst-group Dice by 3.5 points ($\uparrow 6.0\%$) under the tumor-stage grouping and by 4.1 points ($\uparrow 7.4\%$) under the institution grouping over the strongest baseline.
Authors: Chang Liu, Mengting Chen, Yixuan Huang, Haoning Wu, Chen Ju, Shuai Xiao, Jinsong Lan, Yanfeng Wang
Abstract: The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, especially when generating long videos or modeling intensive motions. Existing human image animation works address these issues by incorporating human-specific semantic representations, e.g., dense poses or ID embeddings, as additional conditions. However, conditioning on these representations could decrease the generation flexibility. Moreover, their reliance on RGB pixel supervision also lacks emphasis on learning necessary 3D geometric relationships and temporal coherence. In contrast, we introduce a novel approach named SemanticREPA that leverages these semantic representations as supervision signals through representation alignment. Specifically, we begin by training a structure alignment module that aligns the structure representations obtained from video latents with video depth estimation features. We then fix the pretrained module, and utilize it to provide additional supervision on the structure representations of the diffusion models, achieving structure rectification to generate coherent and stable human structures. Simultaneously, we develop an ID alignment module to align the ID representations of the generated videos to face recognition features. We further propose to use the predicted structure representations to refine identity restoration in relevant regions. With structure and ID alignment, our method demonstrates superior quality on extended character motions and enhanced character consistency.
Authors: Yuecheng Liu, Junda Cheng, Longliang Liu, Wenjing Liao, Hanrui Cheng, Yuzhou Wang, Xin Yang
Abstract: Video depth estimation extends monocular prediction into the temporal domain to ensure coherence. However, existing methods often suffer from spatial blurring in fine-detail regions and temporal inconsistencies. We argue that current approaches, which primarily rely on temporal smoothing via Transformers, struggle to maintain strict 3D geometric consistency-particularly under rotations or drastic view changes. To address this, we propose GemDepth, a framework built on the insight that an explicit awareness of camera motion and global 3D structure is a prerequisite for 3D consistency. Distinctively, GemDepth introduces a Geometry-Embedding Module (GEM) that predicts inter-frame camera poses to generate implicit geometric embeddings. This injection of motion priors equips the network with intrinsic 3D perception and alignment capabilities. Guided by these geometric cues, our Alternating Spatio-Temporal Transformer (ASTT) captures latent point-level correspondences to simultaneously enhance spatial precision for sharp details and enforce rigorous temporal consistency. Furthermore, GemDepth employs a data-efficient training strategy, effectively bridging the gap between high efficiency and robust geometric consistency. As shown in Fig.2, comprehensive evaluations demonstrate that GemDepth achieves state-of-the-art performance across multiple datasets, particularly in complex dynamic scenarios. The code is publicly available at: https://github.com/Yuecheng919/GemDepth.
Authors: Zhilei Shu, Shangwen Zhu, Zihang Liang, Xiaofan Li, Qianyu Peng, Xinyu Cui, Bo Ye, Yiming Li, Fan Cheng, Jian Zhao, Yang Cao, Zheng-Jun Zha, Ruili Feng
Abstract: Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events -- a regime in which 68% of general clips and over 99% of robotics/gameplay clips contain overlapping events, yet existing multi-event generators rest on a single-active-prompt assumption. However, modern video generators, such as Diffusion Transformers (DiT), represent time as discrete points through point-wise positional encodings. This formulation creates a fundamental dimension mismatch: temporally extended intervals and overlapping events are mathematically unrepresentable to the attention mechanism. In this paper, we propose Time Interval Encoding (TIE), a principled, plug-and-play interval-aware generalization of rotary embeddings that elevates time intervals to first-class primitives inside DiT cross-attention. Rather than introducing another heuristic interval embedding, we show that, within RoPE-compatible bilinear attention, TIE is characterized by two basic principles: Temporal Integrability, which requires an event to aggregate positional evidence over its full duration, and Duration Invariance, which removes the trivial bias toward longer intervals. Under a uniform kernel, this characterization yields an efficient closed-form sinc-based solution that preserves the standard attention interface and naturally attenuates boundary noise through interval integration. Empirically, TIE preserves the visual quality of the base DiT model while substantially improving temporal controllability. In our experiments on the OmniEvents dataset, it improves human-verified Temporal Constraint Satisfaction Rate from 77.34% to 96.03% and reduces temporal boundary error from 0.261s to 0.073s, while also improving trajectory-level temporal alignment metrics. The code and dataset are available at https://github.com/MatrixTeam-AI/TIE.
Authors: Vittorio Palladino, Gianluca Palermo, Michael E. Papka, Zhiling Lan
Abstract: As large language models span dense, mixture-of-experts, and state-space architectures and are deployed on heterogeneous accelerators under increasingly diverse multimodal workloads, optimising inference energy has become as critical as optimizing latency and throughput. Existing approaches either treat latency as an energy proxy or rely on data-hungry black-box surrogates. Both fail under varying parallelism strategies: latency and energy optima diverge in over 20% of configurations we tested, and black-box surrogates require hundreds of profiling samples to generalize across model families and hardware. We present EnergyLens, which uses symbolic regression as a structure-discovery tool over profiling data to derive a single twelve-parameter closed-form energy model expressed in terms of system properties such as degree of parallelism, batch size, and sequence length. Unlike black-box surrogates, EnergyLens decouples tensor and pipeline parallelism contributions and separates prefill from decode energy, making its predictions physically interpretable and actionable. Fitted from as few as 50 profiling measurements, EnergyLens achieves 88.2% Top-1 configuration selection accuracy across many evaluation scenarios compared to 60.9% for the closest prior analytical baseline, matches the predictive accuracy of ensemble ML methods with 10x fewer profiling samples, and extrapolates reliably to unseen batch sizes and hardware platforms without structural modification, making it a practical, interpretable tool for energy-optimal LLM deployment.
Authors: Lingjun Zhang, Changjie Wu, Linzhe Shi, Jiangyang Li, Jiaxin Liu, Lei Yang, Hang Zhang, Mu Xu, Hong Wang
Abstract: End-to-end autonomous driving systems are increasingly integrating Vision-Language Model (VLM) architectures, incorporating text reasoning or visual reasoning to enhance the robustness and accuracy of driving decisions. However, the reasoning mechanisms employed in most methods are direct adaptations from general domains, lacking in-depth exploration tailored to autonomous driving scenarios, particularly within visual reasoning modules. In this paper, we propose a driving world model that performs parallel prediction of latent semantic features for consecutive future frames in the bird's-eye-view (BEV) space, thereby enabling long-horizon modeling of future world states. We also introduce an efficient and adaptive text reasoning mechanism that utilizes additional social knowledge and reasoning capabilities to further improve driving performance in challenging long-tail scenarios. We present a novel, efficient, and effective approach that achieves state-of-the-art (SOTA) results on the closed-loop Bench2drive benchmark. Codes are available at: https://github.com/hotdogcheesewhite/DeepSight.
Authors: Nengbo Lu, Bin Zhao
Abstract: In this paper, we aim to jointly model the geometry, appearance, and physical information of 3D scenes solely from dynamic multi-view videos, without relying on any physical priors. Existing works typically employ physical losses merely as soft constraints or integrate physical simulations into neural networks; however, these approaches often fail to effectively learn complex motion physics. Although modeling velocity fields holds the potential to capture authentic physical information, due to the lack of appropriate physical constraints, current methods are unable to correctly learn the interaction mechanisms between rigid and non-rigid particles. To address this, we propose VeloGauss, designed to learn the physical properties of complex dynamic 3D scenes without physical priors. Our method learns the velocity field for each Gaussian particle by introducing a Physics Code and a Particle Dynamics System, and ultimately incorporates Global Physical Constraints to ensure the physical consistency of the scene. Extensive experiments on four public datasets demonstrate that our method outperforms achieves state-of-the-art performance in both Novel View Interpolation and Future Frame Extrapolation tasks.
Authors: Chen Zhong, Xiao An, Jiaxing Sun, Zihan Gui, Guangyi Yang, Wei He
Abstract: Low-level visual perception underpins reliable remote sensing (RS) image analysis, yet current image quality assessment (IQA) methods output uninterpretable scalar scores rather than characterizing physics-driven RS degradations, deviating markedly from the diagnostic needs of RS experts. While Vision-Language Models (VLMs) present a compelling alternative by delivering language-grounded IQA, their visual priors are heavily biased toward ground-level natural images. Consequently, whether VLMs can overcome this domain gap to perceive and articulate RS artifacts remains insufficiently studied. To bridge this gap, we propose \textbf{SenseBench}, the first dedicated diagnostic benchmark for RS low-level visual perception and description. Driven by a physics-based hierarchical taxonomy that unifies both non-reference and reference-based paradigms, SenseBench features over 10K meticulously curated instances across 6 major and 22 fine-grained RS degradation categories. Specifically, two complementary protocols are designed for evaluation: objective low-level visual \textit{perception} and subjective diagnostic \textit{description}. Comprehensive evaluation of 29 state-of-the-art VLMs reveals not only skewed domain priors and multi-distortion collapse, but also \textit{fluency illusion} and a \textit{perception-description inversion} effect. We hope SenseBench provides a robust evaluation testbed and high-quality diagnostic data to advance the development of VLMs in RS low-level perception. Code and datasets are available \href{https://github.com/Zhong-Chenchen/SenseBench}{\textcolor{blue}{here}}.
Authors: Yuanyuan Peng, Wen Li, Xiong Li, Juan Zhou
Abstract: Retinal vessel segmentation is crucial for diagnosis and assessment of ocular diseases. Notably, segmentation of small retinal vessels has been consistently recognized as a challenging and complex task. To tackle this challenge, we design a hybrid CNN-Mamba fusion network that integrates polygon scanning mamba and space-frequency collaborative attention mechanism for the detection of small vessels. Considering that the traditional mamba architecture with horizontal-vertical scanning may compromise the topological integrity of target structures and result in local discontinuities in small retinal vessels, we present a polygon scanning visual state space model (PS-VSS) to identify small vessel structural features by multi-layer reverse scanning way. Which effectively preserves pixels connectivity, thereby substantially mitigating the loss of information pertaining to small vessels. Furthermore, as we all known that the spatial domain prioritizes positional and structural information, while the frequency domain emphasizes global perception and local detail components, a space-frequency collaborative attention mechanism (SFCAM) is introduced within the skip connection to extract efficient features from the spatial and frequency domains. This strategy empowers the model to dynamically enhance the key features while effectively suppressing clutters. To assess the efficacy of our model, it was tested on three publicly available datasets: DRIVE, STARE, and CHASE_DB1. Compared to manual annotations, our model demonstrated F1 scores of 0.8283, 0.8282, and 0.8251, Area Under Curve (AUC) values of 0.9806, 0.9840, and 0.9866, and Sensitivity (SE) values of of 0.8268, 0.8314, and 0.8484 across three datasets, respectively. The effectiveness of our model was validated through both visual inspection and quantitative analysis.
Authors: Guoquan Wei, Liu Shi, Chong Chen, Qiegen Liu
Abstract: Despite extensive research on computed tomography (CT) denoising, few studies exploit projection-domain data characteristics to mitigate noise correlation. To address this, this work proposes FrequencyCT, the first zero-shot self-supervised method for pseudo-label generation in the frequency domain for low-dose CT denoising. Leveraging the characteristic of the frequency domain that largely isolates noise from clean signals, a regional low-frequency anchoring technique is proposed. Phase-preserving amplitude modulation and mask perturbation in the high-frequency region generate pseudo-label data for self-supervision. The fluctuating noise variance in the projection domain prompts truncation of the generated samples to stabilize the network's optimization gradient. Evaluation results on multiple public and real-world datasets confirm the clinical application potential of this research, which will have a revolutionary impact on the field of denoising. The code can be obtained from https://github.com/yqx7150/FrequencyCT.
Authors: Nengbo Lu, Minghua Pan
Abstract: Learning a physical model from video data that can comprehend physical laws and predict the future trajectories of objects is a formidable challenge in artificial intelligence. Prior approaches either leverage various Partial Differential Equations (PDEs) as soft constraints in the form of PINN losses, or integrate physics simulators into neural networks; however, they often rely on strong priors or high-quality geometry reconstruction. In this paper, we propose CausalGS, a framework that learns the causal dynamics of complex dynamic 3D scenes solely from multi-view videos, while dispensing with the reliance on explicit priors. At its core is an inverse physics inference module that decouples the complex dynamics problem from the video into the joint inference of two factors: the initial velocity field representing the scene's kinematics, and the intrinsic material properties governing its dynamics. This inferred physical information is then utilized within a differentiable physics simulator to guide the learning process in a physics-regularized manner. Extensive experiments demonstrate that CausalGS surpasses the state-of-the-art on the highly challenging task of long-term future frame extrapolation, while also exhibiting advanced performance in novel view interpolation. Crucially, our work shows that, without any human annotation, the model is able to learn the complex interactions between multiple physical properties and understand the causal relationships driving the scene's dynamic evolution, solely from visual observations.
Authors: Yanbing Zhang, Bo Wang, Jianhui Liu, Nan Jiang, Jiaxiu Jiang, Haoze Sun, Yijun Yang, Shenghe Zheng, Lin Song, Haoyang Huang, Nan Duan, Wenbo Li
Abstract: Current Large Multimodal Models (LMMs) struggle with spatial reasoning tasks requiring viewpoint-dependent understanding, largely because they are confined to a single, static observation. We propose Thinking with Novel Views (TwNV), a paradigm that integrates generative novel-view synthesis into the reasoning loop: a Reasoner LMM identifies spatial ambiguity, instructs a Painter to synthesize an alternative viewpoint, and re-examines the scene with the additional evidence. Through systematic experiments we address three research questions. (1) Instruction format: numerical camera-pose specifications yield more reliable view control than free-form language. (2) Generation fidelity: synthesized view quality is tightly coupled with downstream spatial accuracy. (3) Inference-time visual scaling: iterative multi-turn view refinement further improves performance, echoing recent scaling trends in language reasoning. Across four spatial subtask categories and four LMM architectures (both closed- and open-source), TwNV consistently improves accuracy by +1.3 to +3.9 pp, with the largest gains on viewpoint-sensitive subtasks. These results establish novel-view generation as a practical lever for advancing spatial intelligence of LMMs.
Authors: Hongyou Zhou, Marc Toussaint, Ling Shao, Zihan Ye
Abstract: Despite strong zero-shot performance, SAM is unreliable under domain shift due to Mask-level Confidence Confusion (MCC), where a single IoU-based mask score fails to reflect pixel-wise reliability near boundaries. Motivated by the contrast between texture-biased shortcuts in neural networks and shape-centric processing in human vision, we model out-of-domain variation as appearance shifts and non-rigid deformations that jointly stress calibration. We propose Segment Anything with Robust Uncertainty-Accuracy Correlation (RUAC) for robust pixel-wise uncertainty estimation under appearance and deformation shifts. RUAC adds a lightweight uncertainty head, trains it with a collaborative style-deformation attack that jointly perturbs texture and geometry, and applies Uncertainty-Accuracy Alignment to ensure uncertainty consistently highlights erroneous pixels even under adversarial perturbations. Across 23 zero-shot domains, RUAC improves segmentation quality and yields more faithful uncertainty with stronger uncertainty-accuracy correlation. Project page: https://github.com/HongyouZhou/ruac.git.
Authors: Guohuan Xie, Xin He, Dingying Fan, Siqi Li, Yun Liu
Abstract: Few-shot anomaly detection (FSAD) has made significant strides, yet existing methods still face critical challenges: (i) dependence on task- or dataset-specific training/fine-tuning, (ii) reliance on language supervision or carefully hand-crafted prompts, and (iii) limited robustness across domains. In this paper, we introduce HyperFSAD, a novel FSAD framework that is training-free, language-free, and robust across domains, offering a powerful solution to these challenges. Built upon DINOv3 and a hypergraph-based inference mechanism, our approach performs inference without any task-specific optimization or text prompts, while remaining competitive. Specifically, we replace sensitive nearest-neighbor / top-$n$ matching with \textbf{Sparse Hyper Matching}: \textit{sparsemax} first selects the most relevant support patches, which are then aggregated into a \textit{hyperedge} as compact normal evidence to suppress background noise and distractors. We further introduce \textbf{Dual-Branch Image Scoring}, which fuses \emph{spatial anomaly evidence} from the patch-grid anomaly map with \emph{global semantic deviation} captured by support-aware CLS matching, yielding a robust image-level anomaly score in a strictly visual manner. Notably, all components of HyperFSAD are purely visual, eliminating the need for labor-intensive hand-crafted text prompts. Under the stringent training-free and language-free setting, HyperFSAD achieves state-of-the-art performance across six datasets spanning four industrial datasets (MVTecAD, VisA, MPDD, BTAD) and two medical datasets (RESC, BraTS).
Authors: Laurenz Nagler, Martin Zach, Thomas Pock
Abstract: Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However, most existing methods rely on large networks with opaque time-conditioning mechanisms, and require offline coil sensitivity estimation. This results in limited interpretability of the reconstruction process and reduced flexibility in the acquisition setup. To address these limitations, we jointly reconstruct the image and the coil sensitivities by combining the parameter-efficient product-of-Gaussian-mixture diffusion model as an image prior with a classical smoothness prior on the coil sensitivities. The proposed method is fast and robust to both contrast and anatomical distribution shifts as well as changing k-space trajectories. Finally, we propose a more expressive parameterization of the image prior which improves results in denoising and magnetic resonance image reconstruction.
Authors: Nikolaos Gkalelis, Vasileios Mezaris
Abstract: Large Vision-Language Models (VLMs) are successful in addressing a multitude of vision-language understanding tasks, such as Visual Question Answering (VQA), but their memory and compute requirements remain a concern for practical deployment. A promising class of techniques for mitigating this concern is Knowledge Distillation, where knowledge from a high-capacity Teacher network is transferred to a considerably smaller Student network. However, the capacity gap between the two networks is both a blessing and a curse: the smaller the Student network, the better its efficiency, and the larger the Teacher, the more knowledge it carries; yet, beyond a point, the larger capacity gap between the two leads to worse knowledge transfer. To counter this effect, we propose a bottom-up cascaded knowledge distillation (CKD) framework. Instead of treating knowledge transfer as an activity involving one high-capacity Teacher (or an ensemble of such), inspired by human formal education systems, we introduce one (potentially, more) additional Teacher(s) of intermediate capacity that gradually bring the Student network to the next level, where the next (higher-capacity) Teacher can take over. We provide a theoretical analysis in order to study the effect of cascaded distillation in the generalization performance of the Student. We apply the proposed framework on models build upon the LLaVA methodology and evaluate the derived models on seven standard, publicly available VQA benchmarks, demonstrating their SotA performance.
Authors: Hantao Zhang, Weidong Guo, Yuhe Liu, Jiancheng Yang, Sathvik Bhagavan, Danli Shi, Mingda Xu, Pascal Fua
Abstract: Data-driven medical AI is traditionally formulated as a discriminative mapping from input $X$ to output $Y$ via a learned function $f$, which does not generalize well across heterogeneous data and modalities encountered in real-world clinical settings. In this work, we propose a fundamentally different, generative paradigm. We model the joint distribution $P(X,Y)$ using diffusion models and reframe inference as a test-time output optimization problem. By guiding the generative process to match observed inputs, our framework enables flexible, gradient-based conditioning at inference time without architectural changes or retraining, effectively supporting arbitrary and previously unseen combinations of observations. Extensive experiments demonstrate strong performance across standard and cross-modality medical image segmentation, few-shot segmentation with only 2 or 4 training samples, degraded-input segmentation, shape completion from sparse and partial observations, and zero-shot application to demonstrate generality. To support these evaluations, we curated and released a large-scale text-shape dataset derived from MedShapeNet. Our results highlight the versatility of generative joint modeling as a foundation for reusable, task-agnostic medical AI systems.
Authors: Michal Byra, Pawel Olszowiec, Grzegorz Stefanski, Grzegorz Gruszczynski, Alberto Presta
Abstract: Vision Transformers (ViTs) are built by stacking independently parameterized blocks, but it remains unclear how much of this depth requires layer specific transformations and how much can be realized through recurrent computation. We study this question with bViT, a single-block recurrent ViT in which one transformer block is applied repeatedly to process an image. This architecture preserves the iterative structure of a deep ViT while removing layer specific block parameterization, providing a controlled setting for studying recurrence in vision. On ImageNet-1K, a 12-step bViT-B achieves accuracy comparable to standard ViT-B under the same training recipe and computational budget, while using an order of magnitude fewer parameters. We observe that recurrent performance improves with representation width, with wider bViTs recovering much more of the performance of standard ViTs than narrow variants. We interpret this behavior as implicit depth multiplexing, where a shared block expresses multiple step-dependent computations through the evolving hidden state. Beyond ImageNet classification, bViT transfers competitively to downstream tasks and enables parameter-efficient fine-tuning. Mechanistic analyses of activations, attention and step-specific pruning show that the shared block changes its effective behavior across recurrent steps rather than simply repeating the same computation. Our results suggest that a large fraction of ViT depth can be implemented through recurrent reuse, provided that the representation space is sufficiently wide.
Authors: Viktor Bergkvist, Felix Rydell, Per-Erik Forss\'en, David Gustafsson, Johan Rideg
Abstract: Event cameras offer distinct advantages over conventional frame-based sensors, including microsecond-level temporal resolution, high dynamic range, and low bandwidth. In this paper, we predict per-pixel depth distributions from monocular event streams using deep neural networks. We estimate uncertainty using Gaussian, log-normal, and evidential learning frameworks. We compare six event representations: spatio-temporal voxel grids with 1, 5, 10, and 20 temporal bins, the Compact Spatio-Temporal Representation (CSTR), and Time-Ordered Recent Event (TORE) volumes. Our U-Net-based models are trained on synthetic data and then fine-tuned on real sequences. We evaluate performance using absolute relative error, root mean squared error, and the area under the sparsification error. Quantitative results show that the representations perform similarly, while 10 bin log-normal and 5 bin evidential learning perform best across metrics. Our experiments demonstrate that uncertainty estimation can be successfully integrated into event-based monocular depth estimation, and be used to indicate pixels with reliable depth.
Authors: Qingxin Xiao, Peilin Zhao, Yangyang Zhao, Lingwei Dang, Qingyao Wu
Abstract: During MLLM decoding, attention often abnormally concentrates on irrelevant image tokens. While existing research dismisses this as invalid noise and forcibly redirects attention to compel focusing on key image information, we argue these tokens are critical carriers of visual and narrative logic, and such coercive corrections exacerbate visual-language imbalance. Adopting a "decoding-as-game" perspective, we reveal that hallucinations stem from an equilibrium imbalance between linguistic priors and visual information. We propose Adversarial Counter-Commonsense Equilibrium (ACE), a training-free framework that perturbs visual context via counter-commonsense patches. Leveraging the fact that authentic visual features remain stable under perturbation while hallucinations fluctuate, ACE implements a dynamic game decoding strategy. This approach precisely suppresses perturbation-sensitive priors while compensating for stable visual signals to restore balance. Extensive experiments demonstrate that ACE, as a plug-and-play strategy, enhances model trustworthiness with negligible inference overhead.
Authors: Zhenyu Liang, Xiao Zhang, Tianchao Li, Jack C. P. Cheng, Chi-Keung Tang
Abstract: Transmissive scenes are ubiquitous in daily life, yet reconstructing and rendering them remains highly challenging due to the inherent entanglement between near-field reflections from the surrounding environment on the transmissive surface, and the transmitted content of the scene behind it. This coupling gives rise to dual surface geometries and dual radiance components within each observation, posing ambiguities for standard methods. We present TransmissiveGS, a novel framework for disentangled reconstruction and rendering of transmissive scenes. Specifically, we model the scene with a dual-Gaussian representation and introduce a deferred shading function to jointly render the two Gaussian components. To separate reflection and transmission, we exploit the inherent multi-view inconsistency of reflections and leverage the residuals from reconstructing multi-view consistent content as cues for disentangled geometry and appearance modeling. We further propose a reflection light field that enables high-fidelity estimation of near-field reflections. During training, we introduce a high-frequency regularization to preserve fine details. We also contribute a new synthetic dataset for evaluating transmissive surface reconstruction. Experiments on both synthetic and real-world scenes demonstrate that TransmissiveGS consistently outperforms prior Gaussian Splatting-based methods in both reconstruction and rendering quality for transmissive scenes.
Authors: Zhenyu Liang, Jack C. P. Cheng
Abstract: Landslide monitoring and simulation play an important role in urban safety assessment and disaster prevention. Existing landslide simulation pipelines typically rely on digital elevation model and mesh-based representations, which are suitable for geometric analysis, but often lack visual realism. This limitation reduces their effectiveness in interactive applications, hazard communication, and public education. In this paper, we propose a UAV-based scan-to-simulation framework that bridges photorealistic scene capture and physics-based landslide simulation through 3DGS. Specifically, our pipeline includes four stages: (1) UAV-based acquisition of slope imagery, (2) reconstruction of a low-anisotropy 3DGS scene representation, (3) volumetric conversion of the target simulation region by filling the interior of the surface-based model, and (4) integration with the Material Point Method (MPM) for landslide simulation. We validate the proposed framework on a real landslide site in Hong Kong that experienced a severe landslide event. The results show that our method supports both realistic visual reconstruction and effective simulation.
Authors: Huimin Wang, Leilei Ouyang, Chang Xia, Yongqi Kang, Yu Fu, Yuqi Ouyang
Abstract: Generating long-horizon music videos (MVs) is frequently constrained by prohibitive computational costs and difficulty maintaining cross-shot consistency. We propose AllocMV, a hierarchical framework formulating music video synthesis as a Multiple-Choice Knapsack Problem (MCKP). AllocMV represents the video's persistent state as a compact, structured object comprising character entities, scene priors, and sharing graphs, produced by a global planner prior to realization. By estimating segment saliency from multimodal cues, a group-level MCKP solver based on dynamic programming optimally allocates resources across High-Gen, Mid-Gen, and Reuse branches. For repetitive musical motifs, we implement a divergence-based forking strategy that reuses visual prefixes to reduce costs while ensuring motif-level continuity. Evaluated via the Cost-Quality Ratio (CQR), AllocMV achieves an optimal trade-off between perceived quality and resource expenditure under strict budgetary and rhythmic constraints.
Authors: Bing Zhao, Chenfei Wu, Deqing Li, Hao Meng, Jiahao Li, Jie Zhang, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kuan Cao, Kun Yan, Liang Peng, Lihan Jiang, Niantong Li, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiao Xu, Xiaoyue Chen, Xihua Wang, Yan Shu, Yanran Zhang, Yi Wang, Yilei Chen, Ying Ba, Yixian Xu, Yujia Wu, Yuxiang Chen, Zecheng Tang, Zekai Zhang, Zhendong Wang, Zihao Liu, Zikai Zhou, An Yang, Chen Cheng, Chenxu Lv, Dayiheng Liu, Fan Zhou, Hantian Xiong, Hongzhu Shi, Hu Wei, Huihong Zhao, Ivy Liu, Jianwei Zhang, Jiawei Zhang, Kai Chen, Kang He, Levon Xue, Lin Qu, Linhan Tang, Luwen Feng, Minggang Wu, Minmin Sun, Na Ni, Rui Men, Shuai Bai, Sishou Zheng, Tao Lan, Tianqi Zhang, Tingkun Wen, Wei Wang, Weixu Qiao, Weiyi Lu, Wenmeng Zhou, Xiaodong Deng, Xiaoxiao Xu, Xinlei Fang, Xionghui Chen, Yanan Wang, Yang Fan, Yichang Zhang, Yixuan Xu, Yu Wu, Zhiyuan Ma, Zhizhi Cai
Abstract: We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework. Despite recent progress, existing models still struggle with ultra-long text rendering, multilingual typography, high-resolution photorealism, robust instruction following, and efficient deployment, especially in text-rich and compositionally complex scenarios. Qwen-Image-2.0 addresses these challenges by coupling Qwen3-VL as the condition encoder with a Multimodal Diffusion Transformer for joint condition-target modeling, supported by large-scale data curation and a customized multi-stage training pipeline. This enables strong multimodal understanding while preserving flexible generation and editing capabilities. The model supports instructions of up to 1K tokens for generating text-rich content such as slides, posters, infographics, and comics, while significantly improving multilingual text fidelity and typography. It also enhances photorealistic generation with richer details, more realistic textures, and coherent lighting, and follows complex prompts more reliably across diverse styles. Extensive human evaluations show that Qwen-Image-2.0 substantially outperforms previous Qwen-Image models in both generation and editing, marking a step toward more general, reliable, and practical image generation foundation models.
Authors: Kaicong Huang, Weiheng Oh, Thomas Guggisberg, Ruimin Ke
Abstract: Automated transit payment analysis is vital for scalable fare auditing and passenger analytics, yet practice still relies on limited manual inspection. Prior vision- and skeleton-based methods remain brittle under noisy onboard surveillance and often depend on poorly generalizable handcrafted features. Building on the success of graph convolutional networks in human action recognition, we observe that skeleton features excel at modeling global spatiotemporal dependencies but tend to underemphasize the subtle local relative motions that distinguish payment actions. In contrast, RGB features preserve fine-grained spatial details yet often lack reliable temporal continuity in surveillance footage. To bridge both system-level deployment needs and model-level design challenges, we present iPay, an integrated payment action recognition framework for onboard transit surveillance system. iPay adopts a multimodal mixture-of-experts architecture with four tightly coupled streams: (1) an RGB expert stream emphasizing local evidence via region-focused computation; (2) a skeleton expert stream modeling articulated motion with a graph convolutional backbone; (3) a dual-attention fusion stream enabling skeleton-to-RGB temporal transfer and RGB-to-skeleton spatial enhancement; and (4) a prior-driven Spatial Difference Discriminator (SDD) that explicitly models hand-to-anchor relative motion to improve task-specific discriminability. We also collaborate with local transit agencies to collect over 55 hours of real onboard surveillance footage, yielding 500+ payment clips. Experiments show that iPay outperforms prior methods and achieves 83.45\% recognition accuracy with competitive computational efficiency, making it suitable for edge deployment. Code is available at https://github.com/ccoopq/iPay.
Authors: Kefei Tian, Yuansheng Lian, Kai Yang, Xiangdong Chen, Shen Li
Abstract: Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing methods, whether rule-based or data-driven, frequently struggle to capture complex scene semantics, infer potential risks, and make reliable decisions in rare, high-risk situations. While vision-language models (VLMs) offer promising approaches for safe decision-making in these environments, most current approaches lack reflective and causal reasoning, thereby limiting their overall robustness. To address this, we propose a counterfactual chain-of-thought (C-CoT) framework that leverages VLMs to decompose driving decisions into five sequential stages: scene description, critical object identification, risk prediction, counterfactual risk reasoning, and final action planning. Within the counterfactual reasoning stage, we introduce a structured meta-action evaluation tree to explicitly assess the potential consequences of alternative action combinations. This self-reflective reasoning establishes causal links between action choices and safety outcomes, improving robustness in long-tail and out-of-distribution scenarios. To validate our approach, we construct the DeepAccident-CCoT dataset based on the DeepAccident benchmark and fine-tune a Qwen2.5-VL (7B) model using low-rank adaptation. Our model achieves a risk prediction recall of 81.9%, reduces the collision rate to 3.52%, and lowers L2 error to 1.98 m. Ablation studies further confirm the critical role of counterfactual reasoning and the meta-action evaluation tree in enhancing safety and interpretability.
Authors: Yifeng Yang, Jubo Feng, Jing Xu, Xinbing Wang, Qinying Gu, Nanyang Ye
Abstract: Vision-language models enable OOD detection by comparing image alignment with ID labels and negative semantics. Existing negative-label-based methods mainly rely on static negative labels constructed before inference, limiting their ability to cover diverse and evolving OOD concepts. Although test-time expansion provides a natural solution, naively learning negative semantics from potential OOD samples may introduce hard ID contamination. To address this issue, we propose a \textbf{T}est-time \textbf{I}D-prototype-separated \textbf{N}egative \textbf{S}emantics learning method, termed \textbf{TINS}. TINS learns sample-specific negative text embeddings via image-to-text modality inversion and introduces ID-prototype-separated regularization to keep them separated from ID semantics. To further stabilize negative semantics expansion, TINS employs group-wise aggregation scoring and a buffer update strategy. Extensive experiments across Four-OOD, OpenOOD, Temporal-shift, and Various ID settings show consistent improvements over strong baselines. Notably, on the Four-OOD benchmark with ImageNet-1K as ID, TINS reduces the average FPR95 from 14.04\% to 6.72\%. Our code is available at https://github.com/zxk1212/tins.
Authors: Wenxuan Li, Pedro R. A. S. Bassi, Xinze Zhou, Jakob Wasserthal, Alan L. Yuille, Zongwei Zhou
Abstract: Cancer screening is a reasoning task. A radiologist observes findings, compares them to prior scans, integrates clinical context, and reaches a diagnostic conclusion confirmed by pathology. We present RadThinking, a Visual Question Answering (VQA) dataset that makes this reasoning explicit and trainable. RadThinking releases VQA pairs at three difficulty tiers. Foundation VQAs are atomic perception questions. Single-step reasoning VQAs apply one clinical rule. Compositional VQAs require multi-step chain-of-thought to reach a guideline category such as LI-RADS-5. For every compositional VQA, we release the chain of foundation VQAs that solves it. The chain follows the rules of the governing clinical reporting standard. The dataset spans 20,362 CT scans from 9,131 patients across 43 cancer groups, plus 2,077 verified healthy controls with >1-year follow-up. To our knowledge, RadThinking is the first cancer-screening VQA corpus that stratifies questions by reasoning depth and grounds compositions in clinical reporting standards. The foundation tier supplies atomic perception supervision. The compositional tier supplies chain-of-thought data and verifiable rewards for reinforcement-learning recipes such as DeepSeek-R1 and OpenAI o1. RadThinking enables systematic training and evaluation of whether AI systems can reason about cancer, not merely detect it.
Authors: Mohamed Eltahir, Lama Ayash, Ali Habibullah, Tanveer Hussain, Naeemullah Khan
Abstract: Long-video understanding in VLMs is bottlenecked by a single monolithic forward pass over thousands of frames at quadratic attention cost. A common mitigation is to first select a small subset of informative frames before the forward pass; common for training-free selectors via auxiliary encoder-space similarities. Such signals are capped by contrastive pretraining, which usually fails on reasoning-heavy queries (negation, cross-frame counting, holistic summarization). We propose GridProbe, an efficient training-free posterior-probing inference paradigm that scores evidence in answer space using a frozen VLM's own reasoning and then selects question-relevant frames adaptively, resulting in sub-quadratic attention cost with little to no accuracy loss. We arrange frames on a $K{\times}K$ grid and run lightweight row R and column C probes, where each probe reads its peak posterior as a query-conditioned confidence. The outer product of R and C yields an interpretable importance map whose skewness and kurtosis drive Shape-Adaptive Selection, a closed-form rule that reliably replaces the fixed frame budget $M$ with a per-question $M_{\mathrm{eff}}$. We show empirically that $M_{\mathrm{eff}}$ tracks intrinsic question difficulty without ever seeing the answer, a sign of test-time adaptive compute. On Video-MME-v2, GridProbe matches the monolithic baseline within $1.6$ pp Avg Acc at $3.36\times$ TFLOPs reduction, while on LongVideoBench it Pareto-dominates the baseline ($+0.9$ pp at $0.35\times$ compute). Because the selector and QA models can be decoupled, pairing a small 2B selector with a stronger 4B or 8B QA is strictly Pareto-dominant over the 2B monolithic baseline (up to $+4.0$ pp at $0.52\times$ compute, on average), with no retraining. Finally, the interpretability of the importance maps opens future avenues for behavioral diagnostics, grounding, and frame-selection distillation.
Authors: Mengqi He, Xinyu Tian, Xin Shen, Shu Zou, Jinhong Ni, Zhaoyuan Yang, Weikang Li, Xuesong Li, Jing Zhang
Abstract: Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibility of transferable multimodal jailbreaks. We revisit this conclusion under a strictly untargeted threat model without enforcing a fixed prefix or response pattern. Our preliminary experiment reveals that refusal behavior concentrates at high-entropy tokens during autoregressive decoding, and non-refusal tokens already carry substantial probability mass among the top-ranked candidates before attack. Motivated by this finding, we propose Untargeted Jailbreak via Entropy Maximization(UJEM)-KL, a lightweight attack that maximizes entropy at these decision tokens to flip refusal outcomes, while stabilizing the remaining low-entropy positions to preserve output quality. Across three VLMs and two safety benchmarks, UJEM-KL achieves competitive white-box attack success rates and consistently improves transferability, while remaining effective under representative defenses. Our experimental results indicate that the limited transferability primarily stems from overly constrained optimization objectives.
Authors: Tao Hu, Da-Wei Zhou
Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, yet real-world deployment often requires continual capability expansion across sequential tasks. In such scenarios, Multimodal Continual Instruction Tuning (MCIT) aims to acquire new capabilities while limiting catastrophic forgetting. Existing methods mainly follow a module-composition paradigm: they maintain task-level prompts or LoRA experts and dynamically route or aggregate a subset of them at inference. However, samples within the same task can still differ substantially in visual scenes, question intents, and reasoning demands. This motivates instance-level adaptation to individual query-image pairs rather than only selecting or combining task-level modules. To this end, we propose DRAPE (Dynamic Cross-Modal Prompt Generation), a prompt-learning framework that synthesizes continuous instance-specific soft prompts for MCIT. Instead of selecting prompts from a fixed pool, DRAPE derives prompt queries from the textual instruction and cross-attends to visual patch features, producing query-image conditioned prompts that are prepended to the frozen LLM. To mitigate forgetting during sequential updates, DRAPE applies null-space gradient projection to the shared projector and uses CLIP-based prototype routing for task-label-free generator selection at inference. Extensive experiments on MCIT benchmarks show that DRAPE achieves state-of-the-art performance among representative prompt-based and LoRA-based continual-learning baselines.
Authors: Ziyi Wang, Xianping Ma, Ziyao Wang, Hongyang Zhang, Man On Pun
Abstract: The multimodal fusion of images and scene captions has been extensively explored and applied in various fields. However, when dealing with complex remote sensing (RS) scenes, existing studies have predominantly concentrated on architectural optimizations for integrating textual semantic information with visual features, while largely neglecting the generation of high-quality RS captions and the investigation of their effectiveness in multimodal semantic fusion.In this context, we propose the Dynamic MLLM Mixture-of-Experts Perception-Guided Remote Sensing Scene Segmentation, referred to as MPerS.We design multiple prompts for MLLMs to generate high-quality RS captions, enabling MLLMs to perceive RS scenes from diverse expert perspectives. DINOv3 is employed to extract dense visual representations of land-covers.We design a Dynamic MixExperts module that adaptively integrates the most effective textual semantics. Linguistic Query Guided Attention is constructed to utilize textual semantic information to guide visual features for precise segmentation. The MLLMs include LLaVA, ChatGPT, and Qwen. Our method achieves superior performance on three public semantic segmentation RS datasets.
Authors: David F. Ramirez, Tim L. Overman, Kristen Jaskie, Marv Kleine, Andreas Spanias
Abstract: Large language-vision models (LLVM), such as OpenAI's ChatGPT and GPT-4, have gained prominence as powerful tools for analyzing text and imagery. The merging of these data domains represents a significant paradigm shift with far-reaching implications for automatic target recognition (ATR). Recent transformer-based LLVM research has shown substantial improvements for geospatial perception tasks. Our study examines the application of LLVM to remote sensing image captioning and visual question-answering (VQA), with a specific focus on synthetic aperture radar (SAR) imagery. We examine newly published LLVM methods, including CLIP and LLaVA neural network transformer architectures. We have developed a work-in-progress SAR training and evaluation benchmark derived from the MSTAR Public Dataset. This has been extended to include descriptive text captions and question-answer pairs for VQA tasks. This challenge dataset is designed to push the boundaries of an LLVM in identifying nuanced ATR details in SAR imagery. Utilizing parameter-efficient fine-tuning, we train an LLVM method to identify fine-grained target qualities at 98% accuracy. We detail our data setup and experiments, addressing potential pitfalls that could lead to misleading conclusions. Accurately identifying and differentiating military vehicle types in SAR data poses a critical challenge, especially under complex environmental conditions. Mastering this target recognition skill may require a human analyst months of training and years of practice. This research represents a unique effort to apply LLVM to SAR applications, advancing machine-assisted remote sensing ATR for military and intelligence contexts.
Authors: Xuanyu Zhu, Yan Bai, Yang Shi, Yihang Lou, Yuanxing Zhang, Jing Jin, Yuan Zhou
Abstract: Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quality. However, existing methods universally extract features from only the last encoder layer, discarding the rich hierarchical information distributed across intermediate layers. We show that low-level visual details survive in the last layer merely as attenuated residuals after multiple layers of semantic abstraction, and that explicitly fusing multi-layer features can substantially recover this lost information. We propose DRoRAE (Depth-Routed Representation AutoEncoder), a lightweight fusion module that adaptively aggregates all encoder layers via energy-constrained routing and incremental correction, producing an enriched latent compatible with a frozen pretrained decoder. A three-phase decoupled training strategy first learns the fusion under the implicit distributional constraint of the frozen decoder, then fine-tunes the decoder to fully exploit the enriched representation. On ImageNet-256, DRoRAE reduces rFID from 0.57 to 0.29 and improves generation FID from 1.74 to 1.65 (with AutoGuidance), with gains also transferring to text-to-image synthesis. Furthermore, we uncover a log-linear scaling law ($R^2{=}0.86$) between fusion capacity and reconstruction quality, identifying \textit{representation richness} as a new, predictably scalable dimension for visual tokenizers analogous to vocabulary size in NLP.
Authors: Quanyun Wu, Kyle Gao, Wentao Sun, Zhengsen Xu, Hudson Sun, Linlin Xu, Yuhao Chen, David A. Clausi, Jonathan Li
Abstract: Accurate quantification of forest coverage and combustible biomass (fuel load) is critical for wildfire risk assessment and ecosystem management. However, traditional methods relying on airborne LiDAR or field surveys are cost-prohibitive and time-intensive, while satellite imagery often lacks the vertical resolution required for canopy volume analysis. This paper proposes a novel, automated pipeline for rapid forest inventory using virtual remote sensing data derived from Google Earth Studio (GES). Our approach first generates low-altitude orbital imagery and camera poses for a target region. For dense 3D reconstruction, we employ Pi-Long, developed within the VGGT-Long framework. This model serves as a scalable extension of the Pi-3 feed-forward Transformer architecture. To address the inherent scale ambiguity in monocular reconstruction, we introduce a metric recovery module that aligns the reconstructed trajectory with GES ground truth poses via Sim(3) Umeyama optimization. The metric-scale point cloud is then orthogonally projected into Bird's-Eye-View (BEV) height and density maps. Finally, we employ a watershed-based segmentation algorithm combined with height variance analysis to classify tree species (conifer vs. broadleaf), calculate Leaf Area Index (LAI), and estimate total fuel load. Experimental results demonstrate that this pipeline offers a scalable, cost-effective alternative to physical scanning, enabling near-real-time estimation of forest biomass with high geometric consistency.
Authors: Juyi Lin, Arash Akbari, Yumei He, Lin Zhao, Haichao Zhang, Arman Akbari, Xingchen Xu, Zoe Y. Lu, Enfu Nan, Hokin Deng, Edmund Yeh, Sarah Ostadabbas, Yun Fu, Jennifer Dy, Pu Zhao, Yanzhi Wang
Abstract: Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, evaluating whether generated videos actually follow these rules remains challenging. Existing physics-focused video benchmarks have made important progress, but they still face three key challenges, including the coarse evaluation frameworks that hide law-specific failures, response biases and fatigue that undermine the validity of annotation judgments, and automated evaluators that are insufficiently physics-aware or difficult to audit. To address those challenges, we introduce PhyGround, a criteria-grounded benchmark for evaluating physical reasoning in video generation. The benchmark contains 250 curated prompts, each augmented with an expected physical outcome, and a taxonomy of 13 physical laws across solid-body mechanics, fluid dynamics, and optics. Each law is operationalized through observable sub-questions to enable per-law diagnostics. We evaluate eight modern video generation models through a large-scale, quality-controlled human study, grounded on social science lab experiment design. A total of 459 annotators provided 5,796 complete annotations and over 37.4K fine-grained labels; after quality control, the retained annotations exhibited high split-half model-ranking correlations (Spearman's rho > 0.90). To support reproducible automated evaluation, we release PhyJudge-9B, an open physics-specialized VLM judge. PhyJudge-9B achieves substantially lower aggregate relative bias than Gemini-3.1-Pro (3.3% vs. 16.6%). We release prompts, human annotations, model checkpoints, and evaluation code on the project page https://phyground.github.io/.
Authors: Azmi Haider, Dan Rosenbaum
Abstract: The remarkable achievements of both generative models of 2D images and neural field representations for 3D scenes present a compelling opportunity to integrate the strengths of both approaches. In this work, we propose a methodology that combines a NeRF-based representation of 3D scenes with probabilistic modeling and reasoning using diffusion models. We view 3D reconstruction as a perception problem with inherent uncertainty that can thereby benefit from probabilistic inference methods. The core idea is to represent the 3D scene as a stochastic latent variable for which we can learn a prior and use it to perform posterior inference given a set of observations. We formulate posterior sampling using the score-based inference method of diffusion models in conjunction with a likelihood term computed from a reconstruction model that includes volumetric rendering. We train the model using a two-stage process: first we train the reconstruction model while auto-decoding the latent representations for a dataset of 3D scenes, and then we train the prior over the latents using a diffusion model. By using the model to generate samples from the posterior we demonstrate that various 3D reconstruction tasks can be performed, differing by the type of observation used as inputs. We showcase reconstruction from single-view, multi-view, noisy images, sparse pixels, and sparse depth data. These observations vary in the amount of information they provide for the scene and we show that our method can model the varying levels of inherent uncertainty associated with each task. Our experiments illustrate that this approach yields a comprehensive method capable of accurately predicting 3D structure from diverse types of observations.
Authors: Xiran Zhao, Jing Jin, Yan Bai, Zhongan Wang, Yifeng Sun, Yihang Lou, Xuanyu Zhu, Tao Feng, Yingna Wu
Abstract: Industrial anomaly detection is critical for manufacturing quality control, yet existing datasets mainly focus on static images or sparse views, which do not fully reflect continuous inspection processes in real industrial scenarios. We introduce MMVIAD (Multi-view Multi-task Video Industrial Anomaly Detection), to the best of our knowledge the first continuous multi-view video dataset for industrial anomaly detection and understanding, together with a benchmark for multi-task evaluation. MMVIAD contains object-centric 2-second inspection clips with approximately 120 degrees of camera motion, covering 48 object categories, 14 environments, and 6 structural anomaly types. It supports anomaly detection, defect classification, object classification, and anomaly visible-time localization. Systematic evaluations on MMVIAD show that current commercial and open-source video MLLMs remain far below human performance, especially for fine-grained defect recognition and temporal grounding. To improve transferable anomaly understanding, we further develop a two-stage post-training pipeline where PS-SFT (Perception-Structured Supervised Fine-Tuning) initializes perception-structured reasoning and VISTA-GRPO (Visibility-grounded Industrial Structured Temporal Anomaly Group Relative Policy Optimization) refines the model with semantic-gated defect reward and visibility-aware temporal reward, producing the final model VISTA. On MMVIAD-Unseen, VISTA improves the base model's average score across the four tasks from 45.0 to 57.5, surpassing GPT-5.4. Source code is available at https://github.com/Georgekeepmoving/MMVIAD.
Authors: Daniel Dratschuk, Paul Swoboda
Abstract: Optical Music Recognition (OMR), the task of transcribing sheet music into a structured textual representation, is currently bottlenecked by a lack of large-scale, annotated datasets of real scans. This forces models to rely on either few-shot transfer or synthetic training pipelines that remain overly simplistic. A secondary challenge is encoding non-uniqueness: in the popular Humdrum **kern format for transcribing music, multiple different text encodings can render into the same visual sheet music. This one-to-many mapping creates a harder learning task and introduces high uncertainty during decoding. We propose Transcoda, an OMR system built on (i) an advanced synthetic data generation pipeline, (ii) a normalization of the **kern encoding to enforce a unique normal form and (iii) grammar-based decoding to ensure the syntactic correctness of the output. This approach allows us to train a compact 59M-parameter model in just 6 hours on a single GPU that outperforms billion-parameter baselines. Transcoda achieves the best score among state of the art baselines on a newly curated benchmark of synthetically rendered scores at 18.46% OMR-NED (compared to 43.91% for the next-best system, Legato) and reduces the error rate on historical Polish scans to 63.97% OMR-NED (down from 80.16% for SMT++).
Authors: Qi Yang, Xiangyao Ma, Xiao Wang, Hao Wang, Rui Wang
Abstract: As global cross-lingual communication intensifies, language barriers in visually rich documents such as PDFs remain a practical bottleneck. Existing document translation pipelines face a tension between linguistic processing and layout preservation: text-oriented Computer-Assisted Translation (CAT) systems often discard structural metadata, while document parsers focus on extraction and do not support faithful re-rendering after translation. We introduce BabelDOC, an Intermediate Representation (IR)-based framework for layout-preserving PDF translation. BabelDOC decouples visual layout metadata from semantic content, enabling document-level translation operations such as terminology extraction, cross-page context handling, glossary-constrained generation, and formula placeholdering. The translated content is then re-anchored to the original layout through an adaptive typesetting engine. Experiments on a curated 200-page benchmark, together with human evaluation and multimodal LLM-as-a-judge evaluation, show that BabelDOC improves layout fidelity, visual aesthetics, and terminology consistency over representative baselines, while maintaining competitive translation precision. The open-source toolkit and its interactive downstream applications are publicly available and have attracted over 8.4K GitHub stars and 17 contributors at the time of writing. A demonstration video is also available.
Authors: Ruinan Jin, Beidi Zhao, Myeongkyun Kang, Qiong Zhang, Xiaoxiao Li
Abstract: Self-verification, re-invoking the same vision language model (VLM) in a fresh context to check its own generated answer, is increasingly used as a default safety layer for medical visual question answering (VQA). We argue that this practice is fundamentally unreliable. We introduce [METHOD NAME], a diagnostic framework for mapping the reliability boundary of medical VLM self-verification by decomposing verifier behavior into discrimination capability and agreement bias. Because the verifier and answer generator are capacity-coupled, the verifier can overly agree with the generator, creating a verification mirage: a regime with both high verifier error and high agreement bias, driven by false acceptance of incorrect answers. Evaluating six open-weight VLMs across five medical VQA datasets and seven medical tasks, we find that this boundary is strongly task-conditioned. Knowledge-intensive clinical tasks fall deepest into the mirage, simpler tasks are more resistant, and perceptual tasks lie in between. Verification also fails to provide an independent safety signal: logistic mixed-effects analysis shows that verifier error and agreement bias become more likely when the generator is wrong, while saliency analyses show that verifiers under-attend to image evidence relative to generators, a phenomenon we call the lazy verifier. Cross-verification reduces but does not eliminate the mirage. Moreover, when verification is reused in multi-turn actor-verifier loops, most initially wrong answers become locked in by false verification. Since our experiments use clean benchmarks, the observed reliability boundary likely underestimates failures in real clinical deployment.
Authors: Lingdong Kong, Ao Liang, Tianyi Yan, Hongsi Liu, Wesley Yang, Ziqi Huang, Xian Sun, Wei Yin, Jialong Zuo, Yixuan Hu, Dekai Zhu, Dongyue Lu, Youquan Liu, Guangfeng Jiang, Linfeng Li, Xiangtai Li, Long Zhuo, Lai Xing Ng, Benoit R. Cottereau, Changxin Gao, Liang Pan, Wei Tsang Ooi, Ziwei Liu
Abstract: Today's driving world models can generate remarkably realistic dash-cam videos, yet no single model excels universally. Some generate photorealistic textures but violate basic physics; others maintain geometric consistency but fail when subjected to closed-loop planning. This disconnect exposes a critical gap: the field evaluates how real generated worlds appear, but rarely whether they behave realistically. We introduce WorldLens, a unified benchmark that measures world-model fidelity across the full spectrum, from pixel quality and 4D geometry to closed-loop driving and human perceptual alignment, through five complementary aspects and 24 standardized dimensions. Our evaluation of six representative models reveals that no existing approach dominates across all axes: texture-rich models violate geometry, geometry-aware models lack behavioral fidelity, and even the strongest performers achieve only 2-3 out of 10 on human realism ratings. To bridge algorithmic metrics with human perception, we further contribute WorldLens-26K, a 26,808-entry human-annotated preference dataset pairing numerical scores with textual rationales, and WorldLens-Agent, a vision-language evaluator distilled from these judgments that enables scalable, explainable auto-assessment. Together, the benchmark, dataset, and agent form a unified ecosystem for assessing generated worlds not merely by visual appeal, but by physical and behavioral fidelity.
Authors: Wei Chow, Linfeng Li, Xian Sun, Lingdong Kong, Zefeng Li, Qi Xu, Hang Song, Tian Ye, Xian Wang, Jinbin Bai, Shilin Xu, Xiangtai Li, Junting Pan, Shaoteng Liu, Ran Zhou, Tianshu Yang, Songhua Liu
Abstract: Diffusion models dominate image editing, yet their global denoising mechanism entangles edited regions with surrounding context, causing modifications to propagate into areas that should remain intact. We propose a fundamentally different approach by leveraging Masked Generative Transformers (MGTs), whose localized token-prediction paradigm naturally confines changes to intended regions. We present EditMGT, an MGT-based editing framework that is the first of its kind. Our approach employs multi-layer attention consolidation to aggregate cross-attention maps into precise edit localization signals, and region-hold sampling to explicitly prevent token flipping in non-target areas. To support training, we construct CrispEdit-2M, a 2M-sample high-resolution (>1024) editing dataset spanning seven categories. With only 960M parameters, EditMGT achieves state-of-the-art image similarity on multiple benchmarks while delivering 6x faster editing, demonstrating that MGTs offer a compelling alternative to diffusion-based editing.
Authors: Anna C. Doris, Jacob Thomas Sony, Ghadi Nehme, Era Syla, Amin Heyrani Nobari, Faez Ahmed
Abstract: Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existing evaluations are fragmented across datasets, modalities, and metrics. We introduce CADBench, a unified benchmark for multimodal CAD program generation. CADBench contains 18,000 evaluation samples spanning six benchmark families derived from DeepCAD, Fusion 360, ABC, MCB, and Objaverse; five input modalities including clean meshes, noisy meshes, single-view renders, photorealistic renders, and multi-view renders; and six metrics covering geometric fidelity, executability, and program compactness. STEP-based families are stratified by B-rep face count and all families are diversity-sampled to support controlled analysis across complexity and object variation. We benchmark eleven CAD-specialized and general-purpose vision-language systems, generating more than 1.4 million CAD programs. Under idealized inputs, specialized mesh-to-CAD models substantially outperform code-generating VLMs, which remain far from reliable CAD program reconstruction. CADBench further reveals three recurring failure modes: reconstruction quality degrades with geometric complexity, CAD-specialized models can be brittle under modality shift, and model rankings change across metrics. Together, these results position CADBench as a diagnostic testbed for measuring progress in editable 3D reconstruction and multimodal CAD understanding. The benchmark is publicly available at https://huggingface.co/datasets/DeCoDELab/CADBench.
Authors: Feifan Song, Yuntian Bo, Haofeng Zhang
Abstract: Cross-domain few-shot medical image segmentation (CD-FSMIS) requires a model to generalise simultaneously to novel anatomical categories and unseen imaging domains from only a handful of annotated examples. Existing prototypical approaches inevitably entangle anatomical structure with domain-specific appearance variations, and thus lack a stable reference for reliable matching under domain shift. We observe that the geometric structure of human anatomy constitutes a reliable, domain-transferable prior that has been overlooked. Building on this insight, we propose GeoProto, a geometry-aware CD-FSMIS framework that enriches prototypical matching with explicit structural priors. The core component, Geometry-Aware Prototype Enrichment (GAPE), augments each local appearance prototype with a learned geometric offset encoding its ordinal position within the organ's interior topology. This offset is derived from an auxiliary Ordinal Shape Branch (OSB) trained under an ordinally consistent objective that enforces monotonic variation of geometric embeddings across interior strata, requiring no annotation beyond standard segmentation masks. Extensive experiments across seven datasets spanning three evaluation settings (cross-modality, cross-sequence, and cross-context) demonstrate that GeoProto achieves state-of-the-art performance.
Authors: Chang Liu, Haoning Wu, Weidi Xie
Abstract: Open-world object counting remains brittle: despite rapid advances in vision-language models (VLMs), reliably counting the objects a user intends is far from solved. We argue that a central reason is that counting granularity is left implicit; users may refer to a specific identity, an attribute, an instance type, a category, or an abstract concept, yet most methods treat "what to count" as a single, category-level matching problem. In this work, we redefine open-world counting as multi-grained counting, where visual exemplars specify target appearance and fine-grained text, with optional negative prompts, specifies the intended semantic granularity across five explicit levels. Making granularity explicit, however, exposes a critical data bottleneck: existing counting datasets lack the multi-category scenes, controlled distractors, and instance-level annotations needed to verify fine-grained prompt semantics. To address this, we propose the first fully automatic data-scaling pipeline that integrates controllable 3D synthesis with consistent image editing and VLM-based filtering, and use it to construct KubriCount, the largest and most comprehensively annotated counting dataset to date, supporting both training and multi-grained evaluation. Systematic benchmarking reveals that both multimodal large language models and specialist counting models exhibit severe prompt-following failures under fine-grained distinctions. Motivated by these findings, we train HieraCount, a multi-grained counting model that jointly leverages text and visual exemplars as complementary target specifications. HieraCount substantially improves multi-grained counting accuracy and generalizes robustly to challenging real-world scenarios. The project page is available here: https://verg-avesta.github.io/KubriCount/.
Authors: Moritz Stammel, Fabio De Sousa Ribeiro, Raghav Mehta, M\'elanie Roschewitz, Ben Glocker
Abstract: Deep learning models in medical imaging often fail when deployed in new clinical environments due to distribution shifts in demographics, scanner hardware, or acquisition protocols. A central challenge is underspecification, where models with similar validation performance exhibit divergent real-world failure modes. Although stress testing has emerged as a tool to assess this, current methods typically rely on simple, uninformed perturbations (e.g., brightness or contrast changes), which fail to capture clinically realistic variation and can overestimate robustness. In this work, we introduce a counterfactual stress testing framework based on causal generative models that create realistic "what if" images by intervening on attributes such as scanner type and patient sex while preserving anatomical identity, enabling controlled and semantically meaningful evaluation under targeted distribution shifts. Across two imaging modalities (chest X-ray and mammography), three model architectures, and multiple shift scenarios, we show that counterfactual stress tests provide a substantially more accurate proxy for real out-of-distribution performance than classical perturbations, capturing the direction and relative magnitude of performance changes as well as model ranking. These results suggest that causal generative models can serve as practical simulators for robustness assessment, offering a more reliable basis for evaluating medical AI systems prior to deployment.
Authors: Wenxuan Song, Han Zhao, Fuhao Li, Ziyang Zhou, Xi Wang, Jing Lyu, Pengxiang Ding, Yan Wang, Donglin Wang, Haoang Li
Abstract: This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods with auxiliary training objectives can improve performance and reduce the number of convergence steps. However, they typically incur significant computational overhead due to the additional losses from auxiliary objectives. To simultaneously achieve the enhanced capabilities of auxiliary training with the simplicity of standard SFT, we decouple the two objectives of auxiliary-objective SFT within the parameter space, namely, enhancing general capabilities and fitting task-specific action distributions. To deliver the goal, we only need to train the model to converge on a small-scale task set using two distinct training strategies, resulting in two finetuned models. The parameters' difference between the two models can then be interpreted as capability vectors provided by auxiliary objectives. These vectors are then merged with pretrained parameters to form a capability-enhanced meta model. Moreover, when standard SFT is augmented with a lightweight orthogonal regularization loss, the merged model attains performance comparable to auxiliary finetuned baselines with reduced computational overhead. Internal and external experiments demonstrate that our capability vectors (1) are effective and versatile across diverse models, (2) can generalize to novel environments and embodiments out of the box.
Authors: Md. Sultan Al Rayhan
Abstract: Recognition of handwritten Bangla compound characters remains a challenging problem due to complex character structures, large intra-class variation, and limited availability of high-quality annotated data. Existing Bangla handwritten character recognition systems often struggle to generalize across diverse writing styles, particularly for compound characters containing intricate ligatures and diacritical variations. In this work, we propose a confidence-guided diffusion augmentation framework for low-resolution Bangla compound character recognition. Our framework combines class-conditional diffusion modeling with classifier guidance to synthesize high-quality handwritten compound character samples. To further improve generation quality, we introduce Squeeze-and-Excitation enhanced residual blocks within the diffusion model's U-Net backbone. We additionally propose a confidence-based filtering mechanism where pre-trained classifiers act as quality gates to retain only highly class-consistent synthetic samples. The filtered synthetic images are fused with the original training data and used to retrain multiple classification architectures. Experiments conducted on the AIBangla compound character dataset demonstrate consistent performance improvements across ResNet50, DenseNet121, VGG16, and Vision Transformer architectures. Our best-performing model achieves 89.2\% classification accuracy, surpassing the previously published AIBangla benchmark by a substantial margin. The results demonstrate that quality-aware diffusion augmentation can effectively enhance handwritten character recognition performance in low-resource script domains.
Authors: Dong-Yang Li, Wang Zhao, Yuxin Chen, Wenbo Hu, Meng-Hao Guo, Fang-Lue Zhang, Ying Shan, Shi-Min Hu
Abstract: Recent advances in 3D generative models have rapidly improved image-to-3D synthesis quality, enabling higher-resolution geometry and more realistic appearance. Yet fidelity, which measures pixel-level faithfulness of the generated 3D asset to the input image, still remains a central bottleneck. We argue this stems from an implicit 2D-3D correspondence issue: most 3D-native generators synthesize shape in canonical space and inject image cues via attention, leaving pixel-to-3D associations ambiguous. To tackle this issue, we draw inspiration from 3D reconstruction and propose Pixal3D, a pixel-aligned 3D generation paradigm for high-fidelity 3D asset creation from images. Instead of generating in a canonical pose, Pixal3D directly generates 3D in a pixel-aligned way, consistent with the input view. To enable this, we introduce a pixel back-projection conditioning scheme that explicitly lifts multi-scale image features into a 3D feature volume, establishing direct pixel-to-3D correspondence without ambiguity. We show that Pixal3D is not only scalable and capable of producing high-quality 3D assets, but also substantially improves fidelity, approaching the fidelity level of reconstruction. Furthermore, Pixal3D naturally extends to multi-view generation by aggregating back-projected feature volumes across views. Finally, we show pixel-aligned generation benefits scene synthesis, and present a modular pipeline that produces high-fidelity, object-separated 3D scenes from images. Pixal3D for the first time demonstrates 3D-native pixel-aligned generation at scale, and provides a new inspiring way towards high-fidelity 3D generation of object or scene from single or multi-view images. Project page: https://ldyang694.github.io/projects/pixal3d/
Authors: Zihui Xue, Ami Baid, Sangho Kim, Mi Luo, Kristen Grauman
Abstract: As wearable devices like smart glasses integrate Large Multimodal Models (LMMs) into the continuous first-person visual streams of individual users, the evolution of these models into true personal assistants hinges on visual personalization: the ability to reason over visual information unique to the wearer. We formalize this capability as Personal Visual Context Learning (Personal VCL), the prompt-time capability of using user-specific visual context to resolve personalized queries. To systematically evaluate this, we present Personal-VCL-Bench, a comprehensive benchmark capturing the personal visual world across persons, objects, and behaviors. Our analysis of frontier LMMs identifies a profound context utilization gap, revealing that the mechanisms for leveraging visual evidence, as well as aggregating multiple visual observations, remain critically understudied. Motivated by these findings, we propose the Agentic Context Bank, a strong inference-time baseline that structures a user's visual context into a self-refining memory bank and employs query-adaptive evidence selection. Our baseline approach consistently improves over standard context prompting regimes across tasks and evaluated backbones, demonstrating a practical path towards future personalized LMMs.
Authors: Haoyuan Sun, Jing Wang, Yuxin Song, Yu Lu, Bo Fang, Yifu Luo, Jun Yin, Pengyu Zeng, Miao Zhang, Tiantian Zhang, Xueqian Wang, Shijian Lu
Abstract: Recently, post-training methods based on reinforcement learning, with a particular focus on Group Relative Policy Optimization (GRPO), have emerged as the robust paradigm for further advancement of text-to-image (T2I) models. However, these methods are often prone to reward hacking, wherein models exploit biases in imperfect reward functions rather than yielding genuine performance gains. In this work, we identify that normalization could lead to miscalibration and directly removing the prompt-level standard deviation term yields an optimal policy ascent direction that is linear in the advantage but still limits the separation of genuine signals from noise. To mitigate the above issues, we propose Super-Linear Advantage Shaping (SLAS) by revisiting the functional update from an information geometry perspective. By extending the Fisher-Rao information metric with advantage-dependent weighting, SLAS introduces a non-linear geometric structure that reshapes the local policy space. This design relaxes constraints along high-advantage directions to amplify informative updates, while tightening those in low-advantage regions to suppress illusory gradients. In addition, batch-level normalization is applied to stabilize training under varying reward scales. Extensive evaluations demonstrate that SLAS consistently surpasses the DanceGRPO baseline across multiple backbones and benchmarks. In particular, it yields faster training dynamics, improved out-of-domain performance on GenEval and UniGenBench++, and enhanced robustness to model scaling, while mitigating reward hacking and preserving semantic and compositional fidelity in generations.
Authors: Yaw Osei Adjei
Abstract: Accurate predictions of smallholder maize yields across national boundaries are critical for food security planning in sub-Saharan Africa, yet most published benchmarks report within-country performance that overstates true generalisability. This paper evaluates whether geospatial foundation model embeddings, specifically Prithvi-EO-1.0-100M and ViT-Base, outperform traditional Sentinel-2 spectral features under a Leave-One-Country-Out cross-validation scheme on 6,404 maize field observations from five African countries. The results show a clear generalisability gap: within-country random cross-validation yields moderate R^2 values, but all feature sets perform poorly under cross-country testing, with universally negative R^2. Frozen Prithvi-EO embeddings provide no meaningful advantage over engineered spectral features for cross-country prediction in this setting. The paper argues that the main limitation is a shift in yield distribution between countries rather than representation quality and releases a reproducible negative benchmark for future work.
Authors: Wang Xiaoyu, Phong Nguyen, Chen Zhao
Abstract: Wepresent Alice v1, a 14-billion parameter open-source video generation model that achieves state-of-the-art quality through consistency distillation with score regularization (rCM). Contrary to conventional distillation-which trades quality for speed-we demonstrate that rCM-based distillation can exceed teacher model quality. We attribute this to three mechanisms: (1) the score regularization term acts as a mode-seeking objective that concentrates probability mass on high-quality outputs rather than covering the full teacher distribution, (2) our targeted synthetic data pipeline with hard example mining provides training signal specifically for failure modes (physics, hands, faces) that the teacher handles inconsistently, and (3) consistency enforcement acts as implicit regularization, eliminating "lucky path" dependence on specific noise samples. Alice v1 generates 5-second 720p videos at 24fps in 4 denoising steps (~8 seconds on H100), a 7x speedup over the 50-step teacher while improving VBench score from 84.0 (Wan2.2) to 91.2. This surpasses both the teacher and closed-source systems including Veo3 (~90) and Sora2 (~88) on automated benchmarks, with competitive results in human preference studies. We release all model weights, training code, synthetic data pipelines, and evaluation scripts to advance open research in video generation.
Authors: Peng Liao, Shangsong Liang, Lin Chen, Peijia Zheng
Abstract: Inertial Measurement Unit (IMU)-based Human Activity Recognition (HAR) aims to interpret and classify user behaviors from temporal motion signals. Recently, deep learning frameworks have advanced this task by learning and extracting discriminative spatiotemporal representations, significantly improving recognition performance. However, IMU-based HAR still faces several critical challenges, particularly limited training samples and static knowledge utilization, both of which severely hinder its large-scale deployment. In this paper, we introduce MoRA, the first Retrieval-Augmented Module specifically designed for motion series. It can be flexibly integrated into any existing HAR model, enhancing recognition performance while maintaining inference efficiency. To address issues such as information redundancy in retrieval results and rigid fusion strategies, we propose an uncertainty-adaptive fusion unit within MoRA. This unit leverages previous physical knowledge from IMU signals to dynamically adjust the fusion strategy between original outputs and retrieved information, enabling more robust recognition. Extensive experiments on ten real-world datasets demonstrate that MoRA significantly improves the performance of existing IMU-based HAR models, consistently delivering stable and effective gains. The source code of MoRA is available at: https://github.com/liavonpenn/mora.
Authors: Yanbiao Ma, Fei Luo, Linfeng Zhang, Chuangxin Zhao, Mingxuan Wang, Yinan Wu, Zhe Qian, Yang Lu, Long Chen, Zhao Cao, Xiaoshuai Hao, Ji-Rong Wen, Jungong Han
Abstract: Reasoning in large language models is predominantly evaluated through labeled benchmarks, conflating task performance with the quality of internal inference. Here we study reasoning as an intrinsic dynamical process by examining the evolution of internal representations during inference. We find that inference-time dynamics consistently self-organize into low-dimensional manifolds embedded within high-dimensional representation spaces. we find that such geometric compression, although pervasive, is not sufficient for stable or reliable reasoning. Instead, effective reasoning dynamics emerge within a constrained structural regime characterized by three conditions: adequate representational expressivity, spontaneous manifold compression, and preservation of non-degenerate information volume within the compressed subspace. Models outside this regime exhibit characteristic pathological inference dynamics. Based on these insights, we introduce a unified, label-free diagnostic computed solely from internal dynamics. These findings suggest that reasoning in LLMs is fundamentally governed by geometric and informational constraints, offering a complementary framework to benchmark-centric assessment.
Authors: Fang Wu, Haokai Zhao, Da Xing, Hanqun Cao, Tinson Xu, Yanchao Li, Xiangru Tang, Zehong Wang, Aaron Tu, Kuan Pang, Hanchen Wang, Hongbin Lin, Zeqi Zhou, Yinxi Li, Peng Xia, Li Erran Li, Molei Tao, Jure Leskovec, Aditya Joshi, Yejin Choi
Abstract: Diffusion models have achieved remarkable success across a wide range of generative tasks, yet their training paradigm largely treats injected noise as uniformly informative. In this work, we challenge this assumption and introduce NoiseRater, a meta-learning framework for instance-level noise valuation in diffusion model training. We propose a parametric noise rater that assigns importance scores to individual noise realizations conditioned on data and timestep, enabling adaptive reweighting of the training objective. The rater is trained via bilevel optimization to improve downstream validation performance after inner-loop diffusion updates. To enable efficient deployment, we further design a decoupled two-stage pipeline that transitions from soft weighting during meta-training to hard noise selection during standard training. Extensive experiments on FFHQ and ImageNet demonstrate that not all noise samples contribute equally, and that prioritizing informative noise improves both training efficiency and generation quality. Our results establish noise valuation as a complementary and previously underexplored axis for improving diffusion model training. Our code is available at: https://anonymous.4open.science/r/NoiseRater-DEB116.
Authors: Jingze Ge, Xue Geng, Yun Liu, Wanqi Dong, Wang Zhe Mark, Min Wu, Ngai-Man Cheung, Bharadwaj Veeravalli, Xulei Yang
Abstract: To mitigate the memory constraints associated with fine-tuning large pre-trained models, existing parameter-efficient fine-tuning (PEFT) methods, such as LoRA, rely on low-rank updates. However, such updates fail to fully capture the rank characteristics of the weight modifications observed in full-parameter fine-tuning, resulting in a performance gap. Furthermore, LoRA and other existing PEFT methods still require substantial memory to store the full set of frozen weights, limiting their efficiency in resource-constrained settings. To addres these limitations, we introduce Cumulative Energy-Retaining Subspace Adaptation (CERSA), a novel fine-tuning paradigm that leverages singular value decomposition (SVD) to retain only the principal components responsible for 90% to 95% of the spectral energy. By fine-tuning low-rank representations derived from this principal subspace, CERSA significantly reduces memory consumption. We conduct extensive evaluations of CERSA across models of varying scales and domains, including image recognition, text-to-image generation, and natural language understanding. Empirical results demonstrate that CERSA consistently outperforms state-of-the-art PEFT methods while achieving substantially lower memory requirements. The code will be publicly released.
Authors: Logan Mann, Ajit Saravanan, Ishan Dave, Shikhar Shiromani, Saadullah Ismail, Yi Xia, Emily Huang
Abstract: A pervasive intuition holds that vision-language models (VLMs) are most trustworthy when their attention maps look sharp: concentrated attention on the queried region should imply a confident, calibrated answer. We test this Attention-Confidence Assumption directly. We instrument three open-weight VLM families (LLaVA-1.5, PaliGemma, Qwen2-VL; 3-7B parameters) with a unified mechanistic pipeline -- the VLM Reliability Probe (VRP) -- that compares attention structure, generation dynamics, and hidden-state geometry against a single correctness label. Three results emerge. (i) Attention structure is a near-zero predictor of correctness (R_pb(C_k,y)=0.001, 95% CI [-0.034,0.036]; R_pb(H_s,y)=-0.012, [-0.047,0.024] on a pooled n=3,090 split), even though attention remains causally necessary for feature extraction (top-30% patch masking drops accuracy by 8.2-11.3 pp, p<0.001). (ii) Reliability becomes legible later in the computation: a single hidden-state linear probe reaches AUROC>0.95 on POPE for two of three families, and self-consistency at K=10 is the strongest behavioral predictor we measure at 10x inference cost (R_pb=0.43). (iii) Causal neuron-level ablations expose a sharp architectural split with direct monitor-design implications: late-fusion LLaVA concentrates reliability in a fragile late bottleneck (-8.3 pp object-identification accuracy after top-5 probe-neuron ablation), whereas early-fusion PaliGemma and Qwen2-VL distribute it widely and absorb destruction of ~50% of their peak-layer hidden dimension with <=1 pp degradation. The takeaway is narrow but consequential: in 3-7B VLMs, reliability is read more reliably off hidden-state geometry, layer-wise margin formation, and sparse late-layer circuits than off attention-map sharpness.
Authors: Sparsh Tiwari, Bettina Finzel, Gesina Schwalbe
Abstract: Neurosymbolic systems promise to combine deep neural network's (DNN) processing of raw sensor inputs with few-shot performance of symbolic artificial intelligence. Two-stage approaches explicitly decouple DNN based perception from subsequent rule based reasoning. This avoids optimization and interpretability issues of end to end differentiable approaches, but requires costly labels for the perception output. This paper introduces an efficient weak supervision scheme for the perception stage to ground its output symbols for logical induction in object-centric reasoning tasks. It combines a slot-based architecture for object-centricity with a Variational Autoencoder (VAE) for self-supervision, competing with concept guidance on latent dimensions for human interpretable grounding. The resulting predictions are translated into symbolic background knowledge for reasoning frameworks, such as Inductive Logic Programming (ILP), Decision Trees, and Bayesian Networks. Our extensive empirical evaluation on synthetic and real world datasets shows that our approach can discover complex, abstract rules for object centric reasoning whilst reducing supervision to as little as 1% of labels, and being robust even under substantial domain shift. Notably, at 1% supervision it even outperforms state of the art foundation model baselines in domain generalization
Authors: Adam Szokalski, Mateusz Modrzejewski
Abstract: This paper proposes latent visualization by optimization (LVO), a mechanistic interpretability technique that extends feature visualization by optimization - originally developed for convolutional neural networks - to latent diffusion models. LVO employs sparse autoencoders (SAEs) to disentangle polysemantic layer representations into monosemantic features. Key contributions include latent-space optimization, time-step activity analysis, schedule-matched noise injection, prior initialization through feature steering, and suitable regularization strategies. We demonstrate the method on Stable Diffusion 1.5 fine-tuned on the Style50 dataset, showing that SAE features produce clear visualizations of recognizable concepts - including diagonal compositions, human figures, roses, cables, and waterfall foam - that correlate with dataset examples, while the baseline without disentanglement produces less coherent results. We further show that regularization techniques from pixel-space feature visualization transfer to the latent domain, though they require different configurations for the raw-layer and SAE variants. Compared to dataset examples and steering, LVO provides complementary insights by directly revealing what activates a feature rather than its downstream effects.
Authors: Andrei Lazarev, Dmitrii Sedov, Alexander Galkin
Abstract: The automated extraction of data from scientific charts is a critical task for large-scale literature analysis. While multimodal Large Language Models (LLMs) show promise, their accuracy on non-standardized charts remains a challenge. This raises a key research question: what is the most effective strategy to improve model performance (high-level semantic priming) or low-level spatial priming? This paper presents a comparative investigation into these two distinct strategies. We describe our exploratory experiments with semantic methods, such as a two-stage metadata-first framework and Chain-of-Thought, which failed to produce a statistically significant improvement. In contrast, we present a simple but highly effective spatial priming method: overlaying a coordinate grid onto the chart image before analysis. Our quantitative experiment on a synthetic dataset demonstrates that this grid-based approach provides a statistically significant reduction in data extraction error (SMAPE reduced from 25.5% to 19.5%, p < 0.05) compared to a baseline. We conclude that for the current generation of multimodal models, providing explicit spatial context is a more effective and reliable strategy than high-level semantic guidance for this class of tasks.
Authors: Jungwoo Kim, Jun-Hyuk Kim, Jong-Seok Lee
Abstract: Recent advances in learned image compression (LIC) have enabled practical deployments, spurring active research into image compression for machines and progressive coding schemes. However, their integration remains under-explored: prior works on progressive machine codec predominantly target sample-level difficulty adaptation (i.e., easy-to-hard), without considering semantic-level scalability. In this work, we introduce a semantic hierarchy-aware progressive codec that enables semantic scalability (i.e., coarse-to-fine) from a single bitstream. We first systematically categorize ImageNet-1K classes into CLIP embedding-based semantic hierarchies. Based on a channel-wise autoregressive framework, we decompose latent representations into hierarchically ordered channel blocks, each explicitly optimized for a corresponding semantic hierarchy. Extensive experiments demonstrate that our approach substantially improves coarse-level recognition at low bitrates while maintaining fine-grained accuracy at higher bitrates. By reframing progressive transmission through the lens of semantic scalability, our work provides an efficient and interpretable solution for task-adaptive image coding, outperforming existing progressive codecs under hierarchical evaluation.
Authors: Ray Sheombarsing, Max van Riel, David Heesterbeek, Nico van den Berg, Alessandro Sbrizzi
Abstract: Conventional MRI reconstruction methods treat images and coil sensitivities as discrete objects, leading to high memory demands and limited structural awareness that hamper effective regularization. These limitations hinder accurate reconstruction in highly undersampled scenarios, such as dynamic 3D cardiac magnetic resonance (CMR). We introduce a discretization-free, memory-efficient, model-based framework for dynamic 2D and 3D MRI reconstruction from highly undersampled data. We represent magnetization and coil sensitivities as continuous objects -- differentiable functions -- using tensor products of univariate neural fields. This tensor product structure enables scalable optimization in high-dimensional spatiotemporal settings. Our method outperforms state-of-the-art model-based reconstructions in dynamic 2D and 3D MR settings, preserving structure and motion even under aggressive undersampling (e.g., acceleration factor 16).
Authors: Lennard M. van Karnenbeek, Hilde G. A. van der Pol, Mark Wijkhuizen, Eva Poelman, Caroline A. Drukker, Theo Ruers, Freija Geldof, Behdad Dashtbozorg
Abstract: Purpose: We aim to enhance the image quality of point-of-care ultrasound (POCUS) devices using deep learning and a novel paired dataset of POCUS and high-end ultrasound images. Approach: We collected the first accurately paired dataset using a custom-built automated gantry system of low-end POCUS and high-end ultrasound images. A conditional generative adversarial network (cGAN) was utilized based on the pix2pix architecture, with a U-Net generator that incorporates both L1 and structural similarity index (SSIM) losses to improve perceptual quality. Pretraining on a simulation dataset further boosts performance. Evaluation was performed on 1064 paired ex vivo tissue and phantom ultrasound image sets. Results: Our approach improves the SSIM from 0.29 to 0.54 and PSNR from 19.16 dB to 22.41 dB. No-reference metrics also indicate substantial enhancement, with the Natural Image Quality Evaluator (NIQE) and Perception-based Image Quality Evaluator (PIQE) scores dropping from 7.95 to 4.44 and 31.12 to 19.99, respectively. Conclusions: This work presents the first publicly available accurately paired dataset of low-end POCUS to high end ultrasound images. Additionally, our results demonstrate the potential of the proposed framework to overcome hardware limitations of handheld POCUS, enhancing its diagnostic value in low-resource and point-of-care settings. The POCUS-IQ Dataset is publicly available at https://github.com/NKI-MedTech-AI/POCUS-IQ.
Authors: Xi Wang, Cheng Deng
Abstract: Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement for preserving diverse forms of previous knowledge conflicts with the storage limitations inherent to CL. In this paper, we systematically analyze existing model merging methods under the constraints of CL. We find that current methods prioritize global alignment, which often leads to the accumulation and amplification of task-specific errors within the continuous data stream; and the vanishing gradients at the onset of subsequent tasks frequently cause optimization to stagnate. These leave the merged model in a suboptimal state at the beginning of the next training phase. To address these challenges, we propose Trajectory Regularized Merging (TRM), a framework that reformulates the merging phase as an optimization process within an augmented trajectory subspace. Our framework integrates three synergistic objectives including task alignment, prediction consistency, and gradient responsiveness to concurrently preserve merged model's historical stability and re-activate optimization dynamics. Extensive experimental results demonstrate that our method achieves state-of-the-art performance across multiple benchmarks.
Authors: Zehua Jiang, Fenghao Zhu, Xinquan Wang, Chongwen Huang, Zhaoyang Zhang
Abstract: Generative models based on flow matching have emerged as a powerful paradigm for inverse problems, offering straighter trajectories and faster sampling compared to diffusion models. However, existing approaches often necessitate differentiating through unrolled paths, leading to numerical instability and prohibitive computational overhead. To address this, we propose P-Flow, a framework that stabilizes the reconstruction process by leveraging a proxy gradient to update the source point. This approach effectively circumvents the numerical instability and memory overhead of long-chain differentiation. To ensure consistency with the prior distribution, we employ a Gaussian spherical projection motivated by the concentration of measure phenomenon in high-dimensional spaces. We further provide a theoretical analysis for P-Flow based on Bayesian theory and Lipschitz continuity. Experiments across diverse restoration tasks demonstrate that P-Flow delivers competitive performance, especially under extreme degradations such as severely ill-posed conditions and high measurement noise.
Authors: Rania Briq, Michael Kamp, Ohad Fried, Sarel Cohen, Stefan Kesselheim
Abstract: In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capacity shrinkage. We characterize this stability by their tendency to generate similar outputs under identical noise seeds. We provide a perspective relating this phenomenon to flow matching theory, which indicates that this stability is inherent to the FM objective. We further exploit this stability to derive practical algorithms for more efficient training and inference. Concretely, first, we show that by training LFM models on significantly reduced datasets, the performance does not degrade perceptually or quantitatively. This yields multiple advantages, such as reducing training time by converging faster under limited compute budget, and alleviating annotation effort when training conditional models. Second, LFM stability under architectural shrinkage gives rise to a two-model coarse-to-fine approach, one using a light-weight architecture for the first phase of the FM trajectory, and one with higher capacity for the second, thereby reducing the inference cost substantially. To determine which samples are informative, we introduce three sample-scoring criteria and evaluate them under standard metrics for generative models. Our results are thoroughly evaluated on multiple datasets, demonstrating the practical advantage of this stability, including data saving and a more than two-fold inference speedup while generating comparable outputs.
Authors: Dongdong Wang, Deepak Balakrishnan, Ravi Srinivasan, Shenhao Wang
Abstract: This work investigates the use of large language models (LLMs) for tasks in smart cities. The core idea is to leverage remote sensing imagery to characterize the built environment, including design suggestions, constructability assessment, landuse patterns, and risk identification. We examine remote sensing imagery at multiple spatial scales as inputs for multimodal language modeling and evaluate their effects on built-environment-related reasoning. In addition, we compare state-of-the-art LLMs, including InternVL and Qwen, in terms of accuracy and reliability when generating built environment recommendations. The results demonstrate the potential of integrating remote sensing imagery with large language models to assist smart cities and decision-making.
Authors: Daniel Wesego, Pedram Rooshenas
Abstract: Adversarial purification with diffusion models seeks to project adversarial examples back toward the data manifold, but balancing semantic preservation and robustness against adaptive attacks remains challenging. Recent work shows that standard diffusion purification can fail under adaptive evaluation, while test-time score-based optimization is more resilient. Existing optimization defenses, however, typically rely on a single diffusion noise regime or treat timesteps uniformly, overlooking the distinct roles of coarse and fine denoising scales. We propose Temporal Adversarial Rectification Optimization (TARO), an inference-time purification method that builds a temporally guided score prior from multiple denoising views along the diffusion trajectory. TARO forms a coarse-to-fine residual target: high-noise experts provide globally smoothed structure with reduced adversarial sensitivity, while low-noise experts restore image-specific, class-relevant details. A guidance strength controls this temporal correction, allowing TARO to balance robust global rectification with semantic preservation. Empirically, TARO improves robust accuracy across datasets and adaptive threat models in a zero-shot setting, while remaining compatible with complementary adversarial-likelihood objectives for further robustness gains.
Authors: Andreas Maier, Md Hasan, Paulina Conrad, Paula Andrea Perez-Toro
Abstract: We describe an approach for estimating the statistical risk of deep networks that contain a mix of learned and known operators. Building on the maximal training error bounds previously established for known operator learning, we derive a deep risk estimator that connects the expected error of a layered network to the size of the training sample. The estimator decomposes the total risk into a sum over learned layers; every known operator contributes zero to this sum, while every learned layer adds an approximation term inspired by Barron's classic work and an estimation term that decreases with the number of training samples. We are able to show that the bound shrinks whenever a learned layer is replaced by a known operator and that the corresponding sample requirement scales with the number of trainable parameters of the layer that is replaced. As an application, we use computed tomography as an example and compare an operator-aware filtered backprojection network with a fully connected substitute that collapses the entire reconstruction pipeline into a single learned dense matrix. The predicted parameter ratio coincides with the structural sparsity that the analytic decomposition into a circulant filter and a sparse backprojection exposes. We confirm the predicted scaling on CPU at small image scale and on GPU at medium image scale, all on the same scaling law. Beyond CT reconstruction, the estimator applies to physics-informed neural networks that hardcode a known physical operation in its architecture, and we expect the result to be of interest for a broad community working on operator-aware deep learning. Calibrating the per-layer constants on each sweep yields a bound that tracks the empirical test MSE within a factor of two at every training-set size, so the estimator can be inverted to predict how many training samples are required to reach a target error.
Authors: Jake Lance, Larry Kieu
Abstract: The feedback alignment (FA) algorithm offers a biologically plausible alternative to backpropagation (BP) for training neural networks yet notably fails to scale to convolutional architectures. Modifications have been proposed to address this limitation, but at questionable cost to biological plausibility. In this paper, we evaluate five learning algorithms including modified FA and standard BP, applied to the same convolutional architecture with the CIFAR-10 dataset. We provide a tripartite comparative analysis focusing on biological plausibility, interpretability, and computational complexity. Our results indicate that modified FA algorithms converge on internal representations that are structurally similar to those produced by backpropagation. In particular, it appears the functional success of modified FA algorithms may be rooted in their ability to mimic the representational geometry of backpropagation, converging on similar representations despite relying on fundamentally different weight update mechanisms.
Authors: Jinxiao Zhang, Runmin Dong, Xiyong Wu, Xihan Huang, Shenggan Cheng, Yunkai Yang, Zheng Zhou, Yunpu Xu, Zhaoyang Luo, Miao Yang, Fan Wei, Mengxuan Chen, Yang You, Juepeng Zheng, Weijia Li, Yutong Lu, Haohuan Fu
Abstract: Earth observation is becoming one of the largest data-producing activities in science, yet current pipelines still treat compression as a storage and transmission tool rather than a new way to use data. We present a generative compression framework that learns from historical Earth observation archives and enables on-demand 100x to 10,000x data reduction across downstream tasks. Unlike general visual data, Earth observation repeatedly measures the same evolving planet, making historical-prior learning feasible for extreme compression. To realize this paradigm, we train large generative compression models at exascale on the LineShine Armv9 CPU supercomputer, with co-optimization across model design, kernels, memory hierarchy, runtime, and parallelism. Our implementation sustains 1.54 EFLOP/s and peaks at 2.16 EFLOP/s in end-to-end training. This work shows that historical-prior generative compression can turn Earth observation data into an active, task-adaptive foundation for acquisition, delivery, storage, and scientific use.
Authors: Yuxuan Zhang, Penghui Du, Bo Li, Cong Wei, Junwen Miao, Huaisong Zhang, Songcheng Cai, Yubo Wang, Dongfu Jiang, Yuyu Zhang, Ping Nie, Wenhu Chen, Changqian Yu, Kelsey R. Allen
Abstract: Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-scale preference annotation and additional model training. This creates a data-efficiency gap: humans can often infer the target evaluation criteria from only a few examples, while models are usually trained on hundreds of thousands of comparisons. We present RewardHarness, a self-evolving agentic reward framework that reframes reward modeling as context evolution rather than weight optimization. Instead of learning from large-scale annotations, RewardHarness aligns with human preferences by iteratively evolving a library of tools and skills from as few as 100 preference demonstrations. Given a source image, candidate edited images, and an editing instruction, an Orchestrator selects the most relevant subset of tools and skills from the maintained library, and a frozen Sub-Agent uses them to construct a reasoning chain that produces a preference judgment. By comparing predicted judgments with ground-truth preferences and analyzing successes and failures in the reasoning process, the Orchestrator automatically refines its library of tools and skills without additional human annotation. Using only 0.05% of the EditReward preference data, RewardHarness achieves 47.4% average accuracy on image-editing evaluation benchmarks, surpassing GPT-5 by 5.3 points. When used as a reward signal for GRPO fine-tuning, RL-tuned models achieve 3.52 on ImgEdit-Bench. Project page: https://rewardharness.com.
Authors: Nikhil J. Dhinagar, Vidhi Chhatbar, Chirag Jagad, Pavithra Senthilkumar, Sophia I. Thomopoulos, Mahir H. Khan, Sook-Lei Liew, the ENIGMA-Stroke Recovery Working Group, Paul M. Thompson
Abstract: Deep vision models degrade sharply in low-data regimes, particularly in medical imaging where labeled samples are scarce. We show this arises not merely from overfitting but from a geometric failure: finite-sample noise corrupts the embedding covariance, collapsing the eigengap and limiting the number of recoverable signal-bearing modes. We develop a spectral theory of finite-sample representation learning that quantifies the recoverable dimension K(N), the number of eigenmodes that can be stably estimated from N samples. Using perturbation theory and concentration bounds, we show that only modes with eigenvalues above the noise floor $\|\hat{\Sigma} - \Sigma\|_{\mathrm{op}} \sim \sqrt{D/N}$ are reliable, yielding a truncated Mahalanobis energy that governs classification performance. Under a power-law spectral model, this energy can be approximated by a truncated Riemann zeta function, linking eigenvalue decay to data efficiency and AUC. Within this framework, multimodal learning acts as spectral stabilization: vision-language models impose low-rank constraints that suppress noise-dominated directions and preserve the eigengap, increasing K(N) under data scarcity. Across MNIST and multi-disease neuroimaging, we show that multimodal training maintains more stable modes and improves class separation, even when unimodal models achieve comparable few-shot accuracy. These results identify spectral collapse as a fundamental bottleneck in low-data learning. We use truncated Mahalanobis energy and K(N) to diagnose encoder quality, and introduce zeta-based spectral filtering as a principled approach to improve data efficiency.
Authors: Haimin Luo, Min Ouyang, Lan Xu, Jingyi Yu
Abstract: Hair is a rich medium of visual and cultural expression, yet its digital modeling remains challenging due to the duality of fluidity and structure. Many existing generative approaches rely primarily on continuous diffusion fields, which entangle global topology with local texture and obscure the semantic and structural organization of hairstyles. To address this, we propose HairGPT, a strand-centric framework that treats strands as generative primitives and formulates realistic 3D hairstyle synthesis as a dual-decoupled autoregressive sequence modeling problem. Our method applies spatial decoupling across semantic scalp regions and structural decoupling along a hierarchical strand representation, progressing from global layout to fine-grained style. We further introduce a geometric tokenizer and region-aware semantic annotations to guide strand-level generation, enabling compositional editing, synthesis of rare and complex hairstyles, and adaptation to stylized domains. By aligning generative modeling with the workflow of digital grooming, HairGPT turns hair generation from opaque texture synthesis into a structured and semantically controllable authoring process, supporting robust semantic conditioning and high-fidelity results across realistic and stylized domains. Project Page: https://haiminluo.github.io/hairgpt/
Authors: Xiang Feng, Jiawei Zhou, Zhangfeng Huang, Kewei Wang, Shanshan Ye, Jinxin Hu, Zulong Chen, Yong Luo, Jing Zhang
Abstract: Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation beyond end-to-end answer accuracy. We introduce DocScope, a benchmark that formulates long-document QA as a structured reasoning trajectory prediction problem: given a complete PDF document and a question, the model outputs evidence pages, supporting evidence regions, relevant factual statements, and a final answer. We design a four-stage evaluation protocol -- Page Localization, Region Grounding, Fact Extraction, and Answer Verification -- that audits each level of the trajectory independently through inter-stage decoupling, with all judges selected and calibrated via human alignment studies. DocScope comprises 1,124 questions derived from 273 documents, with all hierarchical evidence annotations completed by human annotators. We benchmark 6 proprietary models, 12 open-weight models, and several domain-specific systems. Our experiments reveal that answer accuracy cannot substitute for trajectory-level evaluation: even among correct answers, the highest observed rate of complete evidence chains is only 29\%. Across all models, region grounding remains the weakest trajectory stage. Furthermore, the primary difficulty stems from aggregating evidence dispersed across long distances and multiple document clusters, while an oracle study identifies faithful perception and fact extraction as the dominant capability bottleneck. Cross-architecture comparisons further suggest that activated parameter count matters more than total scale. The benchmark and code will be publicly released at https://github.com/MiliLab/DocScope.
Authors: Senthil Palanisamy, Akila I. S
Abstract: Monitoring moisture level of land in a large-scale plantation is tedious. The main objective of this project is to use a robotic kit in collaboration with the on-field moisture sensor circuits, thereby creating an efficient and economical moisture monitoring system. A large agriculture field is divided into smaller grids. Each grid is placed with a moisture sensor. Whenever a sensor reports the soil to be dry, the robot goes to the concerned field for inspection. The path to the concerned field is found by applying Dijkstra's shortest path algorithm on the aerial image of the field. Then the total moisture content of the field is calculated by the robot using suitable image processing algorithms and reported accordingly. For developing and testing this work, a small study field was set up above which a camera was mounted at an appropriate height to capture its aerial view. Thus a prototype for an automated system of monitoring agricultural fields' moisture has been developed through this work.
Authors: Yiqun Wang (Beijing Jiaotong University)
Abstract: Automated grading of diabetic retinopathy (DR) faces several critical challenges: subtle inter-grade visual distinctions in fine-grained lesion patterns, distributional discrepancies induced by heterogeneous imaging devices and acquisition conditions, and the inherent inability of purely visual approaches to exploit clinical semantic knowledge. In this paper, we propose CLIP-Guided Semantic Diffusion (CGSD), a DR grading framework that synergistically integrates vision-language pretraining with diffusion probabilistic modeling. We adopt a domain-specific vision-language model tailored for DR grading as the semantic guidance module and adapt it to the target domain via Low-Rank Adaptation (LoRA), effectively bridging the distributional gap between the pretrained model and the target dataset with only a minimal number of trainable parameters. Building on this foundation, we construct a cross-modal semantic conditioning vector by computing the dot product between image features and the text description features of each DR grade, yielding a joint representation that simultaneously encodes visual content and clinical-grade semantics. This vector serves as the conditioning signal for the diffusion denoising network, replacing the structurally complex dual-branch visual prior employed in existing diffusion-based classification methods. Experiments on the APTOS 2019 dataset demonstrate that the proposed approach achieves an accuracy of 87.5% and a macro-averaged F1 score of 0.731, outperforming a variety of representative methods. Ablation studies further validate the independent contribution of each constituent module.
Authors: Rui Liu, Dian Yu, Zhenwen Liang, Yucheng Shi, Tong Zheng, Runpeng Dai, Haitao Mi, Pratap Tokekar, Leoweiliang
Abstract: Aligning Multimodal Large Language Models (MLLMs) requires reliable reward models, yet existing single-step evaluators can suffer from lazy judging, exploiting language priors over fine-grained visual verification. While rubric-based evaluation mitigates these biases in text-only settings, extending it to multimodal tasks is bottlenecked by the complexity of visual reasoning. The critical differences between responses often depend on instance-specific visual details. Robust evaluation requires dynamically synthesizing rubrics that isolate spatial and factual discrepancies. To address this, we introduce $\textbf{DeltaRubric}$, an approach that reformulates multimodal preference evaluation as a plan-and-execute process within a single MLLM. DeltaRubric operates in two steps: acting first as a $\textit{Disagreement Planner}$, the model generates a neutral, instance-specific verification checklist. Transitioning into a $\textit{Checklist Verifier}$, it executes these self-generated checks against the image and question to produce the final grounded judgment. We formulate DeltaRubric as a multi-role reinforcement learning problem, jointly optimizing planning and verification capabilities. Validated on Qwen3-VL 4B and 8B Instruct models, DeltaRubric achieves solid empirical gains. For instance, On VL-RewardBench, it improves base model overall accuracy by $\textbf{+22.6}$ (4B) and $\textbf{+18.8}$ (8B) points, largely outperforming standard no-rubric baselines. The results demonstrate that decomposing evaluation into structured, verifiable steps leads to more reliable and generalizable multimodal reward modeling.
Authors: Meet Shah, Jason Gusdorf, Anil Palepu, Chunjong Park, Jack W. O'Sullivan, Vishnu Ravi, Tim Strother, Pavel Dubov, Aliya Rysbek, Toshiyuki Fukuzawa, Yana Lunts, Jan Freyberg, Michael B. Chang, Aniruddh Raghu, David Stutz, Devora Berlowitz, Eliseo Papa, Taylan Cemgil, JD Velasquez, Jack Chen, Arthur Chen, Doug Fritz, Charlie Taylor, Katya Tregubova, Jing Rong Lim, Richard Green, Sara Mahdavi, Mahvish Nagda, Jihyeon Lee, Craig Schiff, Liviu Panait, Sukhdeep Singh, Valentin Li\'evin, David G. T. Barrett, Hannah Gladman, Anna Cupani, Francesca Pietra, Uchechi Okereke, Katherine Tong, Clemens Meyer, Erwan Rolland, Mili Sanwalka, Michael D. Howell, Shixiang Shane Gu, Bibo Xu, Euan A. Ashley, S. M. Ali Eslami, Gregory Wayne, Pushmeet Kohli, Vivek Natarajan, Adam Rodman, Alan Karthikesalingam, Ryutaro Tanno
Abstract: The practice of medicine relies not only upon skillful dialogue but also on the nuanced exchange and interpretation of rich auditory and visual cues between doctors and patients. Building on the low-latency voice and video processing capabilities of Gemini, we introduce AI co-clinician, a first-of-its-kind conversational AI system utilizing continuous streams of audio-visual data from live patient conversations to inform real-time clinical decisions. Its dual-agent architecture balances deep clinical reasoning with the low latency required for natural dialogue. To assess this system, we implemented a video-based interface emulating telemedicine consultations. We crafted 20 standardized outpatient scenarios requiring proactive real-time auditory and visual reasoning and designed "TelePACES" evaluation criteria alongside case-specific rubrics. In a randomized, interface-blinded, crossover simulation study (n = 120 encounters) with 10 internal medicine residents as patient actors, we compared AI co-clinician with primary care physicians (PCPs), GPT-Realtime, and a baseline agent. AI co-clinician approached PCPs in key TelePACES dimensions, including management plans and differential diagnosis, while significantly outperforming GPT-Realtime across all general criteria. While our agent demonstrated parity with PCPs in case-specific triage measures, physicians maintained superior overall performance in case-specific assessments. Although AI co-clinician marks a significant advance in real-time telemedical AI, gaps remain in physical examination and disease-specific reasoning. Our work shows that text-only approaches fail to capture the true challenges of medical consultation and suggests that high-stakes real-time diagnostic AI is most safely advanced in collaborative, triadic models where AI can be a supportive co-clinician for doctors and patients.
Authors: Wenxuan Liu, Zecheng Hao, Tong Bu, Yuran Wang, Zhaofei Yu
Abstract: Spiking transformers have shown strong potential for neuromorphic vision, yet their token processing across multiple spiking steps still introduces substantial redundancy and inference cost. Existing token reduction methods mainly rely on response based cues, such as activation magnitude, firing statistics, or feature similarity. Although effective, these criteria do not explicitly characterize token importance from the perspective of temporally evolving class evidence. In spiking transformers, token representations are progressively formed across multiple spiking steps rather than determined at a single instant, suggesting that token importance should be evaluated not only by instantaneous responses but also by temporal uncertainty patterns. Our key observation is that tokens exhibit heterogeneous uncertainty trajectories over time, and that their temporally aggregated uncertainty statistics provide an effective cue for distinguishing informative tokens from redundant ones. Motivated by this, we propose Uncert, a training free and plug and play token importance estimation framework for spiking transformers. Specifically, Uncert models token wise class evidence with a Dirichlet distribution and summarizes each token temporal uncertainty using its mean and fluctuation across spiking steps, yielding an uncertainty aware importance score for token reduction during inference. Experiments on both static and neuromorphic benchmarks show that Uncert achieves favorable accuracy and efficiency tradeoffs, with the most consistent gains observed under token pruning. Further analysis reveals a clear empirical connection between temporal uncertainty patterns and token contribution, offering new insights into token dynamics in spiking transformers.
Authors: Daheng Yin, Yili Jin, Jianxin Shi, Isaac Ding, Miao Zhang, Fangxin Wang, Zhaowu Huang, Cong Zhang, Jiangchuan Liu, Fang Dong
Abstract: Volumetric video (VV) streaming enables real-time, immersive access to remote 3D environments, powering telepresence, ecological monitoring, and robotic teleoperation. These applications turn VV streaming into a real-time interface to remote physical environments, imposing new system-level demands for photorealistic scene representation, low-latency interaction, and robust performance under heterogeneous networks. 3D Gaussian Splatting (3DGS) has been widely used for real-time photorealistic rendering, offering superior visual quality and rendering performance, but it faces challenges due to bandwidth consumption. Furthermore, as the foundation of adaptive VV streaming, existing Levels of Detail (LoD) methods based on density are not well-suited to Gaussian representations, leading to visible gaps and severe quality degradation. Recent studies have also explored attribute compression techniques to reduce bandwidth consumption. Our preliminary studies reveal that aggressive attribute compression primarily causes color distortion, which can be effectively corrected in the rendered image using a reference image. Motivated by these findings, we propose a novel Color-Adaptive scheme for adaptive VV streaming that uses vector quantization (VQ) to establish LoDs and correct color distortions with low-resolution reference images. We further present CAGS, an adaptive VV streaming system compatible with diverse Gaussian representations, which integrates the Color-Adaptive scheme by rendering reference images on the streaming server and performing color restoration on the client. Extensive experiments on our prototype system demonstrate that CAGS outperforms the existing adaptive streaming systems in PSNR by 5$\sim$20 dB under fluctuating bandwidth, operates significantly faster than existing scalable Gaussian compression methods, and generalizes across different Gaussian representations.
Authors: Ethan Hsu, Hong Meng Yam, Ivan Ge
Abstract: Partial differential equation (PDE) solvers underpin scientific computing, but real-world deployment is bounded by compute. Classical Monte Carlo solvers such as Walk-on-Spheres (WoS) are unbiased and geometry-agnostic but are slow. Learned solvers are fast but biased and brittle under distribution shift. We present \textbf{MC$^2$}, a hybrid WoS-Neural Network (WoS-NN) PDE solver that treats a low-budget Monte Carlo solution as a structured estimator of the true field and learns a single-pass neural correction to recover a high-fidelity solution. MC$^2$ matches the accuracy of solutions using over $1000\times$ more Monte Carlo compute, outperforming all evaluated classical, denoising, and neural-operator baselines. To enable reproducible study of finite-compute PDE solving, we additionally release \textbf{PDEZoo}, the largest standardized elliptic PDE benchmark to date: 2M PDEs spanning five elliptic families and unlimited geometric compositions, with analytic ground truth and multi-budget Monte Carlo trajectories. Together \textbf{MC$^2$} and \textbf{PDEZoo} (1) empirically establish that finite-sample Monte Carlo error is structured, learnable, and correctable in a single forward pass, (2) show that we can solve PDEs $\sim$\textbf{1000x} faster than with just WoS, and (3) provide the evaluation infrastructure the field has so far lacked.
Authors: Chaitanya Amballa, Sattwik Basu, Jorge Van\v{c}o Sampedro, Romit Roy Choudhury
Abstract: We study posterior sampling for inverse problems in discrete state spaces using discrete diffusion models as generative priors. While continuous diffusion models have become widely used for inverse problems, their discrete counterparts remain comparatively underexplored. Existing discrete posterior samplers often rely on continuous relaxations of discrete variables, Gibbs-style updates, or mechanisms specialized to particular corruption processes, which can limit scalability or generality. We propose $\Delta$LPS, a Discrete Langevin-Inspired Posterior Sampler that uses gradient information to identify promising discrete moves without leaving the discrete state space. The resulting approach enables efficient parallel updates across all token dimensions and is agnostic to the training paradigm of the discrete diffusion prior, including masked and uniform-state diffusion. We evaluate our method on image restoration tasks across MNIST, CIFAR, and FFHQ, as well as spatial mapping, covering linear, nonlinear, and blind inverse problems. Across these settings, we improve over recent discrete diffusion posterior samplers and are competitive with strong continuous diffusion-based inverse solvers. Our results suggest that fully discrete, gradient-informed posterior samplers offer a scalable and general path toward solving inverse problems over discrete representations.
Authors: Guibin Zhang, Yaohui Ling, Fanci Meng, Kun Wang, Shuicheng Yan
Abstract: GUI agents are beginning to operate the web, mobile, and desktop as interactive worlds, where successful control depends on carrying forward visual, procedural, and task-level evidence beyond the fleeting present screen. Yet most agents still treat memory as an external, human-readable artifact: histories are summarized, categorized, retrieved, and reinserted as text or structured records before being encoded again by the policy. This creates a mismatch between the representational form in which experience is stored and the latent embedding sequence over which modern GUI policies actually act. We introduce Mem-W, a series of latent-memory-native GUI agents that treat memory as part of the agent's continuous context rather than as an auxiliary symbolic scaffold. Mem-W weaves both historical trajectories (as experiential memory) and in-session segments (as working memory) into compact memory tokens through a shared trajectory-to-latent compressor. These tokens are woven with the current GUI observation and local context into one continuous embedding sequence, allowing the agent to read successes, failures, and unfinished progress through the same machine-native interface. Mem-W is trained with self-distillation and outcome-aware supervision to preserve decision-relevant state while filtering memory toward evidence that truly supports task success. Across four web and mobile navigation benchmarks, Mem-W consistently improves diverse backbones and memory-enhanced baselines, with gains of up to $+30.0$, suggesting that latent-context-native memory can serve as a scalable foundation for long-horizon GUI agency.
Authors: Wenting Wang, Zhuo Huang, Kun Qian, Neelotpal Dutta, Yuhu Guo, Yingjun Tian, Yeung Yam, Charlie C. L. Wang
Abstract: We present FrameTwin, a curve-anchored Gaussian alignment framework that uses sparse-view images to close the control loop for adaptive wireframe 3D printing. Our key idea is to capture the deformation of thin wireframe structures from sparse-view images using Gaussian kernels anchored to parametric curves, yielding a compact and geometry-aware encoding that explicitly captures strut topology. Driven by a differentiable rendering pipeline, FrameTwin estimates a neural deformation field that aligns the partially printed target model with the deformed structure observed during fabrication, where the optimized curve-Gaussian representation serves as a digital twin of the evolving wireframe. Unlike general Gaussian-splatting approaches, our formulation constrains kernel placement along parametric curves, substantially reducing the ambiguity inherent in sparse-view observations of thin structures. The resultant deformation-field alignment enforces global consistency across all struts. By using the estimated deformation field to blend the distorted printed geometry with the remaining unprinted geometry, FrameTwin enables adaptive updates to future printing trajectories. We demonstrate that FrameTwin can robustly capture and compensate for deformation in wireframe models fabricated using a robotized 3D printing system.
Authors: Ilay Yavlovich, Jad Agbaria, Muhamed Mhamed, Jose Yallouz, Nir Weinberger
Abstract: The Linear Assignment Problem (LAP) is a fundamental combinatorial optimization task with applications ranging from computer vision to logistics. Classical exact solvers such as the Hungarian and Jonker-Volgenant (LAPJV) algorithms guarantee optimality, but their cubic time complexity $\mathcal{O}(N^{3})$ becomes a bottleneck for large-scale instances. Recent learning-based approaches aim to replace these solvers with neural models, often sacrificing exactness or failing to scale due to memory constraints. We propose a learning-augmented framework that accelerates exact assignment solvers while maintaining optimality and worst-case guarantees. Our method predicts dual variables to warm-start a classical solver, with a fallback that prevents asymptotic runtime degradation when the learned advice is unreliable. We introduce RowDualNet, a lightweight row-independent architecture that avoids the $\mathcal{O}(N^{2})$ memory bottleneck of graph-based models, enabling neural warm-starting at large scale ($N=16{,}384$). Feasibility is ensured via a constructive mechanism based on LP duality (namely, the Min-Trick), eliminating costly iterative projection. Empirically, our approach reduces the search effort of LAPJV and achieves over $2{\times}$ speedups on challenging synthetic distributions, in addition to improving over $1.25{\times}$ and $1.5{\times}$ on real-world tracking (MOT) and transportation (LPT) datasets, respectively, while strictly maintaining full optimality, effectively yielding a robust zero-shot generalization to real-world tasks.
Authors: Huitao Yang, Hengzhi He, Guang Cheng
Abstract: Targeted data selection aims to identify training samples from a large candidate pool that improve performance on a specific downstream task. Many recent methods estimate candidate utility by aggregating local attribution scores along a trajectory induced by the candidate pool. When the pool is heterogeneous, however, this reference trajectory may be misaligned with the dynamics of a target-aligned selected subset, creating what we call reference path bias. We propose an alternative reference path: a validation-induced flow obtained from a short, capacity-limited warmup on the available target validation proxy. Along this path, candidates are scored by a normalized endpoint loss drop, yielding a simple zero-order selection rule that requires no candidate gradients or Hessian approximations. Across controlled logistic, vision, and instruction-tuning experiments, this score is competitive with strong dynamic attribution baselines while substantially reducing warmup and storage cost. Moreover, since the reference trajectory is decoupled from any specific candidate pool, the same compact warmup can be reused across additional pools without recomputing the trajectory.
Authors: Jiafeng Liang, Zhihao Zhu, Zihan Zhang, Baoqi Ren, Shixin Jiang, Runxuan Liu, Tao Ren, Ming Liu, See-Kiong Ng, Bing Qin
Abstract: Although Large Multimodal Models (LMMs) have achieved strong performance on general video understanding, their susceptibility to textual prior shortcuts during causal discovery has been recognized as a critical deficit. The underlying mechanisms of this phenomenon remain incompletely understood, as existing benchmarks only measure response accuracy without revealing the sources and extent of the deficit. We introduce ProCauEval, a perturbation-based evaluation protocol that shifts from outcome assessment to mechanism diagnosis, probing causal discovery through five controlled configurations that systematically manipulate visual and textual modalities to decompose their respective contributions to model behavior and dissect the failure modes. Evaluating 17 mainstream LMMs, we find that models faithfully perceive video content yet systematically underexploit it during causal reasoning. We further observe that stronger post-training amplifies rather than mitigates textual prior reliance, and that higher baseline performance correlates with greater fragility under perturbation. To address these, we propose Anti-Distillation Policy Optimization (ADPO), a reinforcement learning framework built on negative teacher alignment, which augments GRPO by explicitly pushing the policy away from a prior-only counterfactual teacher induced by visual corruption. Specifically, ADPO maximizes the divergence between the policy distributions conditioned on the original and visually corrupted inputs, thereby forcing the model to ground its reasoning in visual evidence rather than textual shortcuts. Extensive experiments show that ADPO improves visual engagement without sacrificing fundamental comprehension, thus offering a preliminary step toward reliable causal discovery.
Authors: Feng Ding, Haisheng Fu, Jie Liang, Qihan Xu, Siyu Zhu, Jingning Han
Abstract: We study full-reference image quality assessment from a machine-centric perspective, where images are evaluated by how well they preserve information for downstream models. We formulate machine-oriented quality as a latent machine utility and approximate it through pairwise predictive-consistency comparisons. To this end, we construct PCMP, a dataset of PSNR-matched distortion pairs labeled by consistency votes from multiple pretrained models. We further propose ML-CLIPSim, a differentiable quality metric built on a frozen CLIP visual encoder, which aggregates intermediate patch-token similarities and global image embeddings. Experiments on machine-preference benchmarks, human-IQA datasets, and learned image compression show that ML-CLIPSim better aligns with machine-oriented preferences than conventional fidelity and perceptual metrics, while remaining competitive for human quality prediction. Used as a compression distortion term, it improves rate--task trade-offs across multiple downstream tasks.
Authors: Kuanwei Chen, Mengfeng Tsai
Abstract: Sign Language Translation (SLT) converts sign language videos into spoken-language text, bridging communication between Deaf and hearing communities. Current gloss-free approaches rely on large encoder-decoder models, limiting deployment. We propose a compact 77M-parameter pipeline that couples MMPose skeletal pose extraction with a single linear projection into T5-small. By varying the input frame rate, we expose a practical efficiency trade-off: at 12 fps the model halves its sequence length, achieving a 75% reduction in encoder quadratic self-attention computational complexity while incurring only a modest BLEU-4 drop (9.53 vs. 10.06 at 24 fps on How2Sign). Our system is roughly 3x smaller than prior T5-base systems, demonstrating that a lightweight architecture can remain competitive without hierarchical encoders or large-scale models.
Authors: Mingxuan Liu, Yingqi Hao, Yi Liao, Juncheng Zhu, Haoxiang Li, Hongjia Yang, Yifei Chen, Yijin Li, Kasidit Anmahapong, Zihan Li, Jialan Zheng, Min Kang, Yan Song, Hua Lai, Xiaoling Zhou, Nan Sun, Rong Hu, Gang Ning, Haibo Qu, Qiyuan Tian
Abstract: Background: Prenatal germinal matrix-intraventricular hemorrhage (GMH-IVH) is a leading cause of infant mortality and neurodevelopmental impairment. Manual diagnosis and lesion segmentation are labor-intensive and error-prone. Deep learning models offer potential for automation but typically require large annotated datasets, which are challenging to obtain. Purpose: To develop and validate an annotation-free deep learning framework for automated detection and segmentation of GMH-IVH on brain MRI. Materials and Methods: This retrospective study analyzed 2D T2-weighted MRI data from pregnant women collected from October 2015 to October 2023 at one hospital (internal validation) and two hospitals (external validation). Eligible participants included healthy fetuses and those with GMH-IVH. FreeHemoSeg was developed and trained using pseudo GMH-IVH images synthesized from normal fetal data guided by medical priors. Primary outcomes included diagnostic accuracy (area under the ROC curve [AUROC], sensitivity, specificity) and segmentation accuracy (Dice similarity coefficient [DSC]). A reader study evaluated clinical utility. Results: A total of 1674 stacks from 558 pregnant women were analyzed. FreeHemoSeg achieved the highest performance in both internal (sensitivity: 0.914, 95% CI 0.869-0.945; specificity: 0.966, 95% CI 0.946-0.978; DSC: 0.559, 95% CI 0.546-0.571) and external validation (sensitivity: 0.824, 95% CI 0.739-0.885; specificity: 0.943, 95% CI 0.913-0.964; DSC: 0.512, 95% CI 0.497-0.526), outperforming supervised and unsupervised methods. FreeHemoSeg assistance improved radiologists' sensitivity (from 0.882 to 0.941-1.000) and diagnostic confidence while reducing interpretation time by 16.0-52.7%. Conclusion: FreeHemoSeg accurately detects and localizes fetal brain hemorrhages without annotated training data, enabling earlier diagnosis and supporting timely clinical management.
Authors: Duwei Dai, Caixia Dong, Guowei Dai, Qingsen Yan, Qin Zhang, Fan Liu, Pengyu Ren, Guangyao Kong, Wei Zeng
Abstract: Accurate skin lesion segmentation is vital for dermoscopic Computer-Aided Diagnosis. However, visual ambiguity and morphological irregularity often defeat spatial modeling, necessitating multi-domain architectures. Existing paradigms frequently overlook the active use of prediction uncertainty, leading to deterministic frameworks that suffer from blind cross-domain fusion and overfit to label noise. To address these issues, we propose the Uncertainty-Guided Dual-Domain Network (UGDD-Net). UGDD-Net introduces a novel "Glance-and-Gaze" mechanism to transform uncertainty into an active guiding signal. Specifically, the Uncertainty-Guided Bi-directional Feature Fusion (UGBFF) module uses pixel-level uncertainty to modulate spatial-spectral interactions. The Uncertainty-Guided Graph Refinement (UGGR) module constructs a topology-aware graph to propagate reliable semantic consensus and refine uncertain nodes. Finally, the Uncertainty-Guided Margin-Adaptive Loss (UGML) enforces strict constraints on confident pixels while relaxing penalties on uncertain ones to improve statistical calibration. Extensive experiments on ISIC2017, ISIC2018, PH2, and HAM10000 datasets demonstrate that UGDD-Net achieves state-of-the-art performance, especially on "Hard Samples". Our uncertainty maps align with expert inter-observer variability, providing robust interpretability for human-machine collaborative diagnosis.
Authors: Yule Liu, Yilong Yang, Jiale Teng, Hanze Jia, Zeren Luo, Jingyi Zheng, Zifan Peng, Ke Li, Yifan Liao, Zhen Sun, Jiaheng Wei, Yang Liu, Zhuo Ma, Xinlei He
Abstract: Recent advances in image-to-3D models have significantly improved the fidelity and accessibility of 3D content creation. Such a powerful reconstruction capability that enables creative design can also be misused by the adversary to generate harmful geometries, which can be further fabricated via 3D printers and pose real-world risks. However, such risks are largely underexplored: it remains unclear how well current image-to-3D models can produce these harmful geometries, and whether existing safeguards can reliably prevent such generation. To fill this gap, we conduct a systematic measurement study of harmful geometry generation and mitigation. We first describe this risk through three kinds of unsafe categories: direct-use physical hazards, risky templates or components, and deceptive replicas. Each category is instantiated with representative objects. We evaluate both open-source and commercial image-to-3D models under original, degraded, viewpoint-shifted, and semantically camouflaged inputs. We consider different evaluation metrics, including geometric validity, multi-view VLM-based semantic scoring, targeted human validation, and controlled physical fabrication. The results reveal a concerning reality that current image-to-3D models can effectively reconstruct the harmful geometries, while fewer than 0.3% of such geometries trigger commercial moderation flags. As a first step toward mitigation, we evaluate three representative safeguard families, including input moderation, model-level benign alignment, and output-level filtering. We find that existing safeguards have distinct weaknesses. We further develop a stacked defense that can reduce harmful retention to <1%, but still at 11% overall false-positive cost. Taken together, our findings demonstrate that the risk in current system and encourage better geometry-aware safeguards for moderation.
Authors: Narsimha Menga, Parikshit Sakurikar, Amirreza Rouhi, Satya Sai Reddy, Anirudh Govil, Sri Harsha Chittajallu, Rajat Aggarwal, Anoop Namboodiri, Sashi Reddi
Abstract: Robotic deployment in real-world environments depends on rich, domain-specific action data as much as on strong model architecture. General-purpose robot foundation models show modest performance in complex unseen tasks such as manipulation in a retail domain when applied out of the box. The root cause is a data gap: retail environments are structurally absent from general robot pretraining distributions, and the path to filling that gap through teleoperation is prohibitively expensive, logistically constrained, and difficult to scale. We introduce SABER, a high-fidelity retail robotics action dataset built from over 100 hours of natural in-store capture across multiple real grocery environments. Egocentric footage from head-mounted cameras records fine-grained hand activity at the point of interaction, while exocentric 360-degree scene footage from DreamVu's ALIA camera simultaneously observes all actors and activities across the entire space. This combination yields a uniquely complete picture of human retail behavior: dexterous hand activity, whole-body motion, and scene dynamics, all captured without staging, scripting, or teleoperation overhead. The SABER corpus contains 44.8K training samples across three action representation streams: 25K latent action sequences via LAPA-style encoding, 18.6K dexterous hand-pose trajectories retargeted to robot joint space, and 1.2K whole-body synchronized motion sequences retargeted to a humanoid embodiment. When applied to GR00T N1.6 via a shared-backbone multi-task post-training recipe, SABER yields a mean success rate of 29.3% across ten retail manipulation tasks -- more than 2.19x over fine-tuning baselines (13.4%). SABER demonstrates that the path to capable retail robots runs through better data, which can be collected today, at scale, without a robot in the loop. The dataset and code are available at https://dreamvu.ai/saber
URLs: https://dreamvu.ai/saber
Authors: Alvin Kimbowa, Moein Heidari, David Liu, Ilker Hacihaliloglu
Abstract: While U-Net architectures remain the gold standard for medical image segmentation, their deployment in resource-constrained environments demands aggressive model compression. However, finding an optimally efficient configuration is computationally prohibitive, typically requiring exhaustive train-and-evaluate cycles to find the smallest model that maintains peak performance. In this paper, we introduce a training-free selection framework to automatically identify ultralightweight, dataset-specific U-Net configurations directly at initialization. We observe that systematically scaling down U-Net channel width induces a sharp transition from a stable performance plateau to representational capacity collapse. To pinpoint this boundary without training, we propose a Jacobian-based sensitivity metric that scores discrete, width-capped U-Net variants using a small set of unlabeled images. By analyzing the total variation of this sensitivity curve, we isolate the smallest stable configuration, which we denote as XTinyU-Net. Evaluated across six diverse medical datasets within the nnU-Net framework, XTinyU-Net achieves segmentation accuracy comparable to the heavy nnU-Net baseline with 400x-1600x fewer parameters, and outperforms contemporary lightweight architectures while utilizing 5x-72x fewer parameters. Code is publicly accessible on https://github.com/alvinkimbowa/nntinyunet.git.
Authors: Aws Khalil, Jaerock Kwon
Abstract: Teleoperation systems are fundamentally limited by communication latency, which degrades situational awareness and control performance. Predictive display aims to mitigate this limitation by presenting an estimate of the current visual state rather than delayed observations. While recent advances in generative video models enable high-quality video synthesis, their suitability for latency-sensitive predictive display remains unclear. This paper presents a zero-shot benchmark of off-the-shelf generative video models for short-horizon predictive display, without task-specific fine-tuning. We formulate the problem as rollout-based future frame prediction and develop a unified benchmarking pipeline using simulated driving data from the CARLA simulator. Five publicly released video models spanning transformer-based and diffusion-based families are evaluated across two resolutions and two conditioning regimes (multi-frame and single-frame). Performance is assessed using prediction accuracy (mean absolute difference), per-rollout latency, peak GPU memory usage, and temporal error evolution across the prediction horizon. On this zero-shot benchmark, no tested model simultaneously achieves low rollout error, non-divergent per-step error behavior, and real-time inference at the source frame rate. Increasing model scale or resolution yields limited and, in some cases, inverted improvements. These findings highlight a gap between general-purpose generative video synthesis and the requirements of predictive display in teleoperation, suggesting that practical deployment will require either explicit short-horizon temporal supervision, in-domain adaptation, or aggressive inference optimization rather than direct application of off-the-shelf models. Code, configurations, and qualitative results are released on the project page: https://bimilab.github.io/paper-GenPD
Authors: Yukang Shen
Abstract: Modern computer vision systems increasingly encounter performance limitations in data-scarce domains, where collecting large-scale, high-quality labeled data is costly or impractical. While controllable diffusion models enable scalable synthetic image generation, directly applying synthetic augmentation often leads to unstable performance gains due to dataset-level quality issues and insufficient feedback mechanisms. In this work, we present a Real-Calibrated Synthetic-First Data Engine, a modular data engineering framework that combines controllable diffusion generation and multi-stage curation/filtering within a unified pipeline, with optional support for uncertainty-driven selection and human verification. Instead of introducing new generative algorithms, our approach focuses on systematic dataset construction for improving the practical reliability of synthetic augmentation in low-data regimes. The framework is implemented as a modular CLI-based pipeline, where generation, filtering, selection, and validation components can be independently configured and replaced. This design emphasizes reproducibility, flexibility, and practical deployment in real-world data workflows. Through empirical evaluation centered on human pose estimation, we show that synthetic data improves a real-data baseline when used as near-zero-human-annotation-cost augmentation alongside real anchors, while synthetic-only training remains substantially below real-only performance. Supplementary segmentation diagnostics show the same domain-gap pattern. These results highlight the practical value of data-centric orchestration for low-data augmentation.
Authors: Anushree Berlia
Abstract: We present Loom, an outfit recommendation system that combines neural embedding retrieval with structured domain scoring to generate complete, coherent outfits from fashion catalogs. Given an anchor clothing item, Loom retrieves complementary pieces via slot-constrained approximate nearest neighbor search over FashionCLIP embeddings, then scores candidate outfits using a multi-objective function that integrates six signals: embedding similarity, color harmony, formality consistency, occasion coherence, style direction, and within-outfit diversity. We introduce two techniques that address limitations of purely learned or purely rule-based approaches: (1) semantic material weight, which uses CLIP embedding geometry to infer garment heaviness for layer compatibility without hand-coded material taxonomies; and (2) vibe/anti-vibe occasion priors, which embed prose descriptions of occasion contexts as anchor vectors in CLIP space and score items by differential affinity. Ablation experiments on a catalog of 620 items show that each component contributes measurably to outfit quality: the full system achieves a mean outfit score of 0.179 with a 9.3% hard violation rate, compared to 0.054 score and 16.0% violations for a category-constrained random baseline, a 3.3x improvement in score and 42% reduction in violations. Direction reranking is the single indispensable component: removing it drops score to 0.052, essentially equal to random. The system generates three stylistically distinct outfits in under 5 seconds on commodity hardware.
Authors: Haosen Wang, Zhenyang Li, Yinqiang Zhang, Zongqi He, Lutao Jiang, Kai Li, Yizhou Zhao, Liaoyuan Fan, Wenjian Hou, Tingbang Liang, Yibin Wen, Defeng Gu
Abstract: Zero-shot object navigation has advanced rapidly with open-vocabulary detectors, image--text models, and language-guided exploration. However, even after current methods detect a plausible target hypothesis, the agent may still oscillate between exploration and pursuit, or abandon the object near success. We identify this failure mode as an action consistency gap: semantic evidence is repeatedly reinterpreted at each step without persistent commitment across the episode. We introduce ConsistNav, a training-free zero-shot ObjectNav framework built around a semantic executive composed of three coordinated modules: Finite-State Executive Controller stages target pursuit through guarded semantic phases; Persistent Candidate Memory accumulates cross-frame target evidence into stable object hypotheses; and Stability-Aware Action Control suppresses rotational stagnation, ineffective pursuit, and unverified stopping. This design changes neither the detector nor the low-level planner; instead, it controls when semantic evidence should influence navigation and when it should be suppressed or revisited. We conduct extensive experiments on HM3D and MP3D, where ConsistNav achieves state-of-the-art results among compared zero-shot ObjectNav methods and improves SR by 11.4% and SPL by 7.9% over the controlled baseline on MP3D. Ablation studies and real-world deployment experiments further demonstrate the effectiveness and robustness of the proposed executive mechanism.
Authors: Hao Liu, Jicheng Liu
Abstract: A vision-language model can look at a knot diagram and report what it sees, yet fail to act on that structure. KnotBench pairs an 858,318-image corpus from 1,951 prime-knot prototypes (crossing numbers 3 to 19) with a protocol whose answers are checked against Regina's canonical knot signature. Its 14 tasks span four families, equivalence judgment, move prediction, identification, and cross-modal grounding; an image-versus-symbol split locates failures along the perception-operation gap. We score Claude Opus 4.7 and GPT-5, each with and without thinking, under a 64K output-token budget matched on both vendors. Across 56 (task, model) cases, 15 sit at or below a random baseline and 8 of 14 tasks have a best score under 1.5x random. On diagram-to-symbol transcription, no model produces a strictly correct string, and permissive Regina decoding recovers the knot in 0 to 4 of 100 items. Thinking-mode reasoning lifts overall accuracy by 1.65 points for Claude and 9.25 points for GPT-5, narrowing the gap only modestly. Read together, the four families suggest current vision-language models hold features of a diagram but lack apparatus to simulate moves on those features.
Authors: Boyang Shen, Kaixiang Yang, Hao Wang, Qiuyu Yu, Qiang Xie, Qiang Li, Zhiwei Wang
Abstract: Current Vision-Language-Action (VLA) models typically treat the deepest representation of a vision-language backbone as universally optimal for action prediction. However, robotic manipulation is composed of many frequent closed-loop spatial adjustments, for which excessive abstraction may waste computation and weaken low-level geometric cues essential for precise control. Existing early-exit strategies attempt to reduce computation by stopping at predefined layers or applying heuristic rules such as action consistency, but they do not directly answer when a representation is actually sufficient for action. In this paper, we present LoopVLA, a recurrent VLA architecture that jointly learns representation refinement, action prediction, and sufficiency estimation. LoopVLA iteratively applies a shared Transformer block to refine multimodal tokens, and at each iteration produces both a candidate action and a sufficiency score that estimates whether further refinement is necessary. By sharing parameters across iterations, LoopVLA decouples refinement from absolute layer indices and grounds sufficiency estimation in the evolving representation itself. Since sufficiency has no direct supervision, we introduce a self-supervised distribution alignment objective, where intermediate confidence scores are trained to match the relative action quality across refinement steps, thereby linking sufficiency learning to policy optimization signals. Experiments on LIBERO, LIBERO-Plus, and VLA-Arena show that LoopVLA pushes the efficiency-performance frontier of VLA policies, reducing parameters by 45% and improving inference throughput by up to 1.7 times while matching or outperforming strong baselines in task success.
Authors: Tianhong Gao, Cheng Yu, Yinghao Xu, Mengyu Chu
Abstract: Articulated objects used in simulation and embodied AI are typically specified by geometry and kinematic structure, but lack the fine-grained dynamical effects that govern realistic mechanical behavior, such as frictional holding, detents, soft closing, and snap latching. Existing approaches either ignore the detailed structure of dynamics entirely, or use simple models with limited expressiveness. We introduce JODA, a framework for generating joint-level dynamics as a structured three-channel field over the joint degree of freedom, capturing conservative forces, dry friction, and damping. Instantiated using shape-constrained piecewise cubic interpolation (PCHIP), this formulation defines a compact and expressive function space that is both interpretable and compatible with differentiable simulation. Building on this representation, we develop methods for inferring and refining joint dynamics from multimodal inputs. Given visual observations and joint context, a vision-language model proposes structured dynamical primitives, which are composed into a unified dynamics field. The resulting representation supports both direct manipulation and gradient-based refinement. We demonstrate that JODA enables plausible and controllable modeling of diverse joint behaviors, providing a unified interface for inference, editing, and optimization. Code and example assets with their generated profiles will be released upon publication.
Authors: Zhongyu Xia, Guanyu Zhu, Guo Tang, Wenhao Chen, Yongtao Wang
Abstract: End-to-end autonomous driving has witnessed rapid progress, yet existing benchmarks are increasingly saturated, with state-of-the-art models achieving near-perfect scores on widely used open-loop and closed-loop benchmarks. This saturation does not mean that the problem has been solved; instead, it reveals that current benchmarks remain limited in scenario diversity, object variety, and the breadth of driving capabilities they evaluate. In particular, they lack sufficient long-tail scenarios involving rare but safety-critical objects and fail to assess advanced decision-making such as legal compliance, ethical reasoning, and emergency response. To address these gaps, we propose HiDrive, a new closed-loop benchmark for end-to-end autonomous driving that emphasizes long-tail scenarios and a richer evaluation of driving capabilities. HiDrive introduces a diverse set of rare objects and uncommon traffic situations, and expands evaluation from basic driving skills to more advanced capabilities, including rule compliance, moral reasoning, and context-dependent emergency maneuvers. Correspondingly, we extend previous collision-avoidance-centered metrics into a comprehensive evaluation system that encompasses collision and braking, traffic-rule compliance, and moral-reasoning indicators. Built on a more advanced physics engine, HiDrive provides physically realistic lighting and high-fidelity visual rendering, offering a more challenging and realistic testbed for assessing whether autonomous driving systems can handle the complexity of real-world deployment. The HiDrive software, source code, digital assets, and documentation are available at https://github.com/VDIGPKU/HiDrive.
Authors: Evans Han, Yunfan Jiang, Yingke Wang, Haoyue Xiao, Huang Huang, Jianwen Xie, Jiajun Wu, Li Fei-Fei, Ruohan Zhang
Abstract: Recent advances in robot imitation learning have yielded powerful visuomotor policies capable of manipulating a wide variety of objects directly from monocular visual inputs. However, monocular observations inherently lack reliable depth cues and spatial awareness, which are critical for precise manipulation in cluttered or geometrically complex scenes. To address this limitation, we introduce StereoPolicy, a new visuomotor policy learning framework that directly leverages synchronized stereo image pairs to strengthen geometric reasoning, without requiring explicit 3D reconstruction or camera calibration. StereoPolicy employs pretrained 2D vision encoders to process each image independently and fuses the resulting representations through a Stereo Transformer. This design implicitly captures spatial correspondence and disparity cues. The framework integrates seamlessly with diffusion-based and pretrained vision-language-action (VLA) policies, delivering consistent improvements over RGB, RGB-D, point cloud, and multi-view baselines across three simulation benchmarks: RoboMimic, RoboCasa, and OmniGibson. We further validate StereoPolicy on real-robot experiments spanning both tabletop and bimanual mobile manipulation settings. Our results underscore stereo vision as a scalable and robust modality that bridges 2D pretrained representations with 3D geometric understanding for robotic manipulation.
Authors: Tianyang Chen, Mandar M. Sohoni, Saeed A. Khan, J\'er\'emie Laydevant, Shi-Yuan Ma, Tianyu Wang, Peter L. McMahon, Hakan E. T\"ureci
Abstract: Optical readout in low-light imaging is fundamentally limited by measurement noise, including photon shot noise, detector noise, and quantization error. In this regime, downstream inference depends not only on the optical front end, but also on how noisy high-dimensional sensor measurements are represented before classification or decision-making. Here we show that eigentasks provide a measurement-adapted representation for optical sensor outputs by ordering readout features according to their resolvability under noise. Using experimental data from a lens-based optical imaging system and a reanalysis of published data from a single-photon-detection neural network, we find that eigentask representations frequently outperform standard baselines including principal component analysis and filtering-based compression. The advantage is most pronounced in photon-limited, few-shot, and higher-difficulty classification regimes. In few-shot MPEG-7 classification, for example, the advantage over other methods reaches about 10 percentage points as the number of classes increases. In these settings, eigentasks yield more informative low-dimensional features and improve sample-efficient downstream learning. These results identify measurement-adapted representation as a promising strategy for optical inference when photon budget, acquisition time, and task complexity are constrained.
Authors: Xiangkai Wang, Yun Zhao, Dongyi He, Qingling Xia, Gen Li, Xinlai Xing, Yuchi Pan, Bin Jiang
Abstract: Motor imagery electroencephalography (MI-EEG) decoding offers a non-invasive route for post-stroke rehabilitation, but cross-patient use remains difficult because pathological neural reorganization changes task-related EEG dynamics, aperiodic activity, local excitability, cross-regional coordination, and trial-level brain-state context. This makes source-learned MI representations unreliable for unseen patients. To address this problem, we propose CFSPMNet, a cross-patient adaptation framework that models post-stroke MI-EEG as latent neural-state organization. CFSPMNet combines a Fourier-Reorganized State Mamba Network (FRSM) with Shared-Private Prototype Matching (SPPM). FRSM represents each trial as a latent physiological token sequence, reorganizes token states in the Fourier domain, and uses Fourier-derived trial context to guide Mamba state-space propagation. SPPM improves target pseudo-label updating by combining semantic confidence with shared-private physiological consistency, filtering confident but physiologically inconsistent target predictions. Leave-one-subject-out experiments on two stroke MI-EEG datasets show that CFSPMNet outperforms representative CNN-, Transformer-, Mamba-, and adaptation-based baselines, achieving average accuracies of 68.23% on XW-Stroke and 73.33% on 2019-Stroke, with gains of 5.63 and 8.25 percentage points over the strongest competitors. Ablation, sensitivity, feature-alignment, pseudo-label selection, and neurophysiological visualization analyses further support the roles of Fourier-domain token-state reorganization and calibrated pseudo-label updating. These results suggest that latent neural-state modeling can improve rehabilitation-oriented cross-patient BCI decoding. Code is available at https://github.com/wxk1224/CFSPMNet.
Authors: Federico Pizzolato, Francesco Pasti, Nicola Bellotto
Abstract: Terrain segmentation is a fundamental capability for autonomous mobile robots operating in unstructured outdoor environments. However, state-of-the-art models are incompatible with the memory and compute constraints typical of microcontrollers, limiting scalable deployment in small robotics platforms. To address this gap, we develop a complete framework for robust binary terrain segmentation on a low-cost microcontroller. At the core of our approach we design Nano-U, a highly compact binary segmentation network with a few thousand parameters. To compensate for the network's minimal capacity, we train Nano-U via Quantization-Aware Distillation (QAD), combining knowledge distillation and quantization-aware training. This allows the final quantized model to achieve excellent results on the Botanic Garden dataset and to perform very well on TinyAgri, a custom agricultural field dataset with more challenging scenes. We deploy the quantized Nano-U on a commodity microcontroller by extending MicroFlow, a compiler-based inference engine for TinyML implemented in Rust. By eliminating interpreter overhead and dynamic memory allocation, the quantized model executes on an ESP32-S3 with a minimal memory footprint and low latency. This compiler-based execution demonstrates a viable and energy-efficient solution for perception on low-cost robotic platforms.
Authors: Team Phoenix, :, Arka Ray, Askar Ali Mohamed Jawad, Biondi Lee, Elijah Seah, Eva Lim, Fiona Teo, Grace Toh, Guang Xiang Teo, Jun En Tan, Jia Hui Bong, Jiale Wang, Jonathan Ng, Justin Tan, Kai Zhe Yew, Matthew Ong, Shun Yi Yeo, Wen Jett Lam, Wen Xiu Tan, Ze Yu Zhang, Gee Wah Ng, Chee Wee Ang, Mistral AI, :, Adrien Sad\'e, Guillaume Kunsch, Jia Sin Loh, Nicolas Schuhl, Rupert Menneer, Umar Jamil, Vincent Maladi\`ere, Yimu Pan
Abstract: We introduce Phoenix-VL 1.5 Medium, a 123B-parameter natively multimodal and multilingual foundation model, adapted to regional languages and the Singapore context. Developed as a sovereign AI asset, it demonstrates that deep domain adaptation can be achieved with minimal degradation to broad-spectrum intelligence and alignment. Continued pretraining was performed on Mistral Medium 3.1 using a localized 1-trillion tokens multimodal corpus, followed by a 250-billion tokens long-context extension phase. Subsequent post-training incorporated a novel human-annotated Singapore multimodal dataset and curated textual corpus on Singapore culture, knowledge, and legislation, totaling 22-billion tokens. An additional 5 billion tokens of model alignment was performed through Online Direct Preference Optimization. Phoenix-VL 1.5 Medium achieves state-of-the-art performance for its size on Singapore multimodal, legal, and government policy benchmarks while remaining globally competitive on general multimodal intelligence, multilingual, and STEM benchmarks. We also introduce a novel evaluation suite encompassing localized knowledge benchmarks and an institutionally aligned model behavior and safety framework. We report the data curation principles, training methodology, and highlight benchmark and inference performance.
Authors: Xiang Chen, Alexander Binder
Abstract: Current 3D tokenizers largely treat representation as spatial compression: compact codes reconstruct surface geometry, but leave component ownership and attachment validity implicit. In open-world assets with intersecting components, noisy topology, and weak canonical structure, this creates a representation mismatch: local shape, component identity, and assembly relations become entangled in a latent stream and are not natively addressable during decoding. We formulate an alternative view, interface-centric generative states, in which tokenization constructs an operational state rather than a passive compressed code. The state exposes local geometry, component ownership, and attachment validity as variables that can be queried, constrained, and repaired during decoding. We instantiate this formulation with Component-Conditioned Canonical Local Tokens (C2LT-3D), factorizing representation into canonical local geometry, partition-conditioned context, and relational seam variables. Each factor targets a distinct failure mode of compression-centric tokens: pose leakage, cross-component interference, or invalid local attachment. This exposed state supports attachment validation, latent structural repair, targeted intervention, and constrained serialization without a separate post-hoc structure recovery module. Trained on single-object CAD models and evaluated zero-shot on open-world multi-component assets, C2LT-3D improves structural robustness and shows that its latent variables remain actionable under adversarial attachment settings. These results suggest that open-world 3D generative representations should be evaluated not only by reconstruction fidelity, but by whether their discrete states remain operational for assembly-level structural reasoning.
Authors: Yi Zhang, Yidong Zhao, Tijmen Toxopeus, Ma\v{s}a Bo\v{z}i\'c-Iven, Sebastian Weing\"artner, Qian Tao
Abstract: Quantitative cardiac magnetic resonance imaging (MRI) enables non-invasive myocardial tissue characterization but relies on robust motion correction within these variable-length, variable-contrast image sequences. Groupwise registration, which simultaneously aligns all images, has shown greater robustness than pairwise registration for motion correction. However, current deep-learning-based groupwise registration methods cannot generalize across MRI sequences: the architecture typically encodes input data as a fixed-length channel stack, which rigidly couples network design to protocol-specific sequence length, input ordering, and contrast dynamics. At inference time, any change in imaging protocols will render the network unusable. In this work, we introduce \emph{\AnyTwoReg}, a new set-based groupwise registration framework that takes a quantitative MRI sequence as an unordered set. This set formulation fundamentally decouples network design from sequence length and input ordering. By utilizing a shared encoder and correlation-guided feature aggregation, \emph{\AnyTwoReg} constructs a permutation-invariant canonical reference for registration, and learns a permutation-equivariant mapping from images to deformation fields. Additionally, we extract contrast-insensitive image features from an existing foundation model to handle extreme contrast variations. Trained exclusively on a single public $T_1$ mapping dataset (STONE, sequence length $L=11$), \AnyTwoReg generalizes to two unseen quantitative MRI datasets (MOLLI, ASL) with variable lengths ($L \in [11, 60]$) and different contrast dynamics. It achieves strong cross-protocol generalization in a zero-shot manner, and consistently improves downstream quantitative mapping quality. Notably, while designed for quantitative MRI sequences, our framework is directly applicable to Cine MRI sequences for inter-cardiac-phase registration.
Authors: Alan Arazi, Eilam Shapira, Shoham Grunblat, Mor Ventura, Elad Hoffer, Gioia Blayer, David Holzm\"uller, Lennart Purucker, Ga\"el Varoquaux, Frank Hutter, Roi Reichart
Abstract: Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack native support for unstructured modalities such as text and image, and rely on frozen, pretrained embeddings to process them. On established Multimodal Tabular Learning benchmarks, we show that tuning the embeddings to the task improves performance. Existing benchmarks, however, often focus on the mere co-occurrence of modalities; this leads to high variance across datasets and masks the benefits of task-specific tuning. To address this gap, we introduce MulTaBench, a benchmark of 40 datasets, split equally between image-tabular and text-tabular tasks. We focus on predictive tasks where the modalities provide complementary predictive signal, and where generic embeddings lose critical information, necessitating Target-Aware Representations that are aligned with the task. Our experimental results demonstrate that the gains from target-aware representation tuning generalize across both text and image modalities, several tabular learners, encoder scales, and embedding dimensions. MulTaBench constitutes the largest image-tabular benchmarking effort to date, spanning high-impact domains such as healthcare and e-commerce. It is designed to enable the research of novel architectures which incorporate joint modeling and target-aware representations, paving the way for the development of novel Multimodal Tabular Foundation Models.
Authors: Yangneng Chen, Junlin Li, Weijun Yao, Xilai Ma, Guodong Du, Wenya Wang, Jing Li
Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet their reliability is persistently undermined by hallucinations-generating text that contradicts visual input. Recent studies often attribute these errors to inadequate visual attention. In this work, we analyze the attention mechanisms via the logit lens, uncovering a distinct anomaly we term Vocabulary Hijacking. We discover that specific visual tokens, defined as Inert Tokens, disproportionately attract attention. Crucially, when their intermediate hidden states are projected into the vocabulary space, they consistently decode to a fixed set of unrelated words (termed Hijacking Anchors) across layers, revealing a rigid semantic collapse. Leveraging this semantic rigidity, we propose Hijacking Anchor-Based Identification (HABI), a robust strategy to accurately localize these Inert Tokens. To quantify the impact of this phenomenon, we introduce the Non-Hijacked Visual Attention Ratio (NHAR), a novel metric designed to identify attention heads that remain resilient to hijacking and are critical for factual accuracy. Building on these insights, we propose Hijacking-Aware Visual Attention Enhancement (HAVAE), a training-free intervention that selectively strengthens the focus of these identified heads on salient visual content. Extensive experiments across multiple benchmarks demonstrate that HAVAE significantly mitigates hallucinations with no additional computational overhead, while preserving the model's general capabilities. Our code is publicly available at https://github.com/lab-klc/HAVAE.
Authors: Guillem Capellera, Antonio Rubio, Luis Ferraz, Antonio Agudo
Abstract: Multi-agent trajectory modeling traditionally focuses on forecasting, often neglecting more general tasks like trajectory completion, which is essential for real-world applications such as correcting tracking data. Existing methods also generally predict agents' states without offering any state-wise measure of heteroscedastic uncertainty. Moreover, popular multi-modal sampling methods lack error probability estimates for each generated scene under the same prior observations, which makes it difficult to rank the predictions at inference time. We introduce U2Diffine, a unified diffusion model built to perform trajectory completion while simultaneously offering state-wise heteroscedastic uncertainty estimates. This is achieved by augmenting the standard denoising loss with the negative log-likelihood of the predicted noise, and then propagating the latent space uncertainty to the real state space using a first-order Taylor approximation. We also propose U2Diff, a faster baseline that avoids gradient computation during sampling. This approach significantly increases inference speed, making it as efficient as a standard generative-only diffusion model. For post-processing, we integrate a Rank Neural Network (RankNN) that enables error probability estimation for each generated mode, demonstrating strong correlation with ground truth errors. Our method outperforms state-of-the-art solutions in both trajectory completion and forecasting across four challenging sports datasets (NBA, Basketball-U, Football-U, Soccer-U), underscoring the effectiveness of our uncertainty and error probability estimation.
Authors: David F. Ramirez, Tim Overman, Kristen Jaskie, Andreas Spanias
Abstract: We introduce SMART-HC-VQA, a Sentinel-2-based visual question answering dataset derived from the IARPA SMART Heavy Construction dataset, designed for spatiotemporal analysis of human activity. The dataset transforms construction-site annotations, construction-type labels, temporal-phase labels, geographic metadata, and observation relationships into natural language question-answer triplets. This approach redefines the existing dataset as a temporally extended automatic target recognition and visual question answering (VQA) challenge, considering a fixed geospatial site as a target whose attributes and activity states evolve across sparse satellite observations. Currently, SMART-HC-VQA comprises 21,837 accessible Sentinel-2 image chips, 65,511 single-image VQA examples, and approximately 2.3 million two-image temporal comparison examples generated via our novel Image-Pairwise Combinatorial Augmentation. We detail the workflow for retrieving and processing Sentinel-2 imagery, segmenting large satellite tiles into site-centered images, maintaining traceability to SMART-HC annotations, and analyzing the distributions of site size, observation count, temporal coverage, construction type, and phase labels. Additionally, we describe an implemented multi-image MLLM training framework based on LLaVA-NeXT Mistral-7B, adapted to accept multiple dated image inputs and train on metadata-derived VQA examples. This work offers a reproducible foundation for understanding language-guided remote sensing activities, aiming not only to detect change but also to reason about the ongoing processes, their progression, and potential future developments.
Authors: Andreas Bergmeister, Stefanie Jegelka, Nikolas N\"usken, Carles Domingo-Enrich, Jakiw Pidstrigach
Abstract: Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses against a closed-form target. RL post-training aligns the model with a reward. In image generation, this makes samples compose objects correctly, render text legibly, and match human preferences. Existing methods rely on costly SDE rollouts, reward gradients, or surrogate losses, sacrificing pretraining's regression structure. We show that the structure extends to RL post-training. Under KL-regularized reward maximization, the optimal generative process tilts the clean-endpoint distribution towards samples with higher reward and leaves the noising law unchanged. Combining this with the adjoint-matching optimality condition and a REINFORCE identity, we derive Reinforce Adjoint Matching (RAM): a consistency loss that corrects the pretraining target with the reward. At each step, we draw a clean endpoint from the current model, evaluate its reward, noise it as in pretraining, and regress. No SDE rollouts, backward adjoint sweeps, or reward gradients are required. Like the pretraining objective, RAM is simple and scales. On Stable Diffusion 3.5M, RAM achieves the highest reward on composability, text rendering, and human preference, reaching Flow-GRPO's peak reward in up to $50\times$ fewer training steps.
Authors: Zuojin Tang, Haoyun Liu, Xinyuan Chang, Changjie Wu, Dongjie Huo, Yandan Yang, Bin Liu, Zhejia Cai, Feng Xiong, Mu Xu, jiachen Luo, De Ma, Zhiheng Ma, Gang Pan
Abstract: Vision-language-action (VLA) models remain constrained by the scarcity of action-labeled robot data, whereas action-free videos provide abundant evidence of how the physical world changes. Latent action models offer a promising way to extract such priors from videos, but reconstruction-trained latent codes are not necessarily suitable for policy generation: they may predict future observations while lacking the structure needed to be reused or generated coherently with robot actions. We introduce ALAM (Algebraic Latent Action Model), an Algebraically Consistent Latent Action Model that turns temporal relations in action-free video into structural supervision. Given frame triplets, ALAM learns latent transitions that are grounded by reconstruction while being regularized by composition and reversal consistency, encouraging a locally additive transition space. For downstream VLA learning, we freeze the pretrained encoder and use its latent transition sequences as auxiliary generative targets, co-generated with robot actions under a joint flow-matching objective. This couples structured latent transitions with flow-based policy generation, allowing the policy to exploit ALAM's locally consistent transition geometry without requiring latent-to-action decoding. Representation probes show that ALAM reduces additivity and reversibility errors by 25-85 times over unstructured latent-action baselines and improves long-horizon cumulative reconstruction. When transferred to VLA policies, ALAM raises the average success rate from 47.9% to 85.0% on MetaWorld MT50 and from 94.1% to 98.1% on LIBERO, with consistent gains on real-world manipulation tasks. Ablations further confirm that the strongest improvements arise from the synergy between algebraically structured latent transitions and joint flow matching.
Authors: Haozhe Zhang, Kaichen Liu, Miaomiao Chen, Lei Li, Shaojie Yang, Cheng Peng, Hanjie Chen
Abstract: Industrial Computer-Aided Design (CAD) code generation requires models to produce executable parametric programs from visual or textual inputs. Beyond recognizing the outer shape of a part, this task involves understanding its 3D structure, inferring engineering parameters, and choosing CAD operations that reflect how the part would be designed and manufactured. Despite the promise of Multimodal large language models (MLLMs) for this task, they are rarely evaluated on whether these capabilities jointly hold in realistic industrial CAD settings. We present BenchCAD, a unified benchmark for industrial CAD reasoning. BenchCAD contains 17,900 execution-verified CadQuery programs across 106 industrial part families, including bevel gears, compression springs, twist drills, and other reusable engineering designs. It evaluates models through visual question answering, code question answering, image-to-code generation, and instruction-guided code editing, enabling fine-grained analysis across perception, parametric abstraction, and executable program synthesis. Across 10+ frontier models, BenchCAD shows that current systems often recover coarse outer geometry but fail to produce faithful parametric CAD programs. Common failures include missing fine 3D structure, misinterpreting industrial design parameters, and replacing essential operations such as sweeps, lofts, and twist-extrudes with simpler sketch-and-extrude patterns. Fine-tuning and reinforcement learning improve in-distribution performance, but generalization to unseen part families remains limited. These results position BenchCAD as a benchmark for measuring and improving the industrial readiness of multimodal CAD automation.
Authors: Ishpuneet Singh, Gursmeep Kaur, Uday Pratap Singh Atwal, Guramrit Singh, Gurjot Singh, Maninder Singh
Abstract: Continuous authentication in high-stakes digital environments requires datasets with fine-grained behavioral signals under realistic cognitive and motor demands. But current benchmarks are often limited by small scale, unimodal sensing or lack of synchronised environmental context. To address this gap, this paper introduces BEACON ( Behavioral Engine for Authentication \& Continuous Monitoring), a large-scale multimodal dataset that captures diverse skill tiers in competitive \textit{Valorant} gameplay. BEACON contains approximately 430 GB of synchronised modality data (461 GB total on-disk including auxiliary \textit{Valorant} configuration captures) from 79 sessions across 28 distinct players, estimated at 102.51 hours of active gameplay, including high-frequency mouse dynamics, keystroke events, network packet captures, screen recordings, hardware metadata, and in-game configuration context. BEACON leverages the high precision motor skills and high cognitive load that are inherent to tactical shooters, making it a rigorous stress test for the robustness of behavioral biometrics. The dataset allows for the study of continuous authentication, behavioral profiling, user drift and multimodal representation learning in a high-fidelity esports setting. The authors release the dataset and code on Hugging Face and GitHub to create a reproducible benchmark for evaluating next-generation behavioral fingerprinting and security models
Authors: Yaman Kindap, Manfred Opper, Benjamin Dupuis, Umut Simsekli, Tolga Birdal
Abstract: Modelling extreme events and heavy-tailed phenomena is central to building reliable predictive systems in domains such as finance, climate science, and safety-critical AI. While L\'evy processes provide a natural mathematical framework for capturing jumps and heavy tails, Bayesian inference for L\'evy-driven stochastic differential equations (SDEs) remains intractable with existing methods: Monte Carlo approaches are rigorous but lack scalability, whereas neural variational inference methods are efficient but rely on Gaussian assumptions that fail to capture discontinuities. We address this tension by introducing a neural exponential tilting framework for variational inference in L\'evy-driven SDEs. Our approach constructs a flexible variational family by exponentially reweighting the L\'evy measure using neural networks. This parametrization preserves the jump structure of the underlying process while remaining computationally tractable. To enable efficient inference, we develop a quadratic neural parametrization that yields closed-form normalization of the tilted measure, a conditional Gaussian representation for stable processes that facilitates simulation, and symmetry-aware Monte Carlo estimators for scalable optimization. Empirically, we demonstrate that the method accurately captures jump dynamics and yields reliable posterior inference in regimes where Gaussian-based variational approaches fail, on both synthetic and real-world datasets.
Authors: Yanhua Zhang, Ke Zhang, Jingyu Wang, Gabriella Balestra, Samanta Rosati, Yulin Wu, Wuwei Wang, Valentina Giannini
Abstract: U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating multi-level features, whereas the efficiency of the latter is constrained by its quadratic computational and memory complexity. In this work, we propose an effective alternative to traditional U-shaped architectures by constructing parallel branches at different levels to obtain multi-scale features and corresponding predictions. Furthermore, we enhance our network by integrating Mamba, a state space model that captures long-range dependencies with linear complexity. First, a dual-path architecture with lateral connections aggregates high-level semantic information and low-level spatial details at each branch. Then, we introduce a Recursive Alignment Module (RAM) that restores spatial details in low-resolution features through stepwise alignment, optimizing them for subsequent global feature learning and multi-scale fusion. We further build parallel Mamba branches upon aligned features to establish hierarchical global representations. Finally, we propose a Mamba-based attention mechanism for adaptive multi-scale prediction fusion; this mechanism utilizes Mamba to enhance information exchange across scales along both the channel and spatial dimensions. Experiments across three imaging modalities (MRI, CT, and dermoscopy) underscore the superior generalization of the proposed network. Compared to state-of-the-art 2D CNN, Transformer, and Mamba-based networks, our model achieves the highest segmentation performance on the Synapse, ACDC, ISIC-2018, and PH2 datasets while maintaining high efficiency, featuring the second-smallest parameters (14.05 M) and moderate computational complexity (8.94 GFLOPs).
Authors: Hao Ding, Yuqian Zhang, Tuxun Lu, Ruixing Liang, Hongchao Shu, Lalithkumar Seenivasan, Yonghao Long, Qi Dou, Cong Gao, Yicheng Leng, Seok Bong Yoo, Eung-Joo Lee, Negin Ghamsarian, Klaus Schoeffmann, Raphael Sznitman, Zijian Wu, Yuxin Chen, Septimiu E. Salcudean, Samra Irshad, Shadi Albarqouni, Seong Tae Kim, Yueyi Sun, An Wang, Long Bai, Hongliang Ren, Ihsan Ullah, Ho-Gun Ha, Attaullah Khan, Hyunki Lee, Satoshi Kondo, Satoshi Kasai, Kousuke Hirasawa, Sita Tailor, Ricardo Sanchez-Matilla, Imanol Luengo, Tianhao Fu, Jun Ma, Bo Wang, Marcos Fern\'andez-Rodr\'iguez, Estevao Lima, Jo\~ao L. Vila\c{c}a, Mathias Unberath
Abstract: Surgical data science has seen rapid advancement with the excellent performance of end-to-end deep neural networks (DNNs). Despite their successes, DNNs have been proven susceptible to minor "corruptions," introducing a major concern for the translation of cutting-edge technology, especially in high-stakes scenarios. We introduce the SegSTRONG-C challenge dedicated to better understanding model deterioration under unforeseen but plausible non-adversarial "corruption" and the capabilities of contemporary methods that seek to improve it. Built on a dataset generated through counterfactual robotic replay, SegSTRONG-C provides paired clean and "corrupted" samples, enabling reproducible evaluation of model robustness. Participants are challenged to train tool segmentation algorithms on "uncorrupted" data and evaluate them on "corrupted" test domains for the binary robot tool segmentation task. Through comprehensive baseline experiments and participating submissions from widespread community engagement, SegSTRONG-C reveals key themes for model failure and identifies promising directions for improving robustness. The performance of challenge winners, achieving an average 0.9394 DSC and 0.9301 NSD across the unreleased test sets with "corruption" types: bleeding, smoke, and low brightness. This highlights how prior knowledge, customized training strategies, and architectural choice can be leveraged to improve robustness. In conclusion, the SegSTRONG-C challenge has identified practical approaches for enhancing model robustness. However, most approaches rely on conventional techniques that have known limitations. Looking ahead, we advocate for expanding intellectual diversity and creativity in non-adversarial robustness beyond data augmentation, calling for new paradigms that enhance universal robustness to unforeseen "corruptions" to facilitate richer applications in surgical data science.
Authors: Haeil Lee, Hansang Lee, Seoyeon Gye, Junmo Kim
Abstract: Generative diffusion models have emerged as a powerful tool for high-quality image synthesis, yet their iterative nature demands significant computational resources. This paper proposes an efficient time step sampling method based on an image spectral analysis of the diffusion process, aimed at optimizing the denoising process. Instead of the traditional uniform distribution-based time step sampling, we introduce a Beta distribution-like sampling technique that prioritizes critical steps in the early and late stages of the process. Our hypothesis is that certain steps exhibit significant changes in image content, while others contribute minimally. We validated our approach using Fourier transforms to measure frequency response changes at each step, revealing substantial low-frequency changes early on and high-frequency adjustments later. Experiments with ADM and Stable Diffusion demonstrated that our Beta Sampling method consistently outperforms uniform sampling, achieving better FID and IS scores, and offers competitive efficiency relative to state-of-the-art methods like AutoDiffusion. This work provides a practical framework for enhancing diffusion model efficiency by focusing computational resources on the most impactful steps, with potential for further optimization and broader application.
Authors: Chenhao Ding, Xinyuan Gao, Songlin Dong, Jizhou Han, Qiang Wang, Zhengdong Zhou, Yuhang He, Yihong Gong
Abstract: Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more effective and efficient method for transferring VLMs to downstream tasks, surpassing traditional finetuning methods. However, during the transfer process, these models are prone to severe overfitting, leading to a significant decline in generalization ability. To address this issue, we propose a framework named LPT, specifically designed for vision-language models. Specifically, we use CLIP to filter out fine-grained foreground information that may lead to overfitting, thereby guiding the prompts with basic visual concepts. Additionally, to further mitigate overfitting, we have developed a Structural Preservation (SP) constraint at the feature level, which aligns the model's overall feature space structure with the frozen CLIP, endowing the feature space with overall plasticity and enabling effective reshaping of the feature space during optimization. Moreover, we employ Hierarchical Logit (HL) constraint at the output layer to constrain the overall class information in the output, complementing the role of SP at the output end. Extensive experiments across various benchmarks (from base-to-novel, cross-dataset transfer, and domain generalization) demonstrate that our approach significantly improves generalization capability and effectively alleviates overfitting compared to state-of-the-art methods.
Authors: Nhi Pham, Michael Schott
Abstract: By leveraging both texts and images, large vision language models (LVLMs) have shown significant progress in various multi-modal tasks. Nevertheless, these models often suffer from hallucinations, e.g., they exhibit inconsistencies between the visual input and the textual output. To address this, we propose H-POPE, a coarse-to-fine-grained benchmark that systematically assesses hallucination in object existence and attributes. Our evaluation shows that models are prone to hallucinations on object existence, and even more so on fine-grained attributes. We further investigate whether these models rely on visual input to formulate the output texts.
Authors: Qizao Wang, Bin Li, Xiangyang Xue
Abstract: Large Vision-Language Models (LVLMs) that incorporate visual models and large language models have achieved impressive results across cross-modal understanding and reasoning tasks. In recent years, person re-identification (ReID) has also started to explore cross-modal semantics to improve the accuracy of identity recognition. However, effectively utilizing LVLMs for ReID remains an open challenge. While LVLMs operate under a generative paradigm by predicting the next output word, ReID requires the extraction of discriminative identity features to match pedestrians across cameras. In this paper, we propose LVLM-ReID, a novel framework that harnesses the strengths of LVLMs to promote ReID. Specifically, we employ instructions to guide the LVLM in generating one semantic token that encapsulates key appearance semantics from the person image. This token is further refined through our Semantic-Guided Interaction (SGI) module, establishing a reciprocal interaction between the semantic token and visual tokens. Ultimately, the reinforced semantic token serves as the representation of pedestrian identity. Our framework integrates the semantic understanding and generation capabilities of LVLM into end-to-end ReID training, allowing LVLM to capture rich semantic cues during both training and inference. LVLM-ReID achieves competitive results on multiple benchmarks without additional image-text annotations, demonstrating the potential of LVLM-generated semantics to advance person ReID.
Authors: Ankit Dhiman, Tao Lu, R Srinath, Emre Arslan, Angela Xing, Yuanbo Xiangli, R Venkatesh Babu, Srinath Sridhar
Abstract: Novel-view synthesis plays a crucial role in computer vision with applications in 3D reconstruction, mixed reality, and robotics. Recent approaches, such as 3D Gaussian Splatting (3DGS), have emerged as state-of-the-art solutions, offering high-quality novel view synthesis in real time. However, training 3DGS models remains slow, particularly for high-resolution images, often requiring hours to fit a scene with 200 views. In this work, we aim to accelerate the fitting process by reducing computational overhead and improving learning efficiency. Specifically, we introduce a dilated rendering technique that renders only a subset of pixels instead of the full image, significantly reducing computational costs. To enhance learning efficiency, we develop a convergence-aware budget control mechanism that balances the addition of new Gaussians with the optimization of existing ones. Additionally, to improve densification efficiency and prevent gradient vanishing, we incorporate both positional and appearance errors to improve the effectiveness of densification. With these improvements, we achieve fast 4K-resolution fitting while maintaining, or even improving, novel view rendering quality. Extensive experiments demonstrate that our method achieves significantly faster optimization than existing approaches while preserving high rendering fidelity.
Authors: Lingzhi Yuan, Xinfeng Li, Chejian Xu, Guanhong Tao, Xiaojun Jia, Yihao Huang, Wei Dong, Yang Liu, Bo Li
Abstract: Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, these models are vulnerable to misuse, particularly generating not-safe-for-work (NSFW) content, such as sexually explicit, violent, political, and disturbing images, raising serious ethical concerns. In this work, we present PromptGuard, a novel content moderation technique that draws inspiration from the system prompt mechanism in large language models (LLMs) for safety alignment. Unlike LLMs, T2I models lack a direct interface for enforcing behavioral guidelines. Our key idea is to optimize a safety soft prompt that functions as an implicit system prompt within the T2I model's textual embedding space. This universal soft prompt (P*) directly moderates NSFW inputs, enabling safe yet realistic image generation without affecting inference efficiency or requiring proxy models. We further enhance its reliability and helpfulness through a divide-and-conquer strategy that optimizes category-specific soft prompts and combines them into unified safety guidance. Extensive experiments across five datasets demonstrate that PromptGuard effectively mitigates NSFW content generation while preserving high-quality benign outputs. PromptGuard is 3.8 times faster than prior content moderation methods while outperforming eight state-of-the-art defenses. Evaluations using both a multi-head safety classifier and a VLM-based guardrail further confirm its robustness, with average unsafe ratios of 5.84% and 6.18%, respectively. Our code and dataset are available at https://t2i-promptguard.github.io/.
Authors: Zibo Zhao (refer to the report for detailed contributions), Zeqiang Lai (refer to the report for detailed contributions), Qingxiang Lin (refer to the report for detailed contributions), Yunfei Zhao (refer to the report for detailed contributions), Haolin Liu (refer to the report for detailed contributions), Shuhui Yang (refer to the report for detailed contributions), Yifei Feng (refer to the report for detailed contributions), Mingxin Yang (refer to the report for detailed contributions), Sheng Zhang (refer to the report for detailed contributions), Xianghui Yang (refer to the report for detailed contributions), Huiwen Shi (refer to the report for detailed contributions), Sicong Liu (refer to the report for detailed contributions), Junta Wu (refer to the report for detailed contributions), Yihang Lian (refer to the report for detailed contributions), Fan Yang (refer to the report for detailed contributions), Ruining Tang (refer to the report for detailed contributions), Zebin He (refer to the report for detailed contributions), Xinzhou Wang (refer to the report for detailed contributions), Jian Liu (refer to the report for detailed contributions), Xuhui Zuo (refer to the report for detailed contributions), Zhuo Chen (refer to the report for detailed contributions), Biwen Lei (refer to the report for detailed contributions), Haohan Weng (refer to the report for detailed contributions), Jing Xu (refer to the report for detailed contributions), Yiling Zhu (refer to the report for detailed contributions), Xinhai Liu (refer to the report for detailed contributions), Lixin Xu (refer to the report for detailed contributions), Changrong Hu (refer to the report for detailed contributions), Shaoxiong Yang (refer to the report for detailed contributions), Song Zhang (refer to the report for detailed contributions), Yang Liu (refer to the report for detailed contributions), Tianyu Huang (refer to the report for detailed contributions), Lifu Wang (refer to the report for detailed contributions), Jihong Zhang (refer to the report for detailed contributions), Meng Chen (refer to the report for detailed contributions), Liang Dong (refer to the report for detailed contributions), Yiwen Jia (refer to the report for detailed contributions), Yulin Cai (refer to the report for detailed contributions), Jiaao Yu (refer to the report for detailed contributions), Jingwei Huang (refer to the report for detailed contributions), Yixuan Tang (refer to the report for detailed contributions), Hao Zhang (refer to the report for detailed contributions), Zheng Ye (refer to the report for detailed contributions), Peng He (refer to the report for detailed contributions), Runzhou Wu (refer to the report for detailed contributions), Chao Zhang (refer to the report for detailed contributions), Yonghao Tan (refer to the report for detailed contributions), Jie Xiao (refer to the report for detailed contributions), Yangyu Tao (refer to the report for detailed contributions), Jianchen Zhu (refer to the report for detailed contributions), Jinbao Xue (refer to the report for detailed contributions), Kai Liu (refer to the report for detailed contributions), Chongqing Zhao (refer to the report for detailed contributions), Xinming Wu (refer to the report for detailed contributions), Zhichao Hu (refer to the report for detailed contributions), Lei Qin (refer to the report for detailed contributions), Jianbing Peng (refer to the report for detailed contributions), Zhan Li (refer to the report for detailed contributions), Minghui Chen (refer to the report for detailed contributions), Xipeng Zhang (refer to the report for detailed contributions), Lin Niu (refer to the report for detailed contributions), Paige Wang (refer to the report for detailed contributions), Yingkai Wang (refer to the report for detailed contributions), Haozhao Kuang (refer to the report for detailed contributions), Zhongyi Fan (refer to the report for detailed contributions), Xu Zheng (refer to the report for detailed contributions), Weihao Zhuang (refer to the report for detailed contributions), YingPing He (refer to the report for detailed contributions), Tian Liu (refer to the report for detailed contributions), Yong Yang (refer to the report for detailed contributions), Di Wang (refer to the report for detailed contributions), Yuhong Liu (refer to the report for detailed contributions), Jie Jiang (refer to the report for detailed contributions), Chunchao Guo (refer to the report for detailed contributions)
Abstract: We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two foundation components: a large-scale shape generation model -- Hunyuan3D-DiT, and a large-scale texture synthesis model -- Hunyuan3D-Paint. The shape generative model, built on a scalable flow-based diffusion transformer, aims to create geometry that properly aligns with a given condition image, laying a solid foundation for downstream applications. The texture synthesis model, benefiting from strong geometric and diffusion priors, produces high-resolution and vibrant texture maps for either generated or hand-crafted meshes. Furthermore, we build Hunyuan3D-Studio -- a versatile, user-friendly production platform that simplifies the re-creation process of 3D assets. It allows both professional and amateur users to manipulate or even animate their meshes efficiently. We systematically evaluate our models, showing that Hunyuan3D 2.0 outperforms previous state-of-the-art models, including the open-source models and closed-source models in geometry details, condition alignment, texture quality, and etc. Hunyuan3D 2.0 is publicly released in order to fill the gaps in the open-source 3D community for large-scale foundation generative models. The code and pre-trained weights of our models are available at: https://github.com/Tencent/Hunyuan3D-2
Authors: Yu Feng, Dingxin Zhang, Runkai Zhao, Yong Xia, Heng Huang, Weidong Cai
Abstract: Backdoor attacks pose a severe threat to deep neural networks (DNNs) by implanting hidden backdoors that can be activated with predefined triggers to manipulate model behaviors maliciously. Recent studies have extended backdoor attacks to 3D point clouds, but most existing triggers are sample-wise and often cause visible geometric artifacts or high optimization cost. To address these limitations, we propose the Stealthy Patch-Wise Backdoor Attack (SPBA), a patch-wise backdoor attack framework for 3D point clouds. Specifically, SPBA decomposes a point cloud into local patches, where each patch is formed by a Farthest Point Sampling (FPS) center and its K-nearest neighbors (KNN). Candidate patches are ranked using a patch imperceptibility score derived from local curvature variation, and a unified spectral trigger is injected into the selected patches by perturbing only the coordinates of existing points while preserving the original point cardinality. Extensive experiments on ModelNet40 and ShapeNetPart further demonstrate that SPBA achieves state-of-the-art stealthiness among prior methods and reduces spectral-trigger computation by 98.43% relative to a sample-wise spectral baseline, while maintaining competitive attack performance. These results support localized spectral design as an effective and efficient approach to stealthy backdoor attacks in 3D point cloud models. Code is available at https://github.com/HazardFY/SPBA.
Authors: Patrick Rim, Hyoungseob Park, Vadim Ezhov, Jeffrey Moon, Alex Wong
Abstract: We propose POLAR, a novel radar-guided depth estimation method that introduces polynomial fitting to efficiently transform scaleless depth predictions from pretrained monocular depth estimation (MDE) models into metric depth maps. Unlike existing approaches that rely on complex architectures or expensive sensors, our method is grounded in a fundamental insight: although MDE models often infer reasonable local depth structure within each object or local region, they may misalign these regions relative to one another, making a linear scale and shift (affine) transformation insufficient given three or more of these regions. To address this limitation, we use polynomial coefficients predicted from cheap, ubiquitous radar data to adaptively adjust predictions non-uniformly across depth ranges. In this way, POLAR generalizes beyond affine transformations and is able to correct such misalignments by introducing inflection points. Importantly, our polynomial fitting framework preserves structural consistency through a novel training objective that enforces local monotonicity via first-derivative regularization. POLAR achieves state-of-the-art performance across three datasets, outperforming existing methods by an average of 24.9% in MAE and 33.2% in RMSE, while also achieving state-of-the-art efficiency in terms of latency and computational cost.
Authors: Olivier Rukundo
Abstract: Avoiding the risk of undefined categorical labels using nearest neighbor interpolation overlooks the risk of exacerbating pixel level annotation errors in augmented training data. Additionally, the inherent low pass filtering effects of interpolation algorithms exacerbate the risk of degrading high frequency structural details within annotated regions of interest. To avoid these risks, the author modified convolutional neural networks data transformation functions by incorporating a modified geometric transformation function, removing reliance on nearest neighbor interpolation, and integrating a mean-based class filtering mechanism to handle undefined categorical labels with alternative interpolation algorithms. The author also implemented an offline data augmentation pipeline to generate interpolation specific augmented training data, enabling quantitative assessment of interpolation specific low pass filtering effects on augmented training data. Experimental evaluation on three medical image segmentation datasets and the XBAT datasets demonstrated performance gains across multiple quantitative metrics.
Authors: Haizhen Xie, Kunpeng Du, Qiangyu Yan, Sen Lu, Jianhong Han, Hanting Chen, Hailin Hu, Jie Hu
Abstract: Utilizing pre-trained Text-to-Image (T2I) diffusion models to guide Blind Super-Resolution (BSR) has become a predominant approach in the field. While T2I models have traditionally relied on U-Net architectures, recent advancements have demonstrated that Diffusion Transformers (DiT) achieve significantly higher performance in this domain. In this work, we introduce Enhancing Anything Model (EAM), a novel BSR method that leverages DiT and outperforms previous U-Net-based approaches. We introduce a novel block, $\Psi$-DiT, which effectively guides the DiT to enhance image restoration. This block employs a low-resolution latent as a separable flow injection control, forming a triple-flow architecture that effectively leverages the prior knowledge embedded in the pre-trained DiT. To fully exploit the prior guidance capabilities of T2I models and enhance their generalization in BSR, we introduce a progressive Masked Image Modeling strategy, which also reduces training costs. Additionally, we propose a subject-aware prompt generation strategy that employs a robust multi-modal model in an in-context learning framework. This strategy automatically identifies key image areas, provides detailed descriptions, and optimizes the utilization of T2I diffusion priors. Our experiments demonstrate that EAM achieves state-of-the-art results across multiple datasets, outperforming existing methods in both quantitative metrics and visual quality.
Authors: Yue Fan, Xuehai He, Diji Yang, Kaizhi Zheng, Ching-Chen Kuo, Yuting Zheng, Sravana Jyothi Narayanaraju, Xinze Guan, Xin Eric Wang
Abstract: Recent studies have demonstrated the efficacy of using Reinforcement Learning (RL) in building reasoning models that articulate chains of thoughts prior to producing final answers. However, despite ongoing advances that aim at enabling reasoning for vision-language tasks, existing open-source visual reasoning models typically generate reasoning content with pure natural language, lacking explicit integration of visual information. This limits their ability to produce clearly articulated and visually grounded reasoning chains. To this end, we propose Grounded Reasoning with Images and Texts (GRIT), a novel method for training MLLMs to think with images. GRIT introduces a grounded reasoning paradigm, in which models generate reasoning chains that interleave natural language and explicit bounding box coordinates. These coordinates point to regions of the input image that the model consults during its reasoning process. Additionally, GRIT is equipped with a reinforcement learning approach, GRPO-GR, built upon the GRPO algorithm. GRPO-GR employs robust rewards focused on the final answer accuracy and format of the grounded reasoning output, which eliminates the need for data with reasoning chain annotations or explicit bounding box labels. As a result, GRIT achieves exceptional data efficiency, requiring as few as 20 image-question-answer triplets from existing datasets. Comprehensive evaluations demonstrate that GRIT effectively trains MLLMs to produce coherent and visually grounded reasoning chains, showing a successful unification of reasoning and grounding abilities.
Authors: Wen Wen, Yaohong Wu, Yue Sheng, Neil Birkbeck, Balu Adsumilli, Yilin Wang
Abstract: Video quality assessment (VQA) is a challenging research topic with broad applications. Traditional hand-crafted and discriminative learning-based VQA models mainly focus on pixel-level distortions and lack contextual understanding, while recent multimodal large language models (MLLMs) struggle with sensitivity to small distortions or handle quality scoring and description as separate tasks. To address these shortcomings, we introduce CP-LLM: a Context- and Pixel-aware Large Language Model. CP-LLM is a novel multimodal LLM architecture featuring dual vision encoders designed to independently analyze perceptual quality at both high-level (video context) and low-level (pixel distortion) granularity, along with a language decoder that subsequently reasons about the interplay between these aspects. This design enables CP-LLM to simultaneously produce robust quality scores and interpretable quality descriptions, with enhanced sensitivity to pixel distortions (e.g., compression artifacts). Experiment results demonstrate that CP-LLM achieves state-of-the-art cross-dataset performance on VQA benchmarks and superior robustness to pixel distortions.
Authors: Gihoon Kim, Hyungjin Park, Taesup Kim
Abstract: Personalizing text-to-image diffusion models involves integrating novel visual concepts from a small set of reference images while retaining the model's original generative capabilities. However, this process often leads to overfitting, where the model ignores the user's prompt and merely replicates the reference images. We attribute this issue to a fundamental misalignment between the true goals of personalization, which are subject fidelity and text alignment, and the training objectives of existing methods that fail to enforce both objectives simultaneously. Specifically, prior approaches often overlook the need to explicitly preserve the pretrained model's output distribution, resulting in distributional drift that undermines diversity and coherence. To resolve these challenges, we introduce a Lipschitz-based regularization objective that constrains parameter updates during personalization, ensuring bounded deviation from the original distribution. This promotes consistency with the pretrained model's behavior while enabling accurate adaptation to new concepts. Furthermore, our method offers a computationally efficient alternative to commonly used, resource-intensive sampling techniques. Through extensive experiments across diverse diffusion model architectures, we demonstrate that our approach achieves superior performance in both quantitative metrics and qualitative evaluations, consistently excelling in visual fidelity and prompt adherence. We further support these findings with comprehensive analyses, including ablation studies and visualizations.
Authors: Shihao Li, Huaibo Huang, Junxian Duan, Aihua Zheng, Jin Tang, Jixin Ma
Abstract: Multi-modal object Re-IDentification (ReID) aims to obtain complete identity features across heterogeneous modalities. However, most existing methods rely on implicit feature fusion modules, making it difficult to model fine-grained recognition patterns under various challenges in real world. Benefiting from the powerful Multi-modal Large Language Models (MLLMs), the object appearances are effectively translated into descriptive captions. In this paper, we propose a reliable caption generation pipeline based on attribute confidence, which significantly reduces the unknown recognition rate of MLLMs and improves the quality of generated text. Additionally, to model diverse identity patterns, we propose a novel ReID framework, named NEXT, the Multi-grained Mixture of Experts via Text-Modulation for Multi-modal Object Re-Identification. Specifically, we decouple the recognition problem into semantic and structural branches to separately capture fine-grained appearance features and coarsegrained structure features. For semantic recognition, we first propose a Text-Modulated Semantic Experts (TMSE), which randomly samples high-quality captions to modulate experts capturing semantic features and mining inter-modality complementary cues. Second, to recognize structure features, we propose a Context-Shared Structure Experts (CSSE), which focuses on the holistic object structure and maintains identity structural consistency via a soft routing mechanism. Finally, we propose a Multi-Grained Features Aggregation (MGFA), which adopts a unified fusion strategy to effectively integrate multi-grained expert features into the final identity representations. Extensive experiments on two public person datasets and three vehicle datasets demonstrate the effectiveness of our method, showing that it significantly outperforms existing state-of-the-art methods.
Authors: Sijia Chen, Yanqiu Yu, En Yu, Wenbing Tao
Abstract: Referring Multi-Object Tracking (RMOT) aims to track targets specified by language instructions. However, existing RMOT paradigms heavily rely on explicit visual-textual matching and consequently fail to generalize to complex instructions that require logical reasoning. To overcome this, we propose Reasoning-based Multi-Object Tracking (ReaMOT), a novel task that elevates tracking to a cognitive level, requiring models to infer and track specific targets satisfying implicit constraints via logical reasoning. To advance this field, we construct the ReaMOT Challenge, a comprehensive benchmark featuring a tailored metric suite and a large scale dataset. This dataset comprises 1,156 language instructions, 423,359 image language pairs, and 869 distinct video sequences systematically categorized into six distinct evaluation scenarios, with over 75\% of the instructions dedicated to High Level Reasoning. Furthermore, recognizing that traditional trackers lack cognitive capacity while direct application of Large Vision-Language Model (LVLM) yields severe temporal inconsistencies, we propose ReaTrack. Driven by the insight to decouple high-level cognitive localization from low-level physical motion continuity, this training-free framework dynamically aligns the semantic detections of a Thinking-variant LVLM with the robust motion priors of SAM2. Extensive experiments on the ReaMOT Challenge benchmark demonstrate that ReaTrack establishes a new leading performance standard. Notably, it achieves a more than threefold improvement in RHOTA on the High Level Reasoning subset. Our dataset and code will be available at https://github.com/chen-si-jia/ReaMOT.
Authors: Chenhao Zheng, Jieyu Zhang, Mohammadreza Salehi, Ziqi Gao, Vishnu Iyengar, Norimasa Kobori, Quan Kong, Ranjay Krishna
Abstract: Effective video tokenization is critical for scaling transformer models for long videos. Current approaches tokenize videos using space-time patches, leading to excessive tokens and computational inefficiencies. The best token reduction strategies degrade performance and barely reduce the number of tokens when the camera moves. We introduce grounded video tokenization, a paradigm that organizes tokens based on panoptic sub-object trajectories rather than fixed patches. Our method aligns with fundamental perceptual principles, ensuring that tokenization reflects scene complexity rather than video duration. We propose TrajViT, a video encoder that extracts object trajectories and converts them into semantically meaningful tokens, significantly reducing redundancy while maintaining temporal coherence. Trained with contrastive learning, TrajViT significantly outperforms space-time ViT (ViT3D) across multiple video understanding benchmarks, e.g., TrajViT outperforms ViT3D by a large margin of 6% top-5 recall in average at video-text retrieval task with 10x token deduction. We also show TrajViT as a stronger model than ViT3D for being the video encoder for modern VideoLLM, obtaining an average of 5.2% performance improvement across 6 VideoQA benchmarks while having 4x faster training time and 18x less inference FLOPs. TrajViT is the first efficient encoder to consistently outperform ViT3D across diverse video analysis tasks, making it a robust and scalable solution.
Authors: Guangrui Bai, Hailong Yan, Wenhai Liu, Yahui Deng, Erbao Dong
Abstract: Real-time low-light image enhancement on mobile and embedded devices requires models that balance visual quality and computational efficiency. Existing deep learning methods often rely on large networks and labeled datasets, limiting their deployment on resource-constrained platforms. In this paper, we propose LiteIE, an ultra-lightweight unsupervised enhancement framework that eliminates dependence on large-scale supervision and generalizes well across diverse conditions. We design a backbone-agnostic feature extractor with only two convolutional layers to produce compact image features enhancement tensors. In addition, we develop a parameter-free Iterative Restoration Module, which reuses the extracted features to progressively recover fine details lost in earlier enhancement steps, without introducing any additional learnable parameters. We further propose an unsupervised training objective that integrates exposure control, edge-aware smoothness, and multi-scale color consistency losses. Experiments on the LOL dataset, LiteIE achieves 19.04 dB PSNR, surpassing SOTA by 1.4 dB while using only 0.07\% of its parameters. On a Snapdragon 8 Gen 3 mobile processor, LiteIE runs at 30 FPS for 4K images with just 58 parameters, enabling real-time deployment on edge devices. These results establish LiteIE as an efficient and practical solution for low-light enhancement on resource-limited platforms.
Authors: Konstantinos Foteinos, Manousos Linardakis, Panagiotis Radoglou-Grammatikis, Vasileios Argyriou, Panagiotis Sarigiannidis, Iraklis Varlamis, Georgios Th. Papadopoulos
Abstract: The rapid evolution of deep learning (DL) models and the ever-increasing size of available datasets have raised the interest of the research community in the always-important field of visual hand gesture recognition (VHGR), and delivered a wide range of applications, such as sign language understanding and human-computer interaction. Despite the large volume of research works in the field, a structured and complete survey on VHGR is still missing, leaving researchers to navigate through hundreds of papers in order to find the current state-of-the-art (SOTA). The current survey aims to fill this gap by presenting a comprehensive overview of this computer vision field. With a systematic research methodology and a structured presentation of the various methods, datasets, and evaluation metrics, this review aims to constitute a useful guideline for researchers, helping them to propose improvements. Specifically, this survey focuses on four fundamental questions: what are the main VHGR aspects, what are the current SOTA methods, what comparative insights can be drawn across methods and tasks, and which challenges shape future research. Starting with the methodology used to locate the related literature, the survey identifies and organizes the key VHGR approaches in a taxonomy-based format. The SOTA methods are grouped across three primary VHGR tasks: static, isolated dynamic and continuous gesture recognition. For each task, the architectural trends and learning strategies are listed. To support the experimental evaluation of future methods in the field, the study reviews commonly used datasets and presents the standard performance metrics. Our survey concludes by identifying the major challenges in VHGR, including both general computer vision issues and domain-specific obstacles, and outlines promising directions for future research.
Authors: Andrii Yermakov, Jan Cech, Jiri Matas, Mario Fritz
Abstract: The generalization of deepfake detectors to unseen manipulation techniques remains a challenge for practical deployment. Although many approaches adapt foundation models by introducing significant architectural complexity, this work demonstrates that robust generalization is achievable through a parameter-efficient adaptation of one of the foundational pre-trained vision encoders. The proposed method, GenD, fine-tunes only the Layer Normalization parameters (0.03% of the total) and enhances generalization by enforcing a hyperspherical feature manifold using L2 normalization and metric learning on it. We conducted an extensive evaluation on 14 benchmark datasets spanning from 2019 to 2025. The proposed method achieves state-of-the-art performance, outperforming more complex, recent approaches in average cross-dataset AUROC. Our analysis yields two primary findings for the field: 1) training on paired real-fake data from the same source video is essential for mitigating shortcut learning and improving generalization, and 2) detection difficulty on academic datasets has not strictly increased over time, with models trained on older, diverse datasets showing strong generalization capabilities. This work delivers a computationally efficient and reproducible method, proving that state-of-the-art generalization is attainable by making targeted, minimal changes to a pre-trained foundational image encoder model. The code is at: https://github.com/yermandy/GenD
Authors: Juangui Xu, Zikun Guo, Jingwei Lv, Xinyue Xu, Hongbin Lin, Shu Yang, Jun Wen, Di Wang, Lijie Hu
Abstract: Visual language models (VLMs) have the potential to transform medical workflows. However, the deployment is limited by sycophancy. Despite this serious threat to patient safety, a systematic benchmark remains lacking. This paper addresses this gap by introducing a Medical benchmark that applies multiple templates to VLMs in a hierarchical medical visual question answering task. We find that current VLMs are highly susceptible to visual cues, with failure rates showing a correlation to model size or overall accuracy. we discover that perceived authority and user mimicry are powerful triggers, suggesting a bias mechanism independent of visual data. To overcome this, we propose a Visual Information Purification for Evidence based Responses (VIPER) strategy that proactively filters out non-evidence-based social cues, thereby reinforcing evidence based reasoning. VIPER reduces sycophancy while maintaining interpretability and consistently outperforms baseline methods, laying the necessary foundation for the robust and secure integration of VLMs.
Authors: Xiaoyu Yang, En Yu, Wei Duan, Jie Lu
Abstract: This paper identifies a critical yet underexplored challenge in reasoning alignment from multiple multi-modal large language models (MLLMs): In non-stationary environments, the diverse reasoning distributions of source models often evolve unpredictably, transmitting systematic biases and drift to the target model. To address this, we formulate multi-source reasoning alignment as a constraint satisfaction problem under concept drift theory. We propose Autonomous Preference Optimization (APO), a novel framework that treats inter-model divergences not as noise, but as dynamic negative constraints. APO operates via a two-stage protocol: first, supervised bootstrapping projects the target model into the capability union of source models; second, constraint-aware optimization synthesizes a consistent consensus manifold by explicitly suppressing drifting trajectories via a multi-negative Plackett-Luce objective. Extensive experiments on chest X-ray interpretation demonstrate that our 7B model achieves superior robustness, outperforming even proprietary source models in average accuracy. Furthermore, we release CXR-MAX, a large-scale benchmark comprising 170,982 reasoning trajectories from seven large-scale MLLMs to facilitate research on reasoning alignment under drift. Code and data are available at: https://github.com/XiaoyuYoung/APO.
Authors: Yuqi Liu, Liangyu Chen, Jiazhen Liu, Mingkang Zhu, Zhisheng Zhong, Bei Yu, Jiaya Jia
Abstract: Post-training Large Vision-and-Language Models (LVLMs) typically involves Supervised Fine-Tuning (SFT) for knowledge injection or Reinforcement Learning with Verifiable Rewards (RLVR) for performance enhancement. However, SFT often leads to sub-optimal performance, while RLVR remains constrained by the model's internal knowledge base. While a sequential SFT $\rightarrow$ RLVR pipeline can be used, it introduces significant computational overhead and suffers from catastrophic forgetting. To address these limitations, we propose ViSurf (\textbf{Vi}sual \textbf{Su}pervised-and-\textbf{R}einforcement \textbf{F}ine-Tuning), a unified, single-stage paradigm that integrates the strengths of both SFT and RLVR. By analyzing their training objectives, we establish a unified framework that injects ground-truth labels directly into RLVR rollouts, facilitating simultaneous external supervision and internal reinforcement. Furthermore, we introduce three novel reward control strategies to ensure training stability and optimization. Extensive experiments demonstrate that ViSurf consistently outperforms standalone SFT, RLVR, and the traditional two-stage pipeline across diverse benchmarks. In-depth analysis corroborates these findings, validating the derivation and design principles of ViSurf.
Authors: M Yashwanth, Sharannya Ghosh, Aditay Tripathi, Anirban Chakraborty
Abstract: Visual Prompt Tuning (VPT) of pre-trained Vision Transformers (ViTs) has proven highly effective as a parameter-efficient fine-tuning technique for adapting large models to downstream tasks with limited data. Its parameter efficiency makes it particularly suitable for Federated Learning (FL), where both communication and computation budgets are often constrained. However, global prompt tuning struggles to generalize across heterogeneous clients, while personalized tuning overfits to local data and lacks generalization. We propose PEP-FedPT (Prompt Estimation from Prototypes for Federated Prompt Tuning), a unified framework designed to achieve both generalization and personalization in federated prompt tuning of ViTs. Within this framework, we introduce the novel Class-Contextualized Mixed Prompt (CCMP) - based on class-specific prompts maintained alongside a globally shared prompt. For each input, CCMP adaptively combines class-specific prompts using weights derived from global class prototypes and client class priors. This approach enables per-sample prompt personalization without storing client-dependent trainable parameters. The prompts are collaboratively optimized via traditional federated averaging technique on the same. Comprehensive evaluations on CIFAR-100, TinyImageNet, DomainNet, and iNaturalist datasets demonstrate that PEP-FedPT consistently surpasses the state-of-the-art baselines under diverse data heterogeneity scenarios, establishing a strong foundation for efficient and generalizable federated prompt tuning of Vision Transformers.
Authors: Chun-Tin Wu, Jun-Cheng Chen
Abstract: Although 3D Gaussian Splatting (3D-GS) achieves efficient rendering for novel view synthesis, extending it to dynamic scenes still results in substantial memory overhead from replicating Gaussians across frames. To address this challenge, we propose 4D Neural Voxel Splatting (4D-NVS), which combines voxel-based representations with neural Gaussian splatting for efficient dynamic scene modeling. Instead of generating separate Gaussian sets per timestamp, our method employs a compact set of neural voxels with learned deformation fields to model temporal dynamics. The design greatly reduces memory consumption and accelerates training while preserving high image quality. We further introduce a novel view refinement stage that selectively improves challenging viewpoints through targeted optimization, maintaining global efficiency while enhancing rendering quality for difficult viewing angles. Experiments demonstrate that our method outperforms state-of-the-art approaches with significant memory reduction and faster training, enabling real-time rendering with superior visual fidelity.
Authors: Junyi Ma, Wentao Bao, Jingyi Xu, Guanzhong Sun, Yu Zheng, Erhang Zhang, Xieyuanli Chen, Hesheng Wang
Abstract: Forecasting how human hands move in egocentric views is critical for applications like augmented reality and human-robot policy transfer. Recently, several hand trajectory prediction (HTP) methods have been developed to generate future possible hand waypoints, which still suffer from insufficient prediction targets, inherent modality gaps, entangled hand-head motion, and limited validation in downstream tasks. To address these limitations, we present a universal hand motion forecasting framework considering multi-modal input, multi-dimensional and multi-target prediction patterns, and multi-task affordances for downstream applications. We harmonize multiple modalities by vision-language fusion, global context incorporation, and task-aware text embedding injection, to forecast hand waypoints in both 2D and 3D spaces. A novel dual-branch diffusion is proposed to concurrently predict human head and hand movements, capturing their motion synergy in egocentric vision. By introducing target indicators, the prediction model can forecast the specific joint waypoints of the wrist or the fingers, besides the widely studied hand center points. In addition, we enable Uni-Hand to additionally predict hand-object interaction states (contact/separation) to facilitate downstream tasks better. As the first work to incorporate downstream task evaluation in the literature, we build novel benchmarks to assess the real-world applicability of hand motion forecasting algorithms. The experimental results on multiple publicly available datasets and our newly proposed benchmarks demonstrate that Uni-Hand achieves the state-of-the-art performance in multi-dimensional and multi-target hand motion forecasting. Extensive validation in multiple downstream tasks also presents its impressive human-robot policy transfer to enable robotic manipulation, and effective feature enhancement for action anticipation/recognition.
Authors: Shuo Ni, Di Wang, He Chen, Haonan Guo, Ning Zhang, Jing Zhang
Abstract: Instruction-driven segmentation in remote sensing generates masks from guidance, offering great potential for accessible and generalizable applications. However, existing methods suffer from fragmented task formulations and limited instruction data, hindering effective understanding and generalization. To address these issues, we introduce GeoSeg-1M, the first million-scale dataset for remote sensing instruction-driven segmentation, constructed via an automatic mask filtering and instruction generation pipeline that synthesizes referring, interactive, and reasoning segmentation instructions from multiple public datasets. GeoSeg-1M contains 590K images, 117 categories, and 1.1M image-mask-instruction triplets. Building upon this foundation, we further curate GeoSeg-Bench, a challenging benchmark designed to evaluate contextual understanding and reasoning capabilities across diverse instruction-driven tasks and complex geospatial scenes. Furthermore, we present UniGeoSeg, a unified framework that serves as a strong baseline, incorporating task-aware text enhancement, latent knowledge memory, and a progressive training strategy to facilitate multi-task learning. Extensive experiments demonstrate the state-of-the-art performance of UniGeoSeg across GeoSeg-Bench and diverse public benchmarks, while exhibiting strong zero-shot generalization. Datasets and source code were released at https://github.com/MiliLab/UniGeoSeg.
Authors: Zhengyang Geng, Yiyang Lu, Zongze Wu, Eli Shechtman, J. Zico Kolter, Kaiming He
Abstract: MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key challenges in both the training objective and the guidance mechanism. First, the original MF's training target depends not only on the underlying ground-truth fields but also on the network itself. To address this issue, we recast the objective as a loss on the instantaneous velocity $v$, re-parameterized by a network that predicts the average velocity $u$. Our reformulation yields a more standard regression problem and improves the training stability. Second, the original MF fixes the classifier-free guidance scale during training, which sacrifices flexibility. We tackle this issue by formulating guidance as explicit conditioning variables, thereby retaining flexibility at test time. The diverse conditions are processed through in-context conditioning, which reduces model size and benefits performance. Overall, our $\textbf{improved MeanFlow}$ ($\textbf{iMF}$) method, trained entirely from scratch, achieves $\textbf{1.72}$ FID with a single function evaluation (1-NFE) on ImageNet 256$\times$256. iMF substantially outperforms prior methods of this kind and closes the gap with multi-step methods while using no distillation. We hope our work will further advance fastforward generative modeling as a stand-alone paradigm.
Authors: Shida Gao, Feng Xue, Xiangfeng Wang, Anlong Ming, Zhaowen Lin, Haiyang Zhang, Teng Long, Nicu Sebe, Yihua Shao, Haozhe Wang, Wei Wang
Abstract: Multimodal large language models (MLLMs) are rapidly expanding from general video understanding to finer-grained understanding such as spatio-temporal video grounding (STVG) and reasoning. In these tasks, an MLLM must localize the user-queried target in time and space and take the results as evidence for reasoning. Existing MLLM methods mainly follow two paradigms: (1) Direct Localization, which outputs STVG results with extra alignment modules or specialized decoders; and (2) Candidate-based Selection, which first constructs tube-level candidates and then selects the relevant one by an MLLM. However, both suffer from a serious efficiency bottleneck: the former incurs linearly growing decoding cost as the queried temporal span increases, while the latter relies on costly candidate construction. To break this bottleneck, we propose DEViL, a detector-empowered Video-LLM with a simple key idea: offloading dense spatial grounding from the MLLM to a fully parallelizable, well-trained detector. Specifically, DEViL distills the query into a detector-compatible reference-semantic token, which replaces the detector's text embedding to enable spatial grounding in a single pass. Then, we design temporal consistency regularization to match objects across frames and enforce their coherence over time. In this way, DEViL avoids long coordinate decoding and heavy candidate pipelines. Extensive experiments show that DEViL achieves strong performance (43.1% m_vIoU on HC-STVG) with superior efficiency (14.33 FPS), while preserving the general reasoning capacity of the MLLM backbone.
Authors: Shravan Venkatraman, Muthu Subash Kavitha, Joe Dhanith P R, V Manikandarajan, Jia Wu
Abstract: Histopathology image segmentation is essential for delineating tissue structures in skin cancer diagnostics, but modeling spatial context and inter-tissue relationships remains a challenge, especially in regions with overlapping or morphologically similar tissues. Current convolutional neural network (CNN)-based approaches operate primarily on visual texture, often treating tissues as independent regions and failing to encode biological context. To this end, we introduce Neural Tissue Relation Modeling (NTRM), a novel segmentation framework that augments CNNs with a tissue-level graph neural network to model spatial and functional relationships across tissue types. NTRM constructs a graph over predicted regions, propagates contextual information via message passing, and refines segmentation through spatial projection. Unlike prior methods, NTRM explicitly encodes inter-tissue dependencies, enabling structurally coherent predictions in boundary-dense zones. On the benchmark Histopathology Non-Melanoma Skin Cancer Segmentation Dataset, NTRM outperforms state-of-the-art methods, achieving a robust Dice similarity coefficient that is 4.9\% to 31.25\% higher than the best-performing models among the evaluated approaches. Our experiments indicate that relational modeling offers a principled path toward more context-aware and interpretable histological segmentation, compared to local receptive-field architectures that lack tissue-level structural awareness. Our code is available at https://github.com/shravan-18/NTRM.
Authors: Nirhoshan Sivaroopan, Hansi Karunarathna, Chamara Madarasingha, Anura Jayasumana, Kanchana Thilakarathna
Abstract: Human Activity Recognition (HAR) underpins applications in healthcare, rehabilitation, fitness tracking, and smart environments, yet existing deep learning approaches demand dataset-specific training, large labeled corpora, and significant computational resources.We introduce RAG-HAR, a training-free retrieval-augmented framework that leverages large language models (LLMs) for HAR. RAG-HAR computes lightweight statistical descriptors, retrieves semantically similar samples from a vector database, and uses this contextual evidence to make LLM-based activity identification. We further enhance RAG-HAR by first applying prompt optimization and introducing an LLM-based activity descriptor that generates context-enriched vector databases for delivering accurate and highly relevant contextual information. Along with these mechanisms, RAG-HAR achieves state-of-the-art performance across six diverse HAR benchmarks. Most importantly, RAG-HAR attains these improvements without requiring model training or fine-tuning, emphasizing its robustness and practical applicability. RAG-HAR moves beyond known behaviors, enabling the recognition and meaningful labelling of multiple unseen human activities.
Authors: Jingchao Wu, Zejian Kang, Haibo Liu, Yuanchen Fei, Xiangru Huang
Abstract: Facial animation is a core component for creating digital characters in Computer Graphics (CG) industry. A typical production workflow relies on sparse, semantically meaningful keyframes to precisely control facial expressions. Enabling such animation directly from natural-language descriptions could significantly improve content creation efficiency and accessibility. However, most existing methods adopt a text-to-continuous-frames paradigm, directly regressing dense facial motion trajectories from language. This formulation entangles high-level semantic intent with low-level motion, lacks explicit semantic control structure, and limits precise editing and interpretability. Inspired by the keyframe paradigm in animation production, we propose KeyframeFace, a framework for semantic facial animation from language via interpretable keyframes. Instead of predicting dense motion trajectories, our method represents animation as a sequence of semantically meaningful keyframes in an interpretable ARKit-based facial control space. A language-driven model leverages large language model (LLM) priors to generate keyframes that align with contextual text descriptions and emotion cues. To support this formulation, we construct a multimodal dataset comprising 2,100 expression scripts paired with monocular videos, per-frame ARKit coefficients, and manually annotated semantic keyframes. Experiments show that incorporating semantic keyframe supervision and language priors significantly improves expression fidelity and semantic alignment compared to methods that do not use facial action semantics.
Authors: Earl Ranario, Mason J. Earles
Abstract: Vision-language models (VLMs) are increasingly proposed as general-purpose solutions for visual recognition tasks, yet their reliability for agricultural decision support remains poorly understood. We benchmark a diverse set of open-source and closed-source VLMs on 27 agricultural image classification datasets from the AgML collection (https://github.com/Project-AgML), spanning 162 classes and 248,000 images across plant disease, pest and damage, and plant and weed species identification. Across all tasks, zero-shot VLMs substantially underperform a supervised task-specific baseline (YOLO11), which consistently achieves markedly higher accuracy than any foundation model. Under multiple-choice prompting, the best-performing VLM (Gemini-3 Pro) reaches approximately 62% average accuracy, while open-ended prompting yields much lower performance, with raw accuracies typically below 25%. Applying LLM-based semantic judging increases open-ended accuracy (e.g., from ~21% to ~30% for top models) and alters model rankings, demonstrating that evaluation methodology meaningfully affects reported conclusions. Among open-source models, Qwen-VL-72B performs best, approaching closed-source performance under constrained prompting but still trailing top proprietary systems. Task-level analysis shows that plant and weed species classification is consistently easier than pest and damage identification, which remains the most challenging category across models. Overall, these results indicate that current off-the-shelf VLMs are not yet suitable as standalone agricultural diagnostic systems, but can function as assistive components when paired with constrained interfaces, explicit label ontologies, and domain-aware evaluation strategies.
Authors: Hengyi Feng, Zeang Sheng, Meiyi Qiang, Yang Li, Wentao Zhang
Abstract: Despite the remarkable success of multimodal large language models (MLLMs) in generative tasks, we observe that they exhibit a counterintuitive deficiency in the zero-shot multimodal retrieval task. In this work, we investigate the underlying mechanisms that hinder MLLMs from being effective retrievers. With the help of sparse autoencoders (SAEs), we decompose MLLM output representations into interpretable semantic concepts to probe their intrinsic behavior. Our analysis reveals that the representation space of MLLMs is overwhelmingly dominated by textual semantics; and the visual semantics essential for multimodal retrieval only constitute a small portion. We find that this imbalance is compounded by the heavy focus of MLLMs on bridging image-text modalities, which facilitates generation but homogenizes embeddings and finally diminishes the discriminative power required for multimodal retrieval. We further discover that the specific feature components that contribute most to the similarity computations of MLLMs are actually distractors that greatly reduce retrieval performance. Building on these insights, we propose ReAlign, a test-time adaptation approach that applies a whitening transformation to adjust the geometry of MLLM representation spaces. Empirical results show that this simple intervention consistently improves zero-shot multimodal retrieval performance across diverse MLLMs without fine-tuning efforts. The code is available at https://github.com/Heinz217/mllm-retrieval-analysis.
Authors: Tiange Luo, Lajanugen Logeswaran, Jaekyeom Kim, Justin Johnson, Honglak Lee
Abstract: Low-rank adaptation (LoRA) is widely used for parameter-efficient fine-tuning, but its standard all-token, all-head design ignores the heterogeneous structure of vision language model (VLM) inputs. We introduce \emph{Image-LoRA}, a vision-oriented PEFT recipe that views LoRA as a token-level residual update and applies this update only to visual tokens. Image-LoRA further restricts adaptation to the value path of a compact subset of attention heads, selected using a one-pass influence estimate from a rank-1 visual-token-only probe. This token-, head-, and value-selective design reduces trainable parameters and adapter-only training FLOPs while leaving the pure-text forward pass of the frozen backbone unchanged when no visual tokens are present. Across visual localization benchmarks with controlled text:image token ratios, Image-LoRA matches or closely approaches standard LoRA, while showing especially favorable trade-offs in image-token-heavy regimes. We further validate its generality on TextVQA and VideoQA, verify pure-text preservation on GSM8K, and show on ViLP that a stronger information bottleneck can yield gains over standard LoRA.
Authors: Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang
Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM reliability. While prior entropy-based attacks maximize uncertainty at all decoding steps, implicitly assuming that every token equally contributes to model instability, we reveal that a small fraction (around 20%) of high-entropy tokens, in the evaluated representative open-source VLMs with diverse architectures, concentrates a disproportionate share of adversarial influence during autoregressive generation. We demonstrate that concentrating adversarial perturbations on these high-entropy positions achieves comparable semantic degradation to global methods while optimizing fewer decoding positions. Additionally, across multiple representative VLMs, such attacks induce not only semantic drift but also a substantial unsafe subset (20-31%) under the current pipeline. Remarkably, since such vulnerable high-entropy tokens recur across architecturally diverse VLMs, attacks focused on them exhibit non-trivial transferability. Motivated by these findings, we design a simple Entropy-Guided Attack (EGA) that operationalizes sparse high-entropy targeting and extends it with a reusable token bank, yielding competitive attack success rates (93-95%) with a considerable harmful rate (30.2-38.6%) on the three representative open-source VLMs.
Authors: Jindi Zhong, Congyaohui Yin, Zhaorong Zhang, Huanshui Zhang
Abstract: This paper proposes a novel second-order optimization algorithm based on the Optimal Control Principle (OCP), applicable to large-scale optimization problems in neural network training. The algorithm has a computational complexity of O(d) and strong robustness. Extensive experiments on multiple benchmarks demonstrate the significant superiority of the proposed method.
Authors: Lichen Ma, Xiaolong Fu, Gaojing Zhou, Zipeng Guo, Ting Zhu, Yichun Liu, Yu Shi, Jason Li, Junshi Huang
Abstract: With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main challenge of this task is to fully understand the instruction and reference image, and thus generate visual text that is style-consistent with the image. Previous methods often involve complex steps of specifying the text content and attributes, such as font size, color, and layout, without considering the stylistic consistency with the reference image. To address this, we propose UM-Text, a unified multimodal model for context understanding and visual text editing by natural language instructions. Specifically, we introduce a Visual Language Model (VLM) to process the instruction and reference image, so that the text content and layout can be elaborately designed according to the context information. To generate an accurate and harmonious visual text image, we further propose the UM-Encoder to combine the embeddings of various condition information, where the combination is automatically configured by VLM according to the input instruction. During training, we propose a regional consistency loss to offer more effective supervision for glyph generation on both latent and RGB space, and design a tailored three-stage training strategy to further enhance model performance. In addition, we contribute the UM-DATA-200K, a large-scale visual text image dataset on diverse scenes for model training. Extensive qualitative and quantitative results on multiple public benchmarks demonstrate that our method achieves state-of-the-art performance.
Authors: Tianyu Li, Zongqian Wu, Songyue Cai, Ping Hu, Xiaofeng Zhu
Abstract: CLIP-based foreground-background (FG-BG) decomposition methods have demonstrated remarkable effectiveness in improving few-shot out-of-distribution (OOD) detection performance. However, existing approaches still suffer from several limitations. For background regions obtained from decomposition, existing methods adopt a uniform suppression strategy for all patches, overlooking the varying contributions of different patches to the prediction. For foreground regions, existing methods fail to adequately consider that some local patches may exhibit appearance or semantic similarity to other classes, which may mislead the training process. To address these issues, we propose a new plug-and-play framework. This framework consists of three core components: (1) a Foreground-Background Decomposition module, which follows previous FG-BG methods to separate an image into foreground and background regions; (2) an Adaptive Background Suppression module, which adaptively weights patch classification entropy; and (3) a Confusable Foreground Rectification module, which identifies and rectifies confusable foreground patches. Extensive experimental results demonstrate that the proposed plug-and-play framework significantly improves the performance of existing FG-BG decomposition methods. Code is available at: https://github.com/lounwb/FoBoR.
Authors: Chenxi Ruan, Yihan Hou, Yu Xiao, Guosheng Hu, Wei Zeng
Abstract: Text-to-image (T2I) models have advanced considerably in generating high-quality images from textual descriptions. However, their ability to associate colors with concepts remains largely constrained to explicit color names or codes, while their capacity to handle \emph{implicit concepts}, such as emotions and visual states, remains underexplored. To address this gap, we introduce ColorConceptBench, an expert-annotated benchmark that systematically evaluates color-concept associations through probabilistic color distributions. ColorConceptBench moves beyond explicit color specifications by examining how models interpret 1,281 implicit color concepts, grounded in 6,584 human annotations. Our evaluation of nine leading T2I models reveals that performance varies substantially across semantic categories, and models exhibit a significant lack of sensitivity to abstract semantics. These limitations persist even when applying classifier-free guidance scaling at inference time, suggesting that achieving human-like color understanding demands a shift in how models learn and represent implicit semantic meaning.
Authors: Yiyang Lu, Susie Lu, Qiao Sun, Hanhong Zhao, Zhicheng Jiang, Xianbang Wang, Tianhong Li, Zhengyang Geng, Kaiming He
Abstract: Modern diffusion/flow-based models for image generation typically exhibit two core characteristics: (i) using multi-step sampling, and (ii) operating in a latent space. Recent advances have made encouraging progress on each aspect individually, paving the way toward one-step diffusion/flow without latents. In this work, we take a further step towards this goal and propose "pixel MeanFlow" (pMF). Our core guideline is to formulate the network output space and the loss space separately. The network target is designed to be on a presumed low-dimensional image manifold (i.e., x-prediction), while the loss is defined via MeanFlow in the velocity space. We introduce a simple transformation between the image manifold and the average velocity field. In experiments, pMF achieves strong results for one-step latent-free generation on ImageNet at 256x256 resolution (2.22 FID) and 512x512 resolution (2.48 FID), filling a key missing piece in this regime. We hope that our study will further advance the boundaries of diffusion/flow-based generative models.
Authors: Hun Chang, Byunghee Cha, Jong Chul Ye
Abstract: Recent studies have explored using pretrained Vision Foundation Models (VFMs) such as DINO for generative autoencoders, showing strong generative performance. Unfortunately, existing approaches often suffer from limited reconstruction fidelity due to the loss of high-frequency details. In this work, we present the \textbf{\em Hyperspherical Autoencoder (HAE)}, a framework that bridges semantic representation and pixel-level reconstruction. Our key insight is that while semantic information in contrastive representations is primarily directional, enforcing strict magnitude matching hinders the preservation of fine-grained details. To address this, we introduce a {\em Directional Feature Alignment} objective that enforces semantic consistency while allowing flexible feature magnitudes for detail retention, alongside a {\em Hierarchical Convolutional Patch Embedding} module to enhance local structure preservation. Furthermore, observing that SSL-based representations intrinsically lie on a hypersphere, we employ {\em Riemannian Flow Matching} to train a Diffusion Transformer (DiT) directly on this spherical latent manifold. Notably, our manifold-aware DiT exhibits highly efficient convergence, achieving an exceptional gFID of \textbf{1.96} alongside a reconstruction rFID of \textbf{0.78} and a PSNR of \textbf{25.2} dB, validating the advantages of our manifold-aware approach.
Authors: Yifan Jiang, Cong Zhang, Bofei Zhang, Qiaofeng Zheng, Yifan Yang, Bingzhang Wang, Yew-Soon Ong
Abstract: Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy overlooked by existing benchmarks that evaluate these abilities in isolation. To fill this void, we introduce Pix2Fact, a visual question-answering benchmark designed to assess expert-level visual perception and knowledge search. Pix2Fact comprises 1,000 high-resolution (4K+) images spanning eight scenarios. Its questions and answers are meticulously crafted by PhD-holding annotators from top global universities across diverse disciplines. Each question requires detailed visual grounding and the integration of external knowledge. Evaluating ten state-of-the-art VLMs, including proprietary models such as Gemini-3.1-Pro and GPT-5.4, we find that Pix2Fact poses a formidable challenge: the most advanced model (Gemini-3.1-Pro) achieves only 51.7% average accuracy, even with access to visual ground truth and search tools. Our analysis attributes this low accuracy to three factors, frequent visual grounding errors even with visual ground truth, shallow search harnessing, and VLM's inability to retrieve long-tail, unstructured local information. This striking gap exposes the limitations of current models in assisting humans with real-world scenarios that demand overwhelming visual comprehension. We believe Pix2Fact will serve as a critical benchmark to drive the next generation of language-vision agents that seamlessly integrate fine-grained perception with robust knowledge search.
Authors: Hao Chen, Tao Han, Jie Zhang, Song Guo, Fenghua Ling, Lei Bai
Abstract: Long-term weather forecasting is critical for socioeconomic planning and disaster preparedness. While recent approaches employ finetuning to extend prediction horizons, they remain constrained by the issues of catastrophic forgetting, error accumulation, and high training overhead. To address these limitations, we present a novel pipeline across pretraining, finetuning and forecasting to enhance long-context modeling while reducing computational overhead. First, we introduce an Efficient Multi-scale Transformer (EMFormer) to extract multi-scale features through a single convolution in both training and inference. Based on the new architecture, we further employ an accumulative context finetuning to improve temporal consistency without degrading short-term accuracy. Additionally, we propose a composite loss that dynamically balances different terms via a sinusoidal weighting, thereby adaptively guiding the optimization trajectory throughout pretraining and finetuning. Experiments show that our approach achieves strong performance in weather forecasting and extreme event prediction, substantially improving long-term forecast accuracy. Moreover, EMFormer demonstrates strong generalization on vision benchmarks (ImageNet-1K and ADE20K) while delivering a 5.69x speedup over conventional multi-scale modules. Code: https://github.com/chenhao-zju/emformer
Authors: Azmine Toushik Wasi, Wahid Faisal, Abdur Rahman, Mahfuz Ahmed Anik, Munem Shahriar, Mohsin Mahmud Topu, Sadia Tasnim Meem, Rahatun Nesa Priti, Sabrina Afroz Mitu, Md. Iqramul Hoque, Shahriyar Zaman Ridoy, Mohammed Eunus Ali, Majd Hawasly, Mohammad Raza, Md Rizwan Parvez
Abstract: Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision-language models (VLMs). Prior work largely relied on synthetic or LLM-generated environments with limited task designs and puzzle-like setups, failing to capture the real-world complexity, visual noise, and diverse spatial relationships that VLMs encounter. To address this, we introduce SpatiaLab, a comprehensive benchmark for evaluating VLMs' spatial reasoning in realistic, unconstrained contexts. SpatiaLab comprises 1,400 visual question-answer pairs across six major categories: Relative Positioning, Depth & Occlusion, Orientation, Size & Scale, Spatial Navigation, and 3D Geometry, each with five subcategories, yielding 30 distinct task types. Each subcategory contains at least 25 questions, and each main category includes at least 200 questions, supporting both multiple-choice and open-ended evaluation. Experiments across diverse state-of-the-art VLMs, including open- and closed-source models, reasoning-focused, and specialized spatial reasoning models, reveal a substantial gap in spatial reasoning capabilities compared with humans. In the multiple-choice setup, InternVL3.5-72B achieves 54.93% accuracy versus 87.57% for humans. In the open-ended setting, all models show a performance drop of around 10-25%, with GPT-5-mini scoring highest at 40.93% versus 64.93% for humans. These results highlight key limitations in handling complex spatial relationships, depth perception, navigation, and 3D geometry. By providing a diverse, real-world evaluation framework, SpatiaLab exposes critical challenges and opportunities for advancing VLMs' spatial reasoning, offering a benchmark to guide future research toward robust, human-aligned spatial understanding. SpatiaLab is available at: https://spatialab-reasoning.github.io/.
Authors: Cem Eteke, Enzo Tartaglione
Abstract: 3D Gaussian Splatting (3DGS) revolutionized novel view rendering. Instead of inferring from dense spatial points, as implicit representations do, 3DGS uses sparse Gaussians. This enables real-time performance but increases space requirements, hindering rate-constrained applications. 3DGS compression emerged as a field aimed at alleviating this issue. While impressive progress has been made, at low rates, compression introduces artifacts that degrade visual quality significantly. We introduce NiFi, a method for extreme 3DGS compression through restoration via artifact-aware, diffusion-based one-step distillation. We show that our method achieves state-of-the-art perceptual quality at extremely low rates, down to 0.1 MB, and towards 1000x rate improvement over 3DGS at comparable perceptual performance. Code is available at: https://github.com/ceteke/nifi
Authors: David F. Ramirez, Tim Overman, Kristen Jaskie, Joe Marvin, Andreas Spanias
Abstract: We present a visual-context image-retrieval-augmented generation (ImageRAG)- assisted AI agent for automatic target recognition (ATR) of synthetic aperture radar (SAR) imagery. SAR is a remote sensing method used in defense and security applications to detect and monitor the positions of military vehicles, which may appear indistinguishable in images. Researchers have extensively studied SAR ATR to improve the differentiation and identification of vehicle types, characteristics, and measurements. Test examples can be compared with known vehicle target types to improve recognition tasks. New methods enhance the capabilities of neural networks, transformer attention, and multimodal large language models. An agentic AI method may be developed to utilize a defined set of tools, such as searching through a library of similar examples. Our proposed method, SAR Retrieval-Augmented Generation (SAR-RAG), combines a multimodal large language model (MLLM) with a vector database of semantic embeddings to support contextual search for image exemplars with known qualities. By recovering past image examples of known true target types, our SAR-RAG system can compare similar vehicle categories, thereby improving ATR prediction accuracy. We evaluate this through search and retrieval metrics, categorical classification accuracy, and numeric regression of vehicle dimensions. These metrics all show improvements when SAR-RAG is added to an MLLM baseline method as an attached ATR memory bank.
Authors: Qianxin Xia, Jiawei Du, Xin Zhang, Yuhan Zhang, Jielei Wang, Guoming Lu
Abstract: Dataset distillation seeks to synthesize a highly compact dataset that achieves performance comparable to the original dataset on downstream tasks. For the classification task that use pre-trained self-supervised models as backbones, previous linear gradient matching optimizes synthetic images by encouraging them to mimic the gradient updates induced by real images on the linear classifier. However, this batch-level formulation requires loading thousands of real images and applying multiple rounds of differentiable augmentations to synthetic images at each distillation step, leading to substantial computational and memory overhead. In this paper, we introduce statistical flow matching , a stable and efficient supervised learning framework that optimizes synthetic images by aligning constant statistical flows from target class centers to non-target class centers in the original data. Our approach loads raw statistics only once and performs a single augmentation pass on the synthetic data, achieving performance comparable to or better than the state-of-the-art methods with 10x lower GPU memory usage and 4x shorter runtime. Furthermore, we propose a classifier inheritance strategy that reuses the classifier trained on the original dataset for inference, requiring only an extremely lightweight linear projector and marginal storage while achieving substantial performance gains.
Authors: Ziye Xie, Oded Schlesinger, Raj Kundu, Jessica Y. Choi, Pablo Iturralde, Dennis A. Turner, Stefan M. Goetz, Guillermo Sapiro, Angel V. Peterchev, J. Matias Di Martino
Abstract: Neuronavigation is widely used in biomedical research and interventions to guide the precise placement of instruments around the head to support procedures such as transcranial magnetic stimulation. Traditional systems, however, rely on subject-mounted markers that require manual registration, may shift during procedures, and can cause discomfort. We introduce and evaluate markerless approaches that replace expensive hardware and physical markers with low-cost visible and infrared light cameras incorporating stereo and depth sensing, combined with algorithmic modeling of the facial geometry. Validation with 50 human subjects yielded a median tracking discrepancy of only 2.32 mm and 2.01$^\circ$ for the best markerless algorithm compared to a conventional marker-based system, which indicates sufficient accuracy for transcranial magnetic stimulation and a substantial improvement over prior markerless results. The study also suggests that integration of the data from the various camera sensors can improve the overall accuracy further. The proposed markerless neuronavigation methods can reduce setup cost and complexity, improve patient comfort, and expand access to neuronavigation in clinical and research settings.
Authors: Hao Phung, Hadar Averbuch-Elor
Abstract: Reconstructing a structured vector-graphics representation from a rasterized floorplan image is typically an important prerequisite for computational tasks involving floorplans such as automated understanding or CAD workflows. However, existing techniques struggle in faithfully generating the structure and semantics conveyed by complex floorplans that depict large indoor spaces with many rooms and a varying numbers of polygon corners. To this end, we propose Raster2Seq, framing floorplan reconstruction as a sequence-to-sequence task in which floorplan elements--such as rooms, windows, and doors--are represented as labeled polygon sequences that jointly encode geometry and semantics. Our approach introduces an autoregressive decoder that learns to predict the next corner conditioned on image features and previously generated corners using guidance from learnable anchors. These anchors represent spatial coordinates in image space, hence allowing for effectively directing the attention mechanism to focus on informative image regions. By embracing the autoregressive mechanism, our method offers flexibility in the output format, enabling for efficiently handling complex floorplans with numerous rooms and diverse polygon structures. Our method achieves state-of-the-art performance on standard benchmarks such as Structure3D, CubiCasa5K, and Raster2Graph, while also demonstrating strong generalization to more challenging datasets like WAFFLE, which contain diverse room structures and complex geometric variations.
Authors: Han Zhou, Yuxuan Gao, Yinchao Du, Xuezhe Zheng
Abstract: Unsupervised industrial anomaly detection (UAD) is essential for modern manufacturing inspection, where defect samples are scarce and reliable detection is required. In this paper, we propose HLGFA, a high-low resolution guided feature alignment framework that learns normality by modeling cross-resolution feature consistency between high-resolution and low-resolution representations of normal samples, instead of relying on pixel-level reconstruction. Dual-resolution inputs are processed by a shared frozen backbone to extract multi-level features, and high-resolution representations are decomposed into structure and detail priors to guide the refinement of low-resolution features through conditional modulation and gated residual correction. During inference, anomalies are naturally identified as regions where cross-resolution alignment breaks down. In addition, a noise-aware data augmentation strategy is introduced to suppress nuisance-induced responses commonly observed in industrial environments. Extensive experiments on standard benchmarks demonstrate the effectiveness of HLGFA, achieving 97.9% pixel-level AUROC and 97.5% image-level AUROC on the MVTec AD dataset, outperforming representative reconstruction-based and feature-based methods.
Authors: Jiayi Lyu, Leigang Qu, Wenjing Zhang, Hanyu Jiang, Kai Liu, Zhenglin Zhou, Xiaobo Xia, Jian Xue, Tat-Seng Chua
Abstract: Realistic talking-head video generation is critical for virtual avatars, film production, and interactive systems. Current methods struggle with nuanced emotional expressions due to the lack of fine-grained emotion control. To address this issue, we introduce a novel two-stage method (AUHead) to disentangle fine-grained emotion control, i.e. , Action Units (AUs), from audio and achieve controllable generation. In the first stage, we explore the AU generation abilities of large audio-language models (ALMs), by spatial-temporal AU tokenization and an "emotion-then-AU" chain-of-thought mechanism. It aims to disentangle AUs from raw speech, effectively capturing subtle emotional cues. In the second stage, we propose an AU-driven controllable diffusion model that synthesizes realistic talking-head videos conditioned on AU sequences. Specifically, we first map the AU sequences into the structured 2D facial representation to enhance spatial fidelity, and then model the AU-vision interaction within cross-attention modules. To achieve flexible AU-quality trade-off control, we introduce an AU disentanglement guidance strategy during inference, further refining the emotional expressiveness and identity consistency of the generated videos. Results on benchmark datasets demonstrate that our approach achieves competitive performance in emotional realism, accurate lip synchronization, and visual coherence, significantly surpassing existing techniques. Our implementation is available at https://github.com/laura990501/AUHead_ICLR
Authors: Yingcheng Hu, Haowen Gong, Chuanguang Yang, Zhulin An, Yongjun Xu, Songhua Liu
Abstract: Pose-guided human image animation aims to synthesize realistic videos of a reference character driven by a sequence of poses. While diffusion-based methods have achieved remarkable success, most existing approaches are limited to single-character animation. We observe that naively extending these methods to multi-character scenarios often leads to identity confusion and implausible occlusions between characters. To address these challenges, in this paper, we propose an extensible multi-character image animation framework built upon modern Diffusion Transformers (DiTs) for video generation. At its core, our framework introduces two novel components-Identifier Assigner and Identifier Adapter - which collaboratively capture per-person positional cues and inter-person spatial relationships. This mask-driven scheme, along with a scalable training strategy, not only enhances flexibility but also enables generalization to scenarios with more characters than those seen during training. Remarkably, trained on only a two-character dataset, our model generalizes to multi-character animation while maintaining compatibility with single-character cases. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in multi-character image animation, surpassing existing diffusion-based baselines.
Authors: Chenhao Zheng, Jieyu Zhang, Jianing Zhang, Weikai Huang, Ashutosh Kumar, Quan Kong, Oncel Tuzel, Chun-Liang Li, Ranjay Krishna
Abstract: Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising solution by decoupling video duration from token count, they rely on complex external segmentation and tracking pipelines that are slow and task-agnostic. We propose TrajTok, an end-to-end video tokenizer module that is fully integrated and co-trained with video models for a downstream objective, dynamically adapting its token granularity to semantic complexity, independent of video duration. TrajTok contains a unified segmenter that performs implicit clustering over pixels in both space and time to directly produce object trajectories in a single forward pass. By prioritizing downstream adaptability over pixel-perfect segmentation fidelity, TrajTok is lightweight and efficient, yet empirically improves video understanding performance. With TrajTok, we implement a video CLIP model trained from scratch (TrajViT2). It achieves the best accuracy at scale across both classification and retrieval benchmarks, while maintaining efficiency comparable to the best token-merging methods. TrajTok also proves to be a versatile component beyond its role as a tokenizer. We show that it can be seamlessly integrated as either a probing head for pretrained visual features (TrajAdapter) or an alignment connector in vision-language models (TrajVLM) with especially strong performance in long-video reasoning.
Authors: Hongyu Li, Kuan Liu, Yuan Chen, Juntao Hu, Huimin Lu, Guanjie Chen, Xue Liu, Guangming Lu, Hong Huang
Abstract: Recent advances in generative AI have shown human-level performance in complex content creation. However, we identify a "Paradox of Simplicity": models that can render complex scenes often fail at trivial, low-entropy tasks, such as generating a uniform pure color image. We argue this is a systemic failure related to uncontrollable emergent abilities. As models scale, strong priors for aesthetics and complexity override deterministic simplicity, creating an "aesthetic bias" that hinders the model's transition from data simulation to true intellectual abstraction. To better investigate this problem, we formalize the concept of AI Obedience, a hierarchical framework that grades a model's ability to transition from probabilistic approximation to pixel-level determinism (Levels 1 to 5). We introduce Violin, the first systematic benchmark designed to evaluate Level 4 Obedience through three deterministic tasks: color purity, image masking, and geometric shape generation. Using Violin, we evaluate several state-of-the-art models and reveal that closed-source models generally outperform open-source ones in deterministic precision. Interestingly, performance on our benchmark correlates with the benchmark in natural image generation. Our work provides a foundational framework and tools for achieving better alignment between human instructions and model outputs.
Authors: Seungwook Kim, Minsu Cho
Abstract: Text-to-image generation powers content creation across design, media, and data augmentation. Post-training of text-to-image generative models is a promising path to improve human preference alignment, factuality, and aesthetics. We introduce SOLACE (Self-Originating LAtent Confidence Estimation), a post-training framework that replaces external reward supervision with an internal self-confidence signal: we re-noise the model's own outputs and measure how accurately it recovers the injected noise, treating low reconstruction error as high self-confidence. SOLACE converts this intrinsic signal into scalar rewards for reinforcement learning, requiring no external reward models, annotators, or preference data. By reinforcing high-confidence generations, SOLACE delivers consistent gains in compositional generation, text rendering, and text-image alignment. Integrating SOLACE with external rewards yields complementary improvements while alleviating reward hacking.
Authors: Tsung-Ming Tai, Sofia Casarin, Andrea Pilzer, Werner Nutt, Oswald Lanz
Abstract: Anticipating future actions in videos is challenging, as the observed frames provide only evidence of past activities, requiring the inference of latent intentions to predict upcoming actions. Existing transformer-based approaches, which rely on dot-product attention over pixel representations, often lack the high-level semantics necessary to model video sequences for effective action anticipation. As a result, these methods tend to overfit to explicit visual cues present in the past frames, limiting their ability to capture underlying intentions and degrading generalization to unseen samples. To address this, we propose Action-Guided Attention (AGA), an attention mechanism that explicitly leverages predicted action sequences as queries and keys to guide sequence modeling. Our approach fosters the attention module to emphasize relevant moments from the past based on the upcoming activity and combine this information with the current frame embedding via a dedicated gating function. The design of AGA enables post-training analysis of the knowledge discovered from the training set. Experiments on the widely adopted EPIC-Kitchens-100 benchmark demonstrate that AGA generalizes well from validation to unseen test sets. Post-training analysis can further examine the action dependencies captured by the model and the counterfactual evidence it has internalized, offering transparent and interpretable insights into its anticipative predictions.
Authors: Miguel Espinosa, Eva Gmelich Meijling, Valerio Marsocci, Elliot J. Crowley, Mikolaj Czerkawski
Abstract: Earth observation applications increasingly rely on data from multiple sensors, including optical, radar, elevation, and land-cover. Relationships between modalities are fundamental for data integration but are inherently non-injective: identical conditioning information can correspond to multiple physically plausible observations, and should be parametrised as conditional distributions. Deterministic models, by contrast, collapse toward conditional means and fail to represent the uncertainty and variability required for tasks such as data completion and cross-sensor translation. We introduce COP-GEN, a multimodal latent diffusion transformer that models the joint distribution of heterogeneous EO modalities at their native spatial resolutions. By parameterising cross-modal mappings as conditional distributions, COP-GEN enables flexible any-to-any conditional generation, including zero-shot modality translation without task-specific retraining. Experiments show that COP-GEN generates diverse yet physically consistent realisations while maintaining strong peak fidelity across optical, radar, and elevation modalities. Qualitative and quantitative analyses demonstrate that the model captures meaningful cross-modal structure and adapts its output uncertainty as conditioning information increases. We release a stochastic benchmark built from multi-temporal Sentinel-2 observations that enables distribution-level comparison of generative EO models. On this benchmark, COP-GEN covers 90% of the real observation manifold and 63% of its per-band reflectance range, while the strongest competing method collapses to 2.8% and 18%, respectively. These results highlight the importance of stochastic generative modeling for EO and motivate evaluation protocols beyond single-reference, pointwise metrics. Website: https://miquel-espinosa.github.io/cop-gen
Authors: Jiajun Cao, Xiaoan Zhang, Xiaobao Wei, Liyuqiu Huang, Zijian Wang, Hanzhen Zhang, Zhengyu Jia, Wei Mao, Hao Wang, Xianming Liu, Shuchang Zhou, Yang Wang, Shanghang Zhang
Abstract: Vision-Language-Action models have shown great promise for autonomous driving, yet they suffer from degraded perception after unfreezing the visual encoder and struggle with accumulated instability in long-term planning. To address these challenges, we propose EvoDriveVLA-a novel collaborative perception-planning distillation framework that integrates self-anchored perceptual constraints and future-informed trajectory optimization. Specifically, self-anchored visual distillation leverages self-anchor teacher to deliver visual anchoring constraints, regularizing student representations via trajectory-guided key-region awareness. In parallel, future-informed trajectory distillation employs a future-aware oracle teacher with coarse-to-fine trajectory refinement and Monte Carlo dropout sampling to synthesize reasoning trajectories that model future evolutions, enabling the student model to internalize the future-aware insights of the teacher. EvoDriveVLA achieves SOTA performance in nuScenes open-loop evaluation and significantly enhances performance in NAVSIM closed-loop evaluation. Our code is available at: https://github.com/hey-cjj/EvoDriveVLA.
Authors: Zhongyu Xia, Yousen Tang, Yongtao Wang, Zhifeng Wang, Weijun Qin
Abstract: 4D radar-camera sensing configuration has gained increasing importance in autonomous driving. However, existing 3D object detection methods that fuse 4D Radar and camera data confront several challenges. First, their absolute depth estimation module is not robust and accurate enough, leading to inaccurate 3D localization. Second, the performance of their temporal fusion module will degrade dramatically or even fail when the ego vehicle's pose is missing or inaccurate. Third, for some small objects, the sparse radar point clouds may completely fail to reflect from their surfaces. In such cases, detection must rely solely on visual unimodal priors. To address these limitations, we propose R4Det, which enhances depth estimation quality via the Panoramic Depth Fusion module, enabling mutual reinforcement between absolute and relative depth. For temporal fusion, we design a Deformable Gated Temporal Fusion module that does not rely on the ego vehicle's pose. In addition, we built an Instance-Guided Dynamic Refinement module that extracts semantic prototypes from 2D instance guidance. Experiments show that R4Det achieves state-of-the-art 3D object detection results on the TJ4DRadSet and VoD datasets. The source code and models will be released at https://github.com/VDIGPKU/R4Det.
Authors: Jennifer Nolan, Travis Driver, John Christian
Abstract: Image-based surface reconstruction and characterization are crucial for missions to small celestial bodies (e.g., asteroids), as it informs mission planning, navigation, and scientific analysis. Recent advances in Gaussian splatting enable high-fidelity neural scene representations but typically rely on a spherical harmonic intensity parameterization that is strictly appearance-based and does not explicitly model material properties or light-surface interactions. We introduce AstroSplat, a physics-based Gaussian splatting framework that integrates planetary reflectance models to improve the autonomous reconstruction and photometric characterization of small-body surfaces from in-situ imagery. The proposed framework is validated on real imagery taken by NASA's Dawn mission, where we demonstrate superior rendering performance and surface reconstruction accuracy compared to the typical spherical harmonic parameterization.
Authors: Ziyu Liu, Shengyuan Ding, Xinyu Fang, Xuanlang Dai, Penghui Yang, Jianze Liang, Jiaqi Wang, Kai Chen, Dahua Lin, Yuhang Zang
Abstract: Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs) achieve strong results via supervised fine-tuning, reinforcement learning remains challenging due to misaligned reward signals. Existing rewards either rely on textual rules or coarse visual embedding similarity, both of which fail to capture fine-grained visual discrepancies and are vulnerable to reward hacking. We propose Visual Equivalence Reward Model (Visual-ERM), a multimodal generative reward model that provides fine-grained, interpretable, and task-agnostic feedback to evaluate vision-to-code quality directly in the rendered visual space. Integrated into RL, Visual-ERM improves Qwen3-VL-8B-Instruct by +8.4 on chart-to-code and yields consistent gains on table and SVG parsing (+2.7, +4.1 on average), and further strengthens test-time scaling via reflection and revision. We also introduce VisualCritic-RewardBench (VC-RewardBench), a benchmark for judging fine-grained image-to-image discrepancies on structured visual data, where Visual-ERM at 8B decisively outperforms Qwen3-VL-235B-Instruct and approaches leading closed-source models. Our results suggest that fine-grained visual reward supervision is both necessary and sufficient for vision-to-code RL, regardless of task specificity.
Authors: Asmae Mouradi, Shruti Kshirsagar
Abstract: Rapid structural damage assessment from remote sensing imagery is essential for timely disaster response. Within human-machine systems (HMS) for disaster management, automated damage detection provides decision-makers with actionable situational awareness. However, models trained on multi-disaster benchmarks often underperform in unseen geographic regions due to domain shift - a distributional mismatch between training and deployment data that undermines human trust in automated assessments. We explore a two-stage ensemble approach using supervised domain adaptation (SDA) for building damage classification across four severity classes. The pipeline adapts the xView2 first-place method to the Ida-BD dataset using SDA and systematically investigates the effect of individual augmentation components on classification performance. Comprehensive ablation experiments on the unseen Ida-BD test split demonstrate that SDA is indispensable: removing it causes damage detection to fail entirely. Our pipeline achieves the most robust performance using SDA with unsharp-enhanced RGB input, attaining a Macro-F1 of 0.5552. These results underscore the critical role of domain adaptation in building trustworthy automated damage assessment modules for HMS-integrated disaster response.
Authors: Junxin Wang, Dai Guan, Weijie Qiu, Zhihang Li, Yongbo Gai, Zhengyi Yang, Mengyu Zhou, Erchao Zhao, Xiaoxi Jiang, Guanjun Jiang
Abstract: Vision-language process reward models (VL-PRMs) are increasingly used to score intermediate reasoning steps and rerank candidates under test-time scaling. However, they often function as black-box judges: a low step score may reflect a genuine reasoning mistake or simply the verifier's misperception of the image. This entanglement between perception and reasoning leads to systematic false positives (rewarding hallucinated visual premises) and false negatives (penalizing correct grounded statements), undermining both reranking and error localization. We introduce Explicit Visual Premise Verification (EVPV), a lightweight verification interface that conditions step scoring on the reliability of the visual premises a step depends on. The policy is prompted to produce a step-wise visual checklist that makes required visual facts explicit, while a constraint extractor independently derives structured visual constraints from the input image. EVPV matches checklist claims against these constraints to compute a scalar visual reliability signal, and calibrates PRM step rewards via reliability gating: rewards for visually dependent steps are attenuated when reliability is low and preserved when reliability is high. This decouples perceptual uncertainty from logical evaluation without per-step tool calls. Experiments on VisualProcessBench and six multimodal reasoning benchmarks show that EVPV improves step-level verification and consistently boosts Best-of-N reranking accuracy over strong baselines. Furthermore, injecting controlled corruption into the extracted constraints produces monotonic performance degradation, providing causal evidence that the gains arise from constraint fidelity and explicit premise verification rather than incidental prompt effects. Code is available at: https://github.com/Qwen-Applications/EVPV-PRM
Authors: Lin Li, Haoran Feng, Zehuan Huang, Haohua Chen, Wenbo Nie, Shaohua Hou, Keqing Fan, Pan Hu, Sheng Wang, Buyu Li, Lu Sheng
Abstract: We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D via distillation or multi-view mask aggregation, often suffering from cross-view inconsistency and blurred boundaries, or explore native 3D discriminative segmentation, which typically requires large-scale annotated 3D data and substantial training resources. In contrast, SegviGen leverages the structured priors encoded in pretrained 3D generative model to induce segmentation through distinctive part colorization, establishing a novel and efficient framework for part segmentation. Specifically, SegviGen encodes a 3D asset and predicts part-indicative colors on active voxels of a geometry-aligned reconstruction. It supports interactive part segmentation, full segmentation, and full segmentation with 2D guidance in a unified framework. Extensive experiments show that SegviGen improves over the prior state of the art by 40% on interactive part segmentation and by 15% on full segmentation, while using only 0.32% of the labeled training data. It demonstrates that pretrained 3D generative priors transfer effectively to 3D part segmentation, enabling strong performance with limited supervision. See our project page at https://fenghora.github.io/SegviGen-Page/.
Authors: Niklas Ro{\ss}berg, Sinan Hasirlioglu, Mohamed Essayed Bouzouraa, Wolfgang Utschick, Michael Botsch
Abstract: Approval of ADS depends on evaluating its behavior within representative real-world traffic scenarios. A common way to obtain such scenarios is to extract them from real-world data recordings. These can then be grouped and serve as basis on which the ADS is subsequently tested. This poses two central challenges: how scenarios are extracted and how they are grouped. Existing extraction methods rely on heterogeneous definitions, hindering scenario comparability. For the grouping of scenarios, rule-based or ML-based methods can be utilized. However, while modern ML-based approaches can handle the complexity of traffic scenarios, unlike rule-based approaches, they lack interpretability and may not align with domain-knowledge. This work contributes to a standardized scenario extraction based on the Scenario-as-Specification concept, as well as a domain-knowledge-guided scenario clustering process. Experiments on the highD dataset demonstrate that scenarios can be extracted reliably and that domain-knowledge can be effectively integrated into the clustering process. As a result, the proposed methodology supports a more standardized process for deriving scenario categories from highway data recordings and thus enables a more efficient validation process of automated vehicles.
Authors: Carlos Esteves, Ameesh Makadia
Abstract: Denoising diffusion models are widely used for high-quality image and video generation. Their performance depends on noise schedules, which define the distribution of noise levels applied during training and the sequence of noise levels traversed during sampling. Noise schedules are typically handcrafted and require manual tuning across different resolutions. In this work, we propose a principled way to design per-instance noise schedules for pixel diffusion, based on the image's spectral properties. By deriving theoretical bounds on the efficacy of minimum and maximum noise levels, we design ``tight'' noise schedules that eliminate redundant steps. During inference, we propose to conditionally sample such noise schedules. Experiments show that our noise schedules improve generative quality of single-stage pixel diffusion models, particularly in the low-step regime.
Authors: Qingdong He, Chaoyi Wang, Peng Tang, Yifan Yang, Xiaobin Hu
Abstract: Video subtitle removal aims to distinguish text overlays from background content while preserving temporal coherence. Existing diffusion-based methods necessitate explicit mask sequences during both training and inference phases, which restricts their practical deployment. In this paper, we present CLEAR (Context-aware Learning for End-to-end Adaptive Video Subtitle Removal), a mask-free framework that achieves truly end-to-end inference through context-aware adaptive learning. Our two-stage design decouples prior extraction from generative refinement: Stage I learns disentangled subtitle representations via self-supervised orthogonality constraints on dual encoders, while Stage II employs LoRA-based adaptation with generation feedback for dynamic context adjustment. Notably, our method only requires 0.77% of the parameters of the base diffusion model for training. On Chinese subtitle benchmarks, CLEAR outperforms mask-dependent baselines by + 6.77dB PSNR and -74.7% VFID, while demonstrating superior zero-shot generalization across six languages (English, Korean, French, Japanese, Russian, German), a performance enabled by our generation-driven feedback mechanism that ensures robust subtitle removal without ground-truth masks during inference.
Authors: Hamidreza Aftabi, Faye Yu, Brooke Switzer, Zachary Fishman, Eitan Prisman, Antony Hodgson, Cari Whyne, Sidney Fels, Michael Hardisty
Abstract: Predicting long-term bone remodeling after mandibular reconstruction would be of great clinical benefit, yet standard generative models struggle to maintain trajectory-level consistency and anatomical fidelity over long horizons. We introduce OsteoFlow, a flow-based framework predicting Year-1 post-operative CT scans from Day-5 scans. Our core contribution is Lyapunov-guided trajectory distillation: Unlike one-step distillation, our method distills a continuous trajectory over transport time from a registration-derived stationary velocity field teacher. Combined with a resection-aware image loss, this enforces geometric correspondence without sacrificing generative capacity. Evaluated on 344 paired regions of interest, OsteoFlow significantly outperforms state of-the-art baselines, reducing mean absolute error in the surgical resection zone by ~20%. This highlights the promise of trajectory distillation for long-term prediction. Code is available on GitHub: OsteoFlow.
Authors: Nanxiang Jiang, Zhaoxin Fan, Baisen Wang, Daiheng Gao, Junhang Cheng, Jifeng Guo, Yalan Qin, Yeying Jin, Hongwei Zheng, Faguo Wu, Wenjun Wu
Abstract: Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Net and dual-stream architectures (e.g., Flux), this task remains under-explored in the recent emerging paradigm of single-stream diffusion transformers (e.g., Z-Image). In this new paradigm, text and image tokens are processed as a single unified sequence via shared parameters. Consequently, directly applying prior erasure methods typically leads to generation collapse. To bridge this gap, we introduce Z-Erase, the first concept erasure method tailored for single-stream T2I models. To guarantee stable image generation, Z-Erase first proposes a Stream Disentangled Concept Erasure Framework that decouples updates and enables existing methods on single-stream models. Subsequently, within this framework, we introduce Lagrangian-Guided Adaptive Erasure Modulation, a constrained algorithm that further balances the sensitive erasure-preservation trade-off. Moreover, we provide a rigorous convergence analysis proving that Z-Erase can converge to a Pareto stationary point. Experiments demonstrate that Z-Erase successfully overcomes the generation collapse issue, achieving state-of-the-art performance across a wide range of tasks.
Authors: Emad Bahrami, Olga Zatsarynna, Parth Pathak, Sunando Sengupta, Juergen Gall, Mohsen Fayyaz
Abstract: We introduce STRIVE (SpatioTemporal Reinforcement with Importance-aware Variant Exploration), a structured reinforcement learning framework for video question answering. While group-based policy optimization methods have shown promise in large multimodal models, they often suffer from low reward variance when responses exhibit similar correctness, leading to weak or unstable advantage estimates. STRIVE addresses this limitation by constructing multiple spatiotemporal variants of each input video and performing joint normalization across both textual generations and visual variants. By expanding group comparisons beyond linguistic diversity to structured visual perturbations, STRIVE enriches reward signals and promotes more stable and informative policy updates. To ensure exploration remains semantically grounded, we introduce an importance-aware sampling mechanism that prioritizes frames most relevant to the input question while preserving temporal coverage. This design encourages robust reasoning across complementary visual perspectives rather than overfitting to a single spatiotemporal configuration. Experiments on six challenging video reasoning benchmarks including VideoMME, TempCompass, VideoMMMU, MMVU, VSI-Bench, and PerceptionTest demonstrate consistent improvements over strong reinforcement learning baselines across multiple large multimodal models. Our results highlight the role of structured spatiotemporal exploration as a principled mechanism for stabilizing multimodal reinforcement learning and improving video reasoning performance.
Authors: Jiahao Chen, Bing Su
Abstract: Long-tailed recognition has benefited from foundation models and fine-tuning paradigms, yet existing studies and benchmarks are mainly confined to natural image domains, where pre-training and fine-tuning data share similar distributions. In contrast, scientific images exhibit distinct visual characteristics and supervision signals, raising questions about the effectiveness of fine-tuning foundation models in such settings. In this work, we investigate scientific long-tailed recognition under a purely visual and fine-tuning paradigm. Experiments on three scientific benchmarks show that fine-tuning foundation models yields limited gains, and reveal that penultimate-layer features play an important role, particularly for tail classes. Motivated by these findings, we propose SciLT, a framework that exploits multi-level representations through adaptive feature fusion and dual-supervision learning. By jointly leveraging penultimate- and final-layer features, SciLT achieves balanced performance across head and tail classes. Extensive experiments demonstrate that SciLT consistently outperforms existing methods, establishing a strong and practical baseline for scientific long-tailed recognition and providing valuable guidance for adapting foundation models to scientific data with substantial domain shifts.
Authors: Shaoyang Cui, Lingbei Meng
Abstract: Video-based numerical reasoning provides a premier arena for testing whether Vision-Language Models (VLMs) truly "understand" real-world dynamics, as accurate numerical deduction necessitates a profound grasp of temporal events, object permanence, and compositional logic beyond superficial pattern matching. However, existing benchmarks are often confined to narrow domains, such as repetitive athletic motions, or treat simple counting merely as a superficial regression task, failing to assess multi-step numerical logic within the inherent complexity of real-world multimedia content. We introduce VidNum-1.4K, a comprehensive VideoQA benchmark comprising 1,379 strictly human-annotated video-question pairs designed to evaluate genuine numerical reasoning across highly diverse environments, encompassing object, action, and event quantification. The VidNum-1.4K is uniquely structured into a three-level hierarchy that evolves from direct visual perception to video-based compositional numerical reasoning, requiring models to perform arithmetic operations, comparisons, and logical deductions grounded in temporal evidence. Our evaluations across a diverse suite of state-of-the-art VLMs reveal a striking reasoning gap: while the Gemini-3.1-pro barely reaches a 60% accuracy threshold, representative open-source families struggle heavily in the 25%--45% range. These findings demonstrate that current VLMs still lack a stable "internal world model", positioning VidNum-1.4K as a demanding diagnostic testbed for the next generation of numerical video intelligence.
Authors: Stella Girtsou, Konstantinos Alexis, Giorgos Giannopoulos, Charalambos Kontoes
Abstract: The increasing frequency and severity of climate related disasters have intensified the need for real time monitoring, early warning, and informed decision-making. Earth Observation (EO), powered by satellite data and Machine Learning (ML), offers powerful tools to meet these challenges. Foundation Models (FMs) have revolutionized EO ML by enabling general-purpose pretraining on large scale remote sensing datasets. However most existing models rely on high-resolution satellite imagery with low revisit rates limiting their suitability for fast-evolving phenomena and time critical emergency response. In this work, we present HighFM, a first cut approach towards a FM for high temporal resolution, multispectral EO data. Leveraging over 2 TB of SEVIRI imagery from the Meteosat Second Generation (MSG) platform, we adapt the SatMAE masked autoencoding framework to learn robust spatiotemporal representations. To support real time monitoring, we enhance the original architecture with fine grained temporal encodings to capture short term variability. The pretrained models are then finetuned on cloud masking and active fire detection tasks. We benchmark our SEVIRI pretrained Vision Transformers against traditional baselines and recent geospatial FMs, demonstrating consistent gains across both balanced accuracy and IoU metrics. Our results highlight the potential of temporally dense geostationary data for real-time EO, offering a scalable path toward foundation models for disaster detection and tracking.
Authors: Zhiqiang Liu, Rui Song, Duanmu Chuangqi, Jiaojiao Li, David Ferstl, Yinlin Hu
Abstract: We present DeSOPE, a large-scale dataset for 6DoF deformed objects. Most 6D object pose methods assume rigid or articulated objects, an assumption that fails in practice as objects deviate from their canonical shapes due to wear, impact, or deformation. To model this, we introduce the DeSOPE dataset, which features high-fidelity 3D scans of 26 common object categories, each captured in one canonical state and three deformed configurations, with accurate 3D registration to the canonical mesh. Additionally, it features an RGB-D dataset with 133K frames across diverse scenarios and 665K pose annotations produced via a semi-automatic pipeline. We begin by annotating 2D masks for each instance, then compute initial poses using an object pose method, refine them through an object-level SLAM system, and finally perform manual verification to produce the final annotations. We evaluate several object pose methods and find that performance drops sharply with increasing deformation, suggesting that robust handling of such deformations is critical for practical applications.
Authors: Yuhang He
Abstract: Positional encoding has become the de facto standard for grounding deep neural networks on discrete point-wise positions, and it has achieved remarkable success in tasks where the input can be represented as a one-dimensional sequence. However, extending this concept to 2D spatial geometric shapes demands carefully designed encoding strategies that account not only for shape geometry and pose, but also for compatibility with neural network learning. In this work, we address these challenges by introducing a training-free, general-purpose encoding strategy, dubbed XShapeEnc, that encodes an arbitrary spatially grounded 2D geometric shape into a compact representation exhibiting five favorable properties, including invertibility, adaptivity, and frequency richness. Specifically, a 2D spatially grounded geometric shape is decomposed into its normalized geometry within the unit disk and its pose vector, where the pose is further transformed into a harmonic pose field that also lies within the unit disk. A set of orthogonal Zernike bases is constructed to encode shape geometry and pose either independently or jointly, followed by a frequency-propagation operation to introduce high-frequency content into the encoding. We demonstrate the theoretical validity, efficiency, discriminability, and applicability of XShapeEnc via extensive analysis and experiments across a wide range of shape-aware tasks and our self-curated XShapeCorpus. We envision XShapeEnc as a foundational tool for research that goes beyond one-dimensional sequential data toward frontier 2D spatial intelligence.
Authors: Yudong Han, Yong Wang, Zaiquan Yang, Zhen Qu, Liyuan Pan, Xiangxiang Chu
Abstract: Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT) decoding with implicit feature propagation, simultaneously enhancing representation informativeness and reducing inference latency. By analyzing token-level gradient dynamics during latent training, we reveal two critical observations: (1) visual tokens exhibit significantly smaller gradient norms than their textual counterparts due to inherent language bias, resulting in systematic visual under-optimization; and (2) semantically simple tokens converge rapidly, whereas complex tokens exhibit persistent gradient instability constrained by fixed architectural depths. To address these limitations, we propose a visual replay module and routing depth scaling to collaboratively enhance visual perception and refine complicated latents for deeper contextual reasoning. The former module leverages causal self-attention to estimate token saliency, reinforcing fine-grained grounding through spatially-coherent constraints. Complementarily, the latter mechanism adaptively allocates additional reasoning steps to complex tokens, enabling deeper contextual refinement. Guided by a curriculum strategy that progressively internalizes explicit CoT into compact latent representations, our framework achieves state-of-the-art performance across diverse benchmarks while delivering substantial inference speedups over explicit CoT baselines.
Authors: Xingjian Ran, Shujie Zhang, Weipeng Zhong, Li Luo, Bo Dai
Abstract: Generating high-fidelity 3D indoor scenes remains a significant challenge due to data scarcity and the complexity of modeling intricate spatial relations. Current methods often struggle to scale beyond training distribution to dense scenes or rely on LLMs/VLMs that lack the ability for precise spatial reasoning. Building on top of the observation that object placement relies mainly on local dependencies instead of information-redundant global distributions, in this paper, we propose Pair2Scene, a novel procedural generation framework that integrates learned local rules with scene hierarchies and physics-based algorithms. These rules mainly capture two types of inter-object relations, namely support relations that follow physical hierarchies, and functional relations that reflect semantic links. We model these rules through a network, which estimates spatial position distributions of dependent objects conditioned on position and geometry of the anchor ones. Accordingly, we curate a dataset 3D-Pairs from existing scene data to train the model. During inference, our framework can generate scenes by recursively applying our model within a hierarchical structure, leveraging collision-aware rejection sampling to align local rules into coherent global layouts. Extensive experiments demonstrate that our framework outperforms existing methods in generating complex environments that go beyond training data while maintaining physical and semantic plausibility.
Authors: Yuhao Liu, Dingju Wang, Ziyang Zheng
Abstract: This paper presents our approach to the NTIRE 2026 3D Restoration and Reconstruction Challenge (Track 1), which focuses on reconstructing high-quality 3D representations from degraded multi-view inputs. The challenge involves recovering geometrically consistent and photorealistic 3D scenes in extreme low-light environments. To address this task, we propose Extreme Low-light Optimized Gaussian Splatting (ELoG-GS), a robust low-light 3D reconstruction pipeline that integrates learning-based point cloud initialization and luminance-guided color enhancement for stable and photorealistic Gaussian Splatting. Our method incorporates both geometry-aware initialization and photometric adaptation strategies to improve reconstruction fidelity under challenging conditions. Extensive experiments on the NTIRE Track 1 benchmark demonstrate that our approach significantly improves reconstruction quality over the baselines, achieving superior visual fidelity and geometric consistency. The proposed method provides a practical solution for robust 3D reconstruction in real-world degraded scenarios. In the final testing phase, our method achieved a PSNR of 18.6626 and an SSIM of 0.6855 on the official platform leaderboard. Code is available at https://github.com/lyh120/FSGS_EAPGS.
Authors: Haoran Lou, Ziyan Liu, Chunxiao Fan, Yuexin Wu, Yue Ming, Hao Wu, Kai Zuo, Yibo Chen, Xu Tang
Abstract: Multimodal Large Language Models (MLLMs) possess intrinsic reasoning and world-knowledge capabilities, yet adapting them for dense retrieval remains challenging. Existing approaches rely on invasive parameter updates, such as full fine-tuning and LoRA, which may disrupt the pre-trained semantic space and impair the structured knowledge essential for reasoning. To address this, we propose SLQ, a parameter-efficient tuning framework that adapts MLLMs for retrieval while keeping the backbone entirely frozen. SLQ introduces a small set of Shared Latent Queries that are appended to both text and image tokens, leveraging the model's native causal attention to aggregate multimodal context into a unified embedding space. Furthermore, to better evaluate retrieval beyond superficial pattern matching, we construct KARR-Bench, a benchmark designed for knowledge-aware reasoning retrieval. Extensive experiments show that SLQ outperforms full fine-tuning and LoRA on COCO and Flickr30K, while achieving competitive performance on MMEB and yielding substantial gains on KARR-Bench, validating that preserving the pre-trained representations via non-invasive adaptation is an effective strategy for MLLM-based retrieval. The code is available under: https://github.com/CnFaker/SLQ.
Authors: Tianshuo Yang, Guanyu Chen, Yutian Chen, Zhixuan Liang, Yitian Liu, Zanxin Chen, Chunpu Xu, Haotian Liang, Jiangmiao Pang, Yao Mu, Ping Luo
Abstract: While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound reasoning capabilities inherited from their base Vision-Language Models (VLMs). To resolve this fundamental trade-off, we propose HiVLA, a visual-grounded-centric hierarchical framework that explicitly decouples high-level semantic planning from low-level motor control. In high-level part, a VLM planner first performs task decomposition and visual grounding to generate structured plans, comprising a subtask instruction and a precise target bounding box. Then, to translate this plan into physical actions, we introduce a flow-matching Diffusion Transformer (DiT) action expert in low-level part equipped with a novel cascaded cross-attention mechanism. This design sequentially fuses global context, high-resolution object-centric crops and skill semantics, enabling the DiT to focus purely on robust execution. Our decoupled architecture preserves the VLM's zero-shot reasoning while allowing independent improvement of both components. Extensive experiments in simulation and the real world demonstrate that HiVLA significantly outperforms state-of-the-art end-to-end baselines, particularly excelling in long-horizon skill composition and the fine-grained manipulation of small objects in cluttered scenes.
Authors: Hong Jiang, Wensong Song, Zongxing Yang, Ruijie Quan, Yi Yang
Abstract: Camera-controllable image editing aims to synthesize novel views of a given scene under varying camera poses while strictly preserving cross-view geometric consistency. However, existing methods typically rely on fragmented geometric guidance, such as only injecting point clouds at the representation level despite models containing multiple levels, and are mainly based on image diffusion models that operate on discrete view mappings. These two limitations jointly lead to geometric drift and structural degradation under continuous camera motion. We observe that while leveraging video models provides continuous viewpoint priors for camera-controllable image editing, they still struggle to form stable geometric understanding if geometric guidance remains fragmented. To systematically address this, we inject unified geometric guidance across three levels that jointly determine the generative output: representation, architecture, and loss function. To this end, we propose UniGeo, a novel camera-controllable editing framework. Specifically, at the representation level, UniGeo incorporates a frame-decoupled geometric reference injection mechanism to provide robust cross-view geometry context. At the architecture level, it introduces geometric anchor attention to align multi-view features. At the loss function level, it proposes a trajectory-endpoint geometric supervision strategy to explicitly reinforce the structural fidelity of target views. Comprehensive experiments across multiple public benchmarks, encompassing both extensive and limited camera motion settings, demonstrate that UniGeo significantly outperforms existing methods in both visual quality and geometric consistency.
Authors: Jinghui Lu, Jiayi Guan, Zhijian Huang, Jinlong Li, Guang Li, Lingdong Kong, Yingyan Li, Han Wang, Shaoqing Xu, Yuechen Luo, Fang Li, Chenxu Dang, Junli Wang, Tao Xu, Jing Wu, Jianhua Wu, Xiaoshuai Hao, Wen Zhang, Tianyi Jiang, Lingfeng Zhang, Lei Zhou, Yingbo Tang, Jie Wang, Yinfeng Gao, Xizhou Bu, Haochen Tian, Yihang Qiu, Feiyang Jia, Lin Liu, Yigu Ge, Hanbing Li, Yuannan Shen, Jianwei Cui, Hongwei Xie, Bing Wang, Haiyang Sun, Jingwei Zhao, Jiahui Huang, Pei Liu, Zeyu Zhu, Yuncheng Jiang, Zibin Guo, Chuhong Gong, Hanchao Leng, Kun Ma, Naiyan Wang, Guang Chen, Kuiyuan Yang, Hangjun Ye, Long Chen
Abstract: Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that is prohibitive for real-time deployment. Latent CoT methods attempt to close this gap by compressing reasoning into continuous hidden states, but consistently fall short of their explicit counterparts. We suggest that this is due to purely linguistic latent representations compressing a symbolic abstraction of the world, rather than the causal dynamics that actually govern driving. Thus, we present OneVL (One-step latent reasoning and planning with Vision-Language explanations), a unified VLA and World Model framework that routes reasoning through compact latent tokens supervised by dual auxiliary decoders. Alongside a language decoder that reconstructs text CoT, we introduce a visual world model decoder that predicts future-frame tokens, forcing the latent space to internalize the causal dynamics of road geometry, agent motion, and environmental change. A three-stage training pipeline progressively aligns these latents with trajectory, language, and visual objectives, ensuring stable joint optimization. In inference, the auxiliary decoders are discarded, and all latent tokens are prefilled in a single parallel pass, matching the speed of answer-only prediction. Across four benchmarks, OneVL becomes the first latent CoT method to surpass explicit CoT, delivering superior accuracy at answer-only latency. These results show that with world model supervision, latent CoT produces more generalizable representations than verbose token-by-token reasoning. Code has been open-sourced to the community. Project Page: https://xiaomi-embodied-intelligence.github.io/OneVL
Authors: Mengting Chen, Zhengrui Chen, Yongchao Du, Zuan Gao, Taihang Hu, Jinsong Lan, Chao Lin, Yefeng Shen, Xingjian Wang, Zhao Wang, Zhengtao Wu, Xiaoli Xu, Zhengze Xu, Hao Yan, Mingzhou Zhang, Jun Zheng, Qinye Zhou, Xiaoyong Zhu, Bo Zheng
Abstract: Recent advances in image generation and editing have opened new opportunities for virtual try-on. However, existing methods still struggle to meet complex real-world demands. We present Tstars-Tryon 1.0, a commercial-scale virtual try-on system that is robust, realistic, versatile, and highly efficient. First, our system maintains a high success rate across challenging cases like extreme poses, severe illumination variations, motion blur, and other in-the-wild conditions. Second, it delivers highly photorealistic results with fine-grained details, faithfully preserving garment texture, material properties, and structural characteristics, while largely avoiding common AI-generated artifacts. Third, beyond apparel try-on, our model supports flexible multi-image composition (up to 6 reference images) across 8 fashion categories, with coordinated control over person identity and background. Fourth, to overcome the latency bottlenecks of commercial deployment, our system is heavily optimized for inference speed, delivering near real-time generation for a seamless user experience. These capabilities are enabled by an integrated system design spanning end-to-end model architecture, a scalable data engine, robust infrastructure, and a multi-stage training paradigm. Extensive evaluation and large-scale product deployment demonstrate that Tstars-Tryon1.0 achieves leading overall performance. To support future research, we also release a comprehensive benchmark. The model has been deployed at an industrial scale on the Taobao App, serving millions of users with tens of millions of requests.
Authors: Tanuj Sur, Shashank Tripathi, Nikos Athanasiou, Ha Linh Nguyen, Kai Xu, Michael J. Black, Angela Yao
Abstract: We introduce UniCon3R, a unified feed-forward framework for online human-scene 4D reconstruction from monocular video. Current feed-forward human-scene reconstruction methods suffer from artifacts, where bodies float above the ground or penetrate parts of the scene. A key reason is the lack of effective interaction modelling between the human and the environment. Our goal is to exploit contact between the human and the scene during inference to actively improve the human mesh reconstruction. To that end, we explicitly model interaction by inferring 4D contact from the human pose and scene geometry and use the contact as a corrective cue for generating the pose. This enables UniCon3R to jointly recover scene geometry and spatially aligned 4D humans within the scene. Experiments on standard human-centric video benchmarks show that UniCon3R outperforms state-of-the-art baselines on physical plausibility and global human motion estimation while preserving fast, feed-forward inference speeds. The results validate our central claim: contact serves as a powerful internal prior, thus establishing a new paradigm for physically grounded joint human-scene reconstruction. Project page is available at https://surtantheta.github.io/UniCon3R .
Authors: Marwane Hariat, Gianni Franchi, David Filliat, Antoine Manzanera
Abstract: We present SS3D, a web-scale SfM-based self-supervision pretraining pipeline for feed-forward 3D estimation from monocular video. Our model jointly predicts depth, ego-motion, and intrinsics in a single forward pass and is trained/evaluated as a coherent end-to-end 3D estimator. To stabilize joint learning, we use an intrinsics-first two-stage schedule and a unified single-checkpoint evaluation protocol. Scaling SfM self-supervision to unconstrained web video is challenging due to weak multi-view observability and strong corpus heterogeneity; we address these with a multi-view signal proxy (MVS) used for filtering and curriculum sampling, and with expert training distilled into a single student. Pretraining on YouTube-8M (~100M frames after filtering) yields strong cross-domain zero-shot transfer and improved fine-tuning performance over prior self-supervised baselines. We release the pretrained checkpoint and code.
Authors: Nikoo Moradi, Gijs Luijten, Behrus Hinrichs-Puladi, Jens Kleesiek, Victor Alves, Jan Egger, Andr\'e Ferreira
Abstract: Diffusion models produce high-quality synthetic data but suffer from slow inference. We propose 3D Variable-Step Denoising Diffusion Probabilistic Model (VS-DDPM) a framework engineered to maintain generative quality while accelerating inference by several factors. We tested our approach on four tasks (missing MRI, tumor removal, MRI-to-sCT, and CBCT-to-sCT) within the BraTS2025 and SynthRAD2025 challenges. Designed for high efficiency under hardware and time constrains imposed by both challenges. VS-DDPM achieved state-of-the-art (SOTA) performance in missing MRI synthesis, yielding Dice scores of 0.80, 0.83, and 0.88 for the enhancing tumor, tumor core, and whole tumor regions, respectively, alongside a structural similarity index (SSIM) of 0.95. For MRI tumor removal, the model attained a root mean squared error (RMSE) of 0.053, a peak signal-to-noise ratio (PSNR) of 26.77, and an SSIM of 0.918. While the framework demonstrated competitive performance in MRI-to-sCT and CBCT-to-sCT tasks, it did not reach SOTA benchmarks, potentially due to sensitivities in data pre and post-processing pipelines or specific loss function configurations. These results demonstrate that VS-DDPM provides a robust and tunable solution for high-fidelity 3D medical image synthesis. The code is available in https://github.com/andre-fs-ferreira/SynthRAD_by_Faking_it.
URLs: https://github.com/andre-fs-ferreira/SynthRAD_by_Faking_it.
Authors: Haojie Zhang, Di Wu, Bingyan Liu, Linjie Zhong, Yuancheng Wei, Xingsong Ye, Nanqing Liu, Yaling Liang
Abstract: While video foundation models excel at single-shot generation, real-world cinematic storytelling inherently relies on complex multi-shot sequencing. Further progress is constrained by the absence of datasets that address three core challenges: authentic narrative logic, spatiotemporal text-video alignment conflicts, and the "copy-paste" dilemma prevalent in Subject-to-Video (S2V) generation. To bridge this gap, we introduce MuSS, a large-scale, dual-track dataset tailored for multi-shot video and S2V generation. Sourced from over 3,000 movies, MuSS explicitly supports both complex montage transitions and subject-centric narratives. To construct this dataset, we pioneer a progressive captioning pipeline that eliminates contextual conflicts by ensuring local shot-level accuracy before enforcing global narrative coherence. Crucially, we implement a cross-shot matching mechanism to fundamentally eradicate the S2V copy-paste shortcut. Alongside the dataset, we propose the Cinematic Narrative Benchmark, featuring a visual-logic-driven paradigm and a novel Anti-Copy-Paste Variance (ACP-Var) metric to rigorously assess continuous storytelling and 3D structural consistency. Extensive experiments demonstrate that while current baselines struggle with continuous narrative logic or degenerate into trivial 2D sticker generators, our MuSS-augmented model achieves state-of-the-art narrative effectiveness and cross-shot identity preservation.
Authors: Ben Wan, Yan Feng, Zihan Tang, Weizhe Huang, Yuting Zeng, Jia Wang, Tongxuan Liu
Abstract: DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural information. Moreover, current token pruning methods for conventional vision-language models (VLMs) fail to preserve textual fidelity due to improper compression mechanisms. By analyzing the decoding process of DeepSeek-OCR, we find that a distinct two-stage reading trajectory: the model initially prioritizes the majority of high-norm tokens, then subsequently redistributes its attention to the remaining ones. Motivated by this insight, we propose RTPrune, a two-stage token pruning method tailored for DeepSeek-OCR. In the first stage, we prioritize high-norm visual tokens that capture salient textual and structural information. In the second stage, the remaining tokens are paired and merged based on optimal transport theory to achieve efficient feature aggregation. We further introduce a dynamic pruning ratio that adapts to token similarity and textual density for OCR tasks, enabling a better efficiency-accuracy trade-off. Extensive experiments demonstrate state-of-the-art performance, as evidenced by 99.47% accuracy and 1.23$\times$ faster prefill on OmniDocBench, achieved with 84.25% token retention when applied to DeepSeek-OCR-Large.
Authors: Zhenhua Ning, Xin Li, Jun Yu, Guangming Lu, Yaowei Wang, Wenjie Pei
Abstract: While 3D Gaussian Splatting (3DGS) has demonstrated impressive real-time rendering performance, its efficacy remains constrained by a reliance on heuristic density control. Despite numerous refinements to these handcrafted rules, such methods inherently lack the flexibility to adapt to diverse scenes with complex geometries. In this paper, we propose a paradigm shift for density control from rigid heuristics to fully learnable policies. Specifically, we introduce \textbf{LeGS}, a framework that reformulates density control as a parameterized policy network optimized via Reinforcement Learning (RL). Central to our approach is the tailored effective reward function grounded in sensitivity analysis, which precisely quantifies the marginal contribution of individual Gaussians to reconstruction quality. To maintain computational tractability, we derive a closed-form solution that reduces the complexity of reward calculation from $O(N^2)$ to $O(N)$. Extensive experiments on the Mip-NeRF 360, Tanks \& Temples, and Deep Blending datasets demonstrate that \textbf{LeGS} significantly outperforms state-of-the-art methods, striking a superior balance between reconstruction quality and efficiency. The code will be released at https://github.com/AaronNZH/LeGS
Authors: Nadav Z. Cohen, Ofir Abramovich, Ariel Shamir
Abstract: Text-to-image diffusion models generate images by gradually converting white Gaussian noise into a natural image. White Gaussian noise is well suited for producing diverse outputs from a single text prompt due to its absence of structure. However, this very property limits control over, and predictability of, specific visual attributes, as the noise is not human-interpretable. In this work, we investigate the characteristics of the input noise in diffusion models. We show that, although all frequencies in white Gaussian noise have comparable statistical energy, low-frequency components primarily determine the images global structure and color composition, while high-frequency components control finer details. Building on this observation, we demonstrate that simple manipulations of the low-frequency noise using low-frequency image priors can effectively condition the generation process to reconstruct these low-frequency visual cues. This allows us to define a simple, training-free method with minimal overhead that steers overall image structure and color, while letting high-frequency components freely emerge as fine details, enabling variability across generated outputs.
Authors: Justin williams, Kishor Datta Gupta, Roy George, Mrinmoy Sarkar
Abstract: Vision-language-action (VLA) models have shown strong semantic grounding and task generalization in manipulation, but aerial deployment remains difficult because drones require low-latency closed-loop guidance under strict onboard compute and communication constraints. We present LiteVLA-H, a compact 256M-parameter VLA system designed for dual-rate operation on an NVIDIA Jetson AGX Orin: a fast outer-loop guidance mode for short action-token outputs and a slower semantic mode for scene understanding, hazard description, and operator-facing narration. The central empirical observation is that, in this compact edge regime, end-to-end latency is dominated by multimodal pre-fill rather than by the marginal cost of decoding a few extra tokens. This motivates a scheduler that issues reactive action tokens at 50.65,ms (19.74,Hz) while still supporting sentence-level semantic outputs at 149.90--164.57\ms (6.08--6.67,Hz) on the same embedded platform. To specialize the model without collapsing its descriptive competence, we use a knowledge-preserving fine-tuning recipe that mixes reactive flight data, aerial semantic data, and generic caption/VQA supervision. Beyond reporting current latency measurements, we position the system against recent state-of-the-art architectures, including AnywhereVLA, FutureVLA, and ReMem-VLA, showing that the measured action branch reaches a higher edge inference rate under our deployment conditions while retaining periodic semantic awareness.
Authors: Anjie Liu, Ziqin Gong, Yan Song, Yuxiang Chen, Xiaolong Liu, Hengtong Lu, Kaike Zhang, Chen Wei, Jun Wang
Abstract: Visual perception in modern Vision-Language Models (VLMs) is constrained by a perceptual bandwidth bottleneck: a broad field of view preserves global context but sacrifices the fine-grained details required for complex reasoning. We argue that high-resolution visual reasoning is therefore not only semantic reasoning but also task-relevant evidence acquisition under limited perceptual bandwidth. Inspired by active vision and information foraging, we formalise this process as sequential Bayesian optimal experimental design (S-BOED), where an agent decides which visual evidence to acquire before answering. Since exact Bayesian inference is intractable in continuous gigapixel spaces, we derive a tractable coverage--resolution objective as a proxy for task-relevant information gain. We instantiate this framework with FOVEA, a training-free procedure that refines VLM crop proposals through evidence-oriented probing. Experiments on high-resolution benchmarks show consistent gains over direct and ReAct-style baselines, with particularly strong improvements in search-dominated remote-sensing settings.
Authors: Peggy Joy Lu, Wei-Yu Chen, Yao-Tsung Huang, Vincent Shin-Mu Tseng
Abstract: We propose HeroCrystal, a novel privacy-preserving framework for multi-camera domain-adaptive object detection, addressing challenges such as data privacy, class imbalance, and heterogeneous architectures. Our framework consists of three key stages. In the Generated Stage, we introduce a one-shot, target-aware diffusion-based generation module that learns visual style from a single target-domain image while leveraging prompt-based control to synthesize specific object instances. Unlike conventional style transfer-based methods that require large target datasets and ignore semantic-level discrepancies, our approach enables privacy-preserving augmentation to reduce ethical concerns, and introduces controllable rare object generation to mitigate long-tailed category degradation. In the Federated Stage, we employ probabilistic Faster R-CNN on the client side to improve localization accuracy, and a dynamic model contrastive strategy to suppress domain-specific bias. The server side performs model fusion across heterogeneous architectures without accessing raw data. Finally, in the Distilled Stage, we propose an inconsistent categories integration algorithm to resolve label inconsistency and architecture heterogeneity across clients. Extensive experiments on multiple cross-domain detection benchmarks demonstrate that our method outperforms existing multi-source domain adaptation and federated learning baselines under multi-class, privacy-preserving settings. Our method improves mAP by +2.1% over prior privacy-preserving approaches and achieves a new state-of-the-art mAP of 33.4%, highlighting the effectiveness of HeroCrystal in enabling practical multi-camera AI surveillance systems. The source code is publicly available at https://github.com/ccuvislab/HeroCrystal.
Authors: Andong Deng, Dawei Du, Zhenfang Chen, Wen Zhong, Fan Chen, Guang Chen, Chia-Wen Kuo, Longyin Wen, Chen Chen, Sijie Zhu
Abstract: Real-world video editing demands not only expert knowledge of cinematic techniques but also multimodal reasoning to select, align, and combine footage into coherent narratives. While recent Large Multimodal Models (LMMs) have shown remarkable progress in general video understanding, their abilities in multi-video reasoning and operational editing workflows remain largely unexplored. We introduce VEBENCH, the first comprehensive benchmark designed to evaluate both editing knowledge understanding and operational reasoning in realistic video editing scenarios. VEBENCH contains 3.9K high-quality edited videos (over 257 hours) and 3,080 human-verified QA pairs, built through a three-round human-AI collaborative annotation pipeline that ensures precise temporal labeling and semantic consistency. It features two complementary QA tasks: 1) Video Editing Technique Recognition, assessing models' ability to identify 7 editing techniques using multimodal cues; and 2) Video Editing Operation Simulation, modeling real-world editing workflows by requiring the selection and temporal localization of relevant clips from multiple candidates. Extensive experiments across proprietary (e.g., Gemini-2.5-Pro) and open-source LMMs reveal a large gap between current model performance and human-level editing cognition. These results highlight the urgent need for bridging video understanding with creative operational reasoning. We envision VEBENCH as a foundation for advancing intelligent video editing systems and driving future research on complex reasoning.
Authors: Zihao Guo, Jihua Zhu, Jian Liu, Ajmal Saeed Mian
Abstract: Pre-trained 3D point cloud foundation models (PFMs) have demonstrated strong transferability across diverse downstream tasks. However, full fine-tuning these models is computationally expensive and storage-intensive. Parameter-efficient fine-tuning (PEFT) offers a promising alternative, but existing PEFT approaches are primarily designed for Transformer-based backbones and rely on token-level prompting or feature transformation. Mamba-based backbones introduce a granularity mismatch between token-level adaptation and state-level sequence dynamics. Consequently, straightforward transfer of existing PEFT approaches to frozen Mamba backbones leads to substantial accuracy degradation and unstable optimization. To address this issue, we propose Mantis, the first Mamba-native PEFT framework for 3D PFMs. Specifically, a State-Aware Adapter (SAA) is introduced to inject lightweight task-conditioned control signals into selective state-space updates, enabling state-level adaptation while keeping the pre-trained backbone frozen. Moreover, different valid point cloud serializations are regularized by Dual-Serialization Consistency Distillation (DSCD), thereby reducing serialization-induced instability. Extensive experiments across multiple benchmarks demonstrate that our Mantis achieves competitive performance with only about 5% trainable parameters. Our code is available at https://github.com/gzhhhhhhh/Mantis.
Authors: Chih-Chung Liu, Zhiwei Lin, Yongtao Wang
Abstract: Open-world object detection aims to localize and recognize objects beyond a fixed closed-set label space. It is commonly divided into two categories, i.e., open-vocabulary detection, which assumes a predefined category list at test time, and open-ended detection, which requires generating candidate categories during the inference. Existing methods rely primarily on coarse textual semantics and parametric knowledge, which often provide insufficient visual evidence for fine-grained appearance variation, rare categories, and cluttered scenes. In this paper, we propose VL-SAM-v3, a unified framework that augments open-world detection with retrieval-grounded external visual memory. Specifically, once candidate categories are available, VL-SAM-v3 retrieves relevant visual prototypes from a non-parametric memory bank and transforms them into two complementary visual priors, i.e., sparse priors for instance-level spatial anchoring and dense priors for class-aware local context. These priors are integrated with the original detection prompts via Memory-Guided Prompt Refinement, enabling a shared retrieval-and-refinement mechanism that supports open-vocabulary and open-ended inference. Extensive zero-shot experiments on LVIS show that VL-SAM-v3 consistently improves detection performance under both open-vocabulary and open-ended inference, with particularly strong gains on rare categories. Moreover, experiments with a stronger open-vocabulary detector (i.e., SAM3) validate the generality of the proposed retrieval-and-refinement mechanism.
Authors: Ahmed Cherif
Abstract: Low-light image enhancement is a fundamental challenge in computer vision and multimedia applications, as images captured under insufficient illumination suffer from poor visibility, low contrast, and color distortion. Existing Retinex-based methods rely on manually tuned parameters that fail to generalize across diverse lighting conditions. This paper proposes BFORE (Butterfly-Firefly Optimized Retinex Enhancement), a novel hybrid metaheuristic-optimized framework that automatically tunes the parameters of a multi-stage Retinex-based pipeline. The proposed method converts the input image to HSV color space and applies Adaptive Gamma Correction with Weighted Distribution (AGCWD) to the luminance channel, followed by adaptive denoising. A Butterfly Optimization Algorithm (BOA) optimizes the Multi-Scale Retinex with Color Restoration (MSRCR) parameters, while a Firefly Algorithm (FA) optimizes the AGCWD and denoising parameters. A hybrid BOA-FA switching strategy dynamically balances global exploration and local exploitation. Experimental evaluation on the LOL benchmark dataset (15 paired test images) demonstrates that BFORE achieves the highest PSNR (17.22 dB) among all traditional enhancement methods, with 20.3% improvement over Histogram Equalization and 17.5% over MSRCR. BFORE produces the most naturally balanced mean brightness (129.97), closest to the ideal mid-tone value. Notably, BFORE outperforms RetinexNet -- a deep learning baseline -- in both PSNR (17.22 vs. 16.77 dB) and SSIM (0.5417 vs. 0.4252) without requiring any training data. The hybrid BOA-FA optimization contributes a 12.3% PSNR improvement and 14.8% SSIM improvement over the unoptimized pipeline.
Authors: Zhuoyue Zhang, Jihua Zhu, Chaowei Fang, Jian Liu, Ajmal Saeed Mian
Abstract: Dynamic point cloud pretraining is still dominated by masked reconstruction objectives. However, these objectives inherit two key limitations. Existing methods inject ground-truth tube centers as decoder positional embeddings, causing spatio-temporal positional leakage. Moreover, they supervise inter-frame motion with deterministic proxy targets that systematically discard distributional structure by collapsing multimodal trajectory uncertainty into conditional means. To address these limitations, we propose Diffusion Masked Pretraining (DiMP), a unified self-supervised framework for dynamic point clouds. DiMP introduces diffusion modeling into both positional inference and motion learning. It first applies forward diffusion noise only to masked tube centers, then predicts clean centers from visible spatio-temporal context. This removes positional leakage while preserving visible coordinates as clean temporal anchors. DiMP also reformulates point-wise inter-frame displacement supervision as a DDPM noise-prediction objective conditioned on decoded representations. This design drives the encoder to target the full conditional distribution of plausible motions under a variational surrogate, rather than collapsing to a single deterministic estimate. Extensive experiments demonstrate that DiMP consistently improves downstream accuracy over the backbone alone, with absolute gains of 11.21% on offline action segmentation and 13.65% under causally constrained online inference.Codes are available at https://github.com/InitalZ/DiMP.git.
Authors: Tencent HY Team
Abstract: Video generation models internalize physical realism as their prior. Anime deliberately violates physics: smears, impact frames, chibi shifts; and its thousands of coexisting artistic conventions yield no single "physics of anime" a model can absorb. Physics-biased models therefore flatten the artistry that defines the medium or collapse under its stylistic variance. We present AniMatrix, a video generation model that targets artistic rather than physical correctness through a dual-channel conditioning mechanism and a three-step transition: redefine correctness, override the physics prior, and distinguish art from failure. First, a Production Knowledge System encodes anime as a structured taxonomy of controllable production variables (Style, Motion, Camera, VFX), and AniCaption infers these variables from pixels as directorial directives. A trainable tag encoder preserves the field-value structure of this taxonomy while a frozen T5 encoder handles free-form narrative; dual-path injection (cross-attention for fine-grained control, AdaLN modulation for global enforcement) ensures categorical directives are never diluted by open-ended text. Second, a style-motion-deformation curriculum transitions the model from near-physical motion to full anime expressiveness. Third, deformation-aware preference optimization with a domain-specific reward model separates intentional artistry from pathological collapse. On an anime-specific human evaluation with five production dimensions scored by professional animators, AniMatrix ranks first on four of five, with the largest gains over Seedance-Pro 1.0 on Prompt Understanding (+0.70, +22.4 percent) and Artistic Motion (+0.55, +16.9 percent). We are preparing accompanying resources for public release to support reproducibility and follow-up research.
Authors: Muyao Peng, Shun Zou, Pei An, You Yang, Qiong Liu
Abstract: Image-to-point-cloud registration (I2P) is a fundamental task in robotic applications such as manipulation,grasping, and localization. Existing deep learning-based I2P methods seek to align image and point cloud features in a learned representation space to establish correspondences, and have achieved promising results. However, when the inlier ratio of the initial matching pairs is low, conventional Perspective-n-Points (PnP) methods may struggle to achieve accurate results. To address this limitation, we propose Angle-I2P, an outlier rejection network that leverages angle-consistent geometric constraints and hierarchical attention. First, we design a scale-invariant, crossmodality geometric constraint based on angular consistency. This explicit geometric constraint guides the model in distinguishing inliers from outliers. Furthermore, we propose a global-tolocal hierarchical attention mechanism that effectively filters out geometrically inconsistent matches under rigid transformation, thereby improving the Inlier Ratio (IR) and Registration Recall (RR). Experimental results demonstrate that our method achieves state-of-the-art performance on the 7Scenes, RGBD Scenes V2, and a self-collected dataset, with consistent improvements across all benchmarks.
Authors: Zishu Zhou, Zaipeng Xie, Xuanyao Jie
Abstract: Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled test streams, yet existing methods largely inherit assumptions from vision tasks and underexploit the inherent inter-window temporal structure in WHAR streams. In this paper, we revisit such temporal structure as a feature-conditioned inference signal rather than merely an output-space smoothing prior. We derive the insight that temporal continuity and observation-induced feature deviations provide complementary cues for determining when to preserve or release temporal inertia and where to route prediction refinement during likely transitions. Building upon this insight, we propose SIGHT, a lightweight and backpropagation-free TTA framework for WHAR, enabling real-time edge deployment. SIGHT estimates predictive surprise by comparing the current feature with a prototype-based expected state, and then uses the resulting feature deviation to guide geometry-aware transition routing based on prototype alignment and stream-level marginal habit tracking. Evaluations on real-world datasets confirm that SIGHT outperforms existing TTA baselines while reducing computational and memory costs.
Authors: Huan Zhang, Lianghong Tan, Yichu Xu, Jiangzhong Cao, Huanqi Wu, Linwei Zhu, Xu Zhang
Abstract: In the Industrial Internet of Things (IIoT), enabling intelligent, real-time Printed Circuit Board (PCB) defect inspection is critical for ensuring product reliability. However, existing IIoT-based visual inspection systems face two compounding challenges: scarce and imbalanced defect samples that limit model training, and insufficient feature representation under complex circuit backgrounds. Existing generation methods rely on single-modality conditions with coarse structural control, while detection methods improve architectures without addressing the data bottleneck. To resolve both challenges jointly, we propose a generation-assisted PCB defect inspection framework that integrates controlled defect synthesis with task-specific defect detection within an IIoT-enabled pipeline. On the generation side, a Multi-modal Condition Generator extracts complementary edge, depth, and text conditions in parallel. A ScaleEncoder then embeds these conditions into the diffusion U-Net at four resolutions, and a Condition Modulation applies FiLM-style spatially-adaptive modulation at each scale, enabling structurally aligned and defect-aware sample synthesis to augment the scarce IIoT dataset. On the detection side, an Inverted Residual Shift Attention couples self-attention with shift-wise convolution to jointly capture global context and local texture, and a Cross-level Complementary Fusion Block generates pixel-level gates for selective cross-level feature fusion. The synthesized samples directly enrich the detection training set, so that improvements in generation compound with improvements in detection. Extensive experiments on DsPCBSD+ demonstrate that UniPCB achieves mAP@0.5 of 98.0% and mAP@0.5:0.95 of 61.8% on defect detection, surpassing all compared methods, while the generation branch attains an FID of 129.61 and SSIM of 0.619, outperforming existing conditional generation approaches.
Authors: Philip Wootaek Shin, Ajay Narayanan Sridhar, Sivani Devarapalli, Rui Zhang, Jack Sampson, Vijaykrishnan Narayanan
Abstract: Vision-language models (VLMs) achieve strong multimodal performance but remain prone to relation hallucination, which requires accurate reasoning over inter-object interactions. We study the impact of visual perturbations, specifically rotation and noise, and show that even mild distortions significantly degrade relational reasoning across models and datasets. We further evaluate prompt-based augmentation and preprocessing strategies (orientation correction and denoising), finding that while they offer partial improvements, they do not fully resolve hallucinations. Our results reveal a gap between perceptual robustness and relational understanding, highlighting the need for more robust, geometry-aware VLMs.
Authors: Yuan Wu, Zhiqiang Yan, Jiawei Lian, Zhengxue Wang, Jian Yang
Abstract: 3D occupancy prediction aims to infer dense, voxel-wise scene semantics from sensor observations, where the 2D-to-3D view transformation serves as a crucial step in bridging image features and volumetric representations. Most previous methods rely on a fixed projection space, where 3D reference points are uniformly sampled along pillars. However, such sampling struggles to capture the sparsity and height variations of real-world scenes, leading to ambiguous correspondences and unreliable feature aggregation. To address these challenges, we propose HiPR, a camera-LiDAR occupancy framework with Height-Guided Projection Reparameterization. HiPR first encodes LiDAR into a BEV height map to capture the maximum height of the point cloud. HiPR then adjusts the sampling range of each pillar using the height prior, enabling adaptive reparameterization of the projection space. As a result, the projected points are redistributed into geometrically meaningful regions rather than fixed ranges. Meanwhile, we mask out the invalid parts of the height map to avoid misleading the feature aggregation. In addition, to alleviate the training instability caused by noisy LiDAR-derived heights, we introduce a training-time Progressive Height Conditioning strategy, which gradually transitions the conditioning signal from ground-truth heights to LiDAR heights. Extensive experiments demonstrate that HiPR consistently outperforms existing state-of-the-art methods while maintaining real-time inference. The code and pretrained models can be found at https://github.com/yanzq95/HiPR.
Authors: Jakob Dexl, Katharina Jeblick, Andreas Mittermeier, Balthasar Schachtner, Anna Theresa St\"uber, Johanna Topalis, Maximilian Rokuss, Fabian Isensee, Klaus H. Maier-Hein, Hamza Kalisch, Jens Kleesiek, Constantin M. Seibold, Hussain Alasmawi, Lap Yan Lennon Chan, Yixuan Yuan, Alexander Jaus, Rainer Stiefelhagen, Pauline Ornela Megne Choudja, Konstantin Nikolaou, Christian La Foug\`ere, Sergios Gatidis, Matthias P. Fabritius, Maurice Heimer, Gizem Abaci, Lalith Kumar Shiyam Sundar, Rudolf A. Werner, Jens Ricke, Clemens C. Cyran, Thomas K\"ustner, Michael Ingrisch
Abstract: We report the design and results of the third autoPET challenge (MICCAI 2024), which benchmarked automated lesion segmentation in whole-body PET/CT under a compositional generalization setting. Training data comprised 1,014 [18F]-FDG PET/CT studies from the University Hospital T\"ubingen and 597 [18F]/[68Ga]-PSMA PET/CT studies from the LMU University Hospital Munich, constituting the largest publicly available annotated PSMA PET/CT dataset to date. The held-out test set of 200 studies covered four tracer-center combinations, two of which represented unseen compositional pairings. A complementary data-centric award category isolated the contribution of data handling strategies by restricting participants to a fixed baseline model. Seventeen teams submitted 27 algorithms, predominantly nnU-Net-based 3D networks with PET/CT channel concatenation. The top-ranked algorithm achieved a mean DSC of 0.66, FNV of 3.18 mL, and FPV of 2.78 mL across all four test conditions, improving DSC by 8% and reducing the false-negative volume by 5 mL relative to the provided baseline. Ranking was stable across bootstrap resampling and alternative ranking schemes for the top tier. Beyond the benchmark, we provide an in-depth analysis of segmentation performance at the patient and lesion level. Three main conclusions can be drawn: (1) in-domain multitracer PET/CT segmentation is sufficient and probably approaching reader agreement; (2) compositional generalization to unseen tracer-center combinations remains an open problem mainly driven by systematic volume overestimation; (3) heterogeneity and case difficulty drive performance variation substantially more than the choice of algorithm among top-ranked teams.
Authors: Megha Mariam K. M, Vineeth N. Balasubramanian, C. V. Jawahar
Abstract: The communication of scientific knowledge has become increasingly multimodal, spanning text, visuals, and speech through materials such as research papers, slides, and recorded presentations. These different representations collectively convey a study's reasoning, results, and insights, offering complementary perspectives that enrich understanding. However, despite their shared purpose, such materials are rarely connected in a structured way. The absence of explicit links across formats makes it difficult to trace how concepts, visuals, and explanations correspond, limiting unified exploration and analysis of research content. To address this gap, we introduce the Multimodal Conference Dataset (MCD), the first benchmark that integrates research papers, presentation videos, explanatory videos, and slides from the same works. We evaluate a range of embedding-based and vision-language models to assess their ability to discover fine-grained cross-format correspondences, establishing the first systematic benchmark for this task. Our results show that vision-language models are robust but struggle with fine-grained alignment, while embedding-based models capture text-visual correspondences well but equations and symbolic content form distinct clusters in the embedding space. These findings highlight both the strengths and limitations of current approaches and point to key directions for future research in multimodal scientific understanding. To ensure reproducibility, we release the resources for MCD at https://github.com/meghamariamkm2002/MCD
Authors: Hao Lin, Kunyang Lv, Xu Jiang, Jingqi Tian, Zhongjing Du, Jiayu Ding, Qiaoman Zhang, Hongbo Jin
Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories. While reinforcement learning with verifiable rewards (RLVR) provides reliable supervision, it fails to capture token level contributions, leading to inefficient learning. Conversely, existing self distillation methods offer dense supervision but lack structure and diagnostic specificity, and often interact unstably with reinforcement learning. In this work, we propose VISD, a structured self distillation framework that introduces diagnostically meaningful privileged information for video reasoning. VISD employs a video aware judge model to decompose reasoning quality into multiple dimensions, including answer correctness, logical consistency, and spatio-temporal grounding, and uses this structured feedback to guide a teacher policy for token level supervision. To stably integrate dense supervision with RL, we introduce a direction magnitude decoupling mechanism, where rollout level advantages computed from rewards determine update direction, while structured privileged signals modulate token level update magnitudes. This design enables semantically aligned and fine grained credit assignment, improving both reasoning faithfulness and training efficiency. Additionally, VISD incorporates curriculum scheduling and EMA based teacher stabilization to support robust optimization over long video sequences. Experiments on diverse benchmarks show that VISD consistently outperforms strong baselines, improving answer accuracy and spatio temporal grounding quality. Notably, VISD reaches these gains with nearly 2x faster convergence in optimization steps, highlighting the effectiveness of structured self supervision in improving both performance and sample efficiency for VideoLLMs.
Authors: YaoYang Liu, Yuechen Zhang, Wenbo Li, Yufei Zhao, Rui Liu, Long Chen
Abstract: High-resolution image-to-video (I2V) generation aims to synthesize realistic temporal dynamics while preserving fine-grained appearance details of the input image. At 2K resolution, it becomes extremely challenging, and existing solutions suffer from various weaknesses: 1) end-to-end models are often prohibitively expensive in memory and latency; 2) cascading low-resolution generation with a generic video super-resolution tends to hallucinate details and drift from input-specific local structures, since the super-resolution stage is not explicitly conditioned on the input image. To this end, we propose SwiftI2V, an efficient framework tailored for high-resolution I2V. Following the widely used two-stage design, it addresses the efficiency--fidelity dilemma by first generating a low-resolution motion reference to reduce token costs and ease the modeling burden, then performing a strongly image-conditioned 2K synthesis guided by the motion to recover input-faithful details with controlled overhead. Specifically, to make generation more scalable, SwiftI2V introduces Conditional Segment-wise Generation (CSG) to synthesize videos segment-by-segment with a bounded per-step token budget, and adopts bidirectional contextual interaction within each segment to improve cross-segment coherence and input fidelity. On VBench-I2V at 2K resolution, SwiftI2V achieves performance comparable to end-to-end baselines while reducing total GPU-time by 202x. Particularly, it enables practical 2K I2V generation on a single datacenter GPU (e.g., H800) or consumer GPU (e.g., RTX 4090).
Authors: Yuchen Guo, Junli Gong, Yao Lu, Xintong Xu, Yiuming Cheung, Weifeng Su
Abstract: Infrared-Visible image fusion (IVIF) aims to integrate thermal information and detailed spatial structures into a single fused image to enhance perception. However, existing evaluation approaches tend to over-optimize both hand-crafted no-reference statistics and full-reference metrics that treat the source images as pseudo ground truths. Recent IVIF reward-modelling efforts learn from human ratings but use scalar regression on aggregated scores, neither leveraging the reasoning of Multimodal Large Language Models (MLLMs) nor encoding per-image perceptual ambiguity in their supervision, but naively introducing MLLMs with discrete one-hot supervision likewise collapses fused images of similar quality into different rating levels. To address this, we introduce FuScore, which utilizes an MLLM to mimic human visual perception by producing continuous quality score, rather than discrete level predictions, enabling fine-grained discrimination among fused images of similar quality. We exploit the agreement among four IVIF-specific sub-dimensions to construct a per-image soft label whose sharpness reflects how consensual the overall judgment is. We further introduce a tripartite objective combining per-image distributional supervision, within-source-pair Thurstone fidelity for method-level ordering, and cross-source-pair Thurstone fidelity for scene-level ordering across scenes. Extensive experiments demonstrate that FuScore achieves state-of-the-art correlation with human visual preferences.
Authors: Chamuditha Jayanga Galappaththige, Jason Lai, Timothy Patten, Donald Dansereau, Niko Suenderhauf, Dimity Miller
Abstract: Scene change detection methods built on Gaussian splatting universally follow a render-then-compare paradigm: the pre-change scene is rendered into 2D and compared against post-change images via pixel or feature residuals. This change detection problem with Gaussian Splatting has been treated as a question about pixels; we treat it as a question about primitives. We provide direct evidence that native primitive attributes alone -- position, anisotropic covariance, and color -- carry sufficient signal for scene change detection. What makes primitive-space comparison hard is the under-constrained nature of Gaussian splatting representation: independent optimizations yield primitive solutions whose count, positions, shapes, and colors differ even where nothing has changed. We address this challenge with anisotropic models of geometric and photometric drift, complemented by a per-primitive observability term that reflects the extent to which each Gaussian is constrained by the camera geometry. Operating directly on primitives gives our method, GD-DIFF, two properties that distinguish it from render-then-compare methods. First, change maps are multi-view consistent by construction, where prior work had to learn this through an additional optimization objective. Second, geometric and appearance changes are scored separately, identifying not just where but what kind of change occurred, distinguishing structural changes (e.g., an added object) from surface-level ones (e.g., a color change) without supervision or external model dependencies. On real-world benchmarks, GS-DIFF surpasses the prior state-of-the-art approach by $\sim$17% in mean Intersection over Union.
Authors: Yu Pan, Andi Zhang, Yi Wang, Sibei Yang, Wenjie Wang
Abstract: Diffusion Vision-Language Models (dVLMs), built upon the non-causal foundations of Diffusion Large Language Models (dLLMs), have demonstrated remarkable efficacy in multimodal tasks by departing from the traditional autoregressive generation paradigm. While dVLMs appear inherently robust against conventional jailbreak tactics, which we categorize as Fixed Prefix Optimization (FPO) (e.g., anchoring responses with "Sure, here is"), this perceived resilience is deceptive. Our investigation into the safety landscape of dVLMs reveals a unique refusal pattern: Immediate Refusal and Progressive Refusal. We find that while FPO-based attacks often fail by triggering the latter, the progressive refinement process itself uncovers a novel, latent attack surface. To exploit this vulnerability, we propose Global Probability Optimization (GPO), a general jailbreak paradigm designed specifically for the denoising trajectory of masked diffusion models. Unlike prefix-based methods, GPO manipulates the global generative dynamics to bypass guardrails in diffusion language models. Building on this, we introduce GPO-V, the first visual-modality jailbreak framework tailored for dVLMs. Empirical results demonstrate that GPO-V produces stealthy perturbations with exceptional cross-model transferability, revealing a critical security gap in non-sequential generative architectures. Our findings underscore the critical urgency of addressing safety alignment in dVLMs. These results necessitate an immediate and fundamental re-evaluation of current defense paradigms to mitigate the unique risks of diffusion-based generation. Our code is available at: https://anonymous.4open.science/r/GPO-V-0250.
Authors: Linxiao Shi, Siming Zheng, Zerong Wang, Hao Zhang, Jinwei Chen, Bo Li, Shifeng Chen, Peng-Tao Jiang
Abstract: Existing mobile devices are constrained by compact optical designs, such as small apertures, which make it difficult to produce natural, optically realistic bokeh effects. Although recent learning-based methods have shown promising results, they still struggle with photos captured under high digital zoom levels, which often suffer from reduced resolution and loss of fine details. A naive solution is to enhance image quality before applying bokeh rendering, yet this two-stage pipeline reduces efficiency and introduces unnecessary error accumulation. To overcome these limitations, we propose MagicBokeh, a unified diffusion-based framework designed for high-quality and efficient bokeh rendering. Through an alternative training strategy and a focus-aware masked attention mechanism, our method jointly optimizes bokeh rendering and super-resolution, substantially improving both controllability and visual fidelity. Furthermore, we introduce degradation-aware depth module to enable more accurate depth estimation from low-quality inputs. Experimental results demonstrate that MagicBokeh efficiently produces photorealistic bokeh effects, particularly on real-world low-resolution images, paving the way for future advancements in bokeh rendering. Our code and models are available at https://github.com/vivoCameraResearch/MagicBokeh.
Authors: Yuliang Li, Chu Zhou, Heng Guo, Boxin Shi, Imari Sato, Zhanyu Ma
Abstract: Mainstream vision-language models (VLMs) fundamentally struggle with severe optical ambiguities, such as reflections and transparent objects, due to the inherent limitations of standard RGB inputs. While polarization imaging captures polarimetric physical parameters that resolve these ambiguities, existing methods are constrained by fixed-format outputs and remain isolated from open-ended reasoning. To bridge this semantic-physical gap, we introduce PolarVLM, the first multimodal framework integrating polarimetric physical parameters into VLMs. By employing a dual-stream architecture and a progressive two-stage training strategy, PolarVLM effectively prevents physical misinterpretations while preserving general visual abilities. Complementing our architecture, we construct PolarVQA, the first benchmark for polarization-aware VQA, featuring 75K physics-grounded instruction-tuning pairs targeting reflective and transparent scenes. Experiments show that PolarVLM surpasses the RGB baseline by 25.4% overall across five evaluation tasks, with remarkable gains of 26.6% in reflection recognition and 34.0% in glass counting, successfully unlocking physics-aware semantic understanding.
Authors: Ke Ma, Jiaqi Tang, Bin Guo, Xueting Han, Ruonan Xu, Qingfeng He, Ziheng Wang, Xu Wang, Qifeng Chen, Zhiwen Yu, Yunhao Liu
Abstract: Proactive streaming video understanding requires Video-LLMs to decide when to respond as a video unfolds, a task where existing methods often fall short due to their implicit, query-agnostic modeling of visual evidence. We introduce Response-G1, a novel framework that establishes explicit, structured alignment between the accumulated video evidence and the query's expected response conditions via scene graphs. The framework operates in three fine-tuning-free stages: (1) online query-guided scene graph generation from streaming clips; (2) memory-based retrieval of the most semantically relevant historical scene graphs; and (3) retrieval-augmented trigger prompting for per-frame "silence/response" decisions. By grounding both evidence and conditions in a shared graph representation, Response-G1 achieves more interpretable and accurate response timing decisions. Experimental results on established benchmarks demonstrate the superiority of our method in both proactive and reactive tasks, validating the advantage of explicit scene graph modeling and retrieval in streaming video understanding.
Authors: Berkehan \"Unal, Hauke Dierend, Dren Fazlija, Christopher Plachetka
Abstract: Over the last few years, research on autonomous systems has matured to such a degree that the field is increasingly well-positioned to translate research into practical, stakeholder-driven use cases across well-defined domains. However, for a wide-scale practical adoption of autonomous systems, adherence to safety regulations is crucial. Many regulations are influenced by the Operational Design Domain (ODD), which defines the specific conditions in which an autonomous agent can function. This is especially relevant for Automated Driving Systems (ADS), as a dependable perception of ODD elements is essential for safe implementation and auditing. Vision-language models (VLMs) integrate visual recognition and language reasoning, functioning without task-specific training data, which makes them suitable for adaptable ODD perception. To assess whether VLMs can function as zero-shot "ODD sensors" that adapt to evolving definitions, we contribute (i) an empirical study of zero-shot ODD classification and detection using four VLMs on a custom dataset and Mapillary Vistas, along with failure analyses; (ii) an ablation of zero-shot optimization strategies with a cost-performance overview; and (iii) a suite of reusable prompting templates with guidance for adaptation. Our findings indicate that definition-anchored chain-of-thought prompting with persona decomposition performs best, while other methods may result in reduced recall. Overall, our results pave the way for transparent and effective ODD-based perception in safety-critical applications.
Authors: Caterina Gallegati, Monica Bianchini, Franco Scarselli, Vittorio Murino, Barbara Toniella Corradini
Abstract: As generative models achieve unprecedented visual quality, the gold standard for image evaluation remains traditional feature-distribution metrics (e.g., FID). However, these metrics are provably hindered by the closed-vocabulary bottleneck of outdated features and the assumptive bias of rigid parametric formulations. Recent alternatives exploit modern backbones to solve the feature bottleneck, yet continue to suffer from parametric limitations. To close this gap, we introduce APEX (Assumption-free Projection-based Embedding eXamination), a novel evaluation framework leveraging the Sliced Wasserstein Distance as a mathematically grounded, assumption-free similarity measure. APEX inherits effective scalability to high-dimensional spaces, as we prove with theoretical and empirical evidences. Moreover, APEX is embedding-agnostic and uses two open-vocabulary foundation models, CLIP and DINOv2, as feature extractors. Benchmarking APEX against established baselines reveals superior robustness to visual degradations. Additionally, we show that APEX metrics exhibit intra- and cross-dataset stability, ensuring highly stable evaluations on out-of-domain datasets.
Authors: Peilin Xiong, Honghui Yuan, Junwen Chen, Keiji Yanai
Abstract: Coarse-mask local image editing asks a model to modify a user-indicated region while preserving the surrounding scene. In practice, however, rough masks often become unintended shape priors: instead of serving as flexible edit support, the mask can pull the generated object toward its accidental boundary. We study this failure as mask-shape bias and frame the task through a Two-Zone Constraint, where the background should remain stable while the editable region should follow the instruction without being forced to inherit the mask contour. BRIDGE addresses this setting by keeping masks outside the DiT backbone for support construction and blending, avoiding DiT-internal mask injection and copied control branches. It uses BridgePath generation, where a Main Path preserves background context and a Subject Path generates editable content from independent noise. Motivated by a diagnostic Qwen-Image experiment showing that positional embeddings and attention connectivity regulate which image context visual tokens reuse, BRIDGE introduces a learnable Discrete Geometric Gate for token-level positional-embedding routing. This gate lets subject tokens borrow background-anchored coordinates near fusion regions or keep subject-centric coordinates for geometric freedom. We evaluate BRIDGE on BRIDGE-Bench, MagicBrush, and ICE-Bench. On BRIDGE-Bench, BRIDGE improves Local SigLIP2-T from 0.262 with FLUX.1-Fill and 0.390 with ACE++ to 0.503, with parallel gains in local DINO and DreamSim. Zero-shot results on MagicBrush and ICE-Bench further indicate competitive alignment and source preservation beyond the curated benchmark, while the added routing module remains compact at 13.31M parameters compared with ControlNet-style copied branches.
Authors: Yulong Chen, Xiaoyun Dong, Haoyu Zhang, Zongxian Yang, Lewei Xie, Xinke Li, Yifan Zhang, Kai Wang, Jianping Wang
Abstract: Reconstructing dynamic scenes from Vehicle-to-Infrastructure Cooperative Autonomous Driving (VICAD) data is fundamentally complicated by temporal asynchrony: vehicle and infrastructure cameras operate on independent clocks, capturing the same dynamic agent such as cars and pedestrians at different physical times. Existing Gaussian Scene Graph methods implicitly assume synchronized observations and assign a single pose per agent per frame, which is an assumption that breaks in cooperative settings, where the resulting gradient conflicts cause severe ghosting on dynamic agents. We identify this as a representation-level failure, not an optimization artifact: we prove that any single-timeline formulation incurs an irreducible photometric loss scaling quadratically with agent velocity and cross-source time offset. To resolve this, we propose Dust (DecoUpled Spatio-Temporal) Gaussian Scene Graph for 4D Cooperative Driving Reconstruction. DUST Gaussian Scene Graph shares a canonical Gaussian set per agent for appearance consistency, while maintaining decouple pose trajectories aligned to each source's true capture timestamps. We prove that this decoupling enables the pose-gradient kernel block-diagonal, eliminating cross-source interference entirely. To make Dust practical, we further introduce a static anchor-based pose correction pipeline that corrects spatio misalignment between vehicle and infrastructure annotations, and a pose-regularized joint optimization scheme that prevents trajectory jitter and drift during early training. On 26 sequences from V2X-Seq, DUST achieves state-of-the-art performance, improving dynamic-area PSNR by 3.2 dB over the strongest baseline and reducing Fr\'echet Video Distance by 37.7%, with keeping robustness under larger temporal asynchrony.
Authors: Zuojin Tang, Shengchao Yuan, Xiaoxin Bai, Zhiyuan Jing, De Ma, Gang Pan, Bin Liu
Abstract: Vision-language-action (VLA) models increasingly rely on auxiliary world modules to plan over long horizons, yet how such modules should be parameterized on top of a pretrained VLA remains an open design question. Existing world-model-augmented VLAs typically pass the per-frame visual stream into the world module at high visual bandwidth and treat its rollout as a side product of action prediction; under a constrained adaptation budget on a frozen backbone, this leaves both the per-frame representation and the latent action coupling under-examined. We introduce OneWM-VLA, which compresses each view into a single semantic token per frame through an Adaptive Attention Pooling, and produces the resulting latent stream and the action trajectory under a single flow-matching objective rather than connecting them through a separate decoder. Empirically, we find that per-frame visual bandwidth can be reduced to a single token without compromising long-horizon performance under our setup. Trained with 14.71M LoRA parameters on a $\pi_0$ (2B) backbone, OneWM-VLA improves the average success rate from 47.9% to 61.3% on MetaWorld~MT50, reaches 95.6% on LIBERO-Long (vs.85.2% for $\pi_0$), and reaches 60.0% on the long-horizon deformable task Fold Cloth on a real Piper arm (vs.20.0% for $\pi_0$).
Authors: Laiqiao Qin, Tianqing Zhu, Linlin Wang, Wanlei Zhou
Abstract: Machine unlearning is an emerging technology that removes a subset of the training data from a trained model without significantly affecting the model performance on the remaining data. This topic is becoming increasingly important in protecting user privacy and eliminating harmful or outdated data. The key challenge lies in effectively and efficiently unlearning specific information without compromising the model's utility on the retained data. For pre-trained models, fine-tuning is an important way to achieve the unlearning target. Previous work typically fine-tuned the entire model's parameters, which incurred significant computational costs. In addition, the fine-tuning process may cause shifts in the intermediate layer features, affecting the model's overall utility. In this work, we propose a novel and efficient machine unlearning method for pre-trained models. We term the method Residual Feature Alignment Unlearning. Specifically, we leverage LoRA (Low-Rank Adaptation) to decompose the model's intermediate features into pre-trained features and residual features. By adjusting the residual features, we align the unlearned model with the pre-trained model at the intermediate feature level to achieve both unlearning and remaining targets. The method aims to learn zero residuals on the retained set and shifted residuals on the unlearning set. Extensive experiments on numerous datasets validate the effectiveness of our approach.
Authors: Hantang Li, Qiang Zhu, Xiandong Meng, Lei Xiong, Shuyuan Zhu, Xiaopeng Fan
Abstract: In practical applications, low-light images are often compressed for efficient storage and transmission. Most existing methods disregard compression artifacts removal or hardly establish a unified framework for joint task enhancement of low-light images with varying compression qualities. To address this problem, we propose an efficient hybrid priors-guided network (HPGN) that enhances compressed low-light images by integrating both compression and illumination priors. Our approach fully utilizes the JPEG quality factor (QF) and DCT quantization matrix (QM) to guide the design of efficient plug-and-play modules for joint tasks. Additionally, we employ a random QF generation strategy to guide model training, enabling a single model to enhance low-light images with different compression levels. Experimental results demonstrate the superiority of our proposed method.
Authors: Hania Ghouse, Juveria Tanveen, Abdul Muqtadir Ahmed, Uma N. Dulhare
Abstract: The increase in cardiac and pulmonary diseases presents an alarming and pervasive health challenge on a global scale responsible for unexpected and premature mortalities. In spite of how serious these conditions are, existing methods of detection and treatment encounter challenges, particularly in achieving timely diagnosis for effective medical intervention. Manual screening processes commonly used for primary detection of cardiac and respiratory problems face inherent limitations, increased by a scarcity of skilled medical practitioners in remote or under-resourced areas. To address this, our study introduces an innovative yet efficient model which integrates AI for diagnosing lung and heart conditions concurrently using the auscultation sounds. Unlike the already high-priced digital stethoscope, our proposed model has been particularly designed to deploy on low-cost embedded devices and thus ensure applicability in under-developed regions that actually face an issue of accessing medical care. Our proposed model incorporates MFCC feature extraction and engineering techniques to ensure that the signal is well analyzed for accurate diagnostics through the hybrid model combining Gated Recurrent Unit with CNN in processing audio signals recorded from the low-cost stethoscope. Beyond its diagnostic capabilities, the model generates digital audio records that facilitate in classifying six pulmonary and five cardiovascular diseases. Hence, the integration of a cost effective stethoscope with an efficient AI empowered model deployed on a web app providing real-time analysis, represents a transformative step towards standardized healthcare
Authors: Haibo Jin, Ruoxi Chen, Peiyan Zhang, Andy Zhou, Zelei Cheng, Haohan Wang
Abstract: As Large Language Models (LLMs) become increasingly integral to various domains, their potential to generate harmful responses has prompted significant societal and regulatory concerns. In response, governments have issued ethics guidelines to promote the development of trustworthy AI. However, these guidelines are typically high-level demands for developers and testers, leaving a gap in translating them into actionable testing questions to verify LLM compliance. To address this challenge, we introduce GUARD (Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics), a testing method designed to operationalize guidelines into specific guideline-violating questions that assess LLM adherence. To implement this, GUARD uses automated generation of guideline-violating questions based on government-issued guidelines, thereby testing whether responses comply with these guidelines. When responses directly violate guidelines, GUARD reports inconsistencies. Furthermore, for responses that do not directly violate guidelines, GUARD integrates the concept of ``jailbreaks'' to diagnostics, named GUARD-JD, which creates scenarios that provoke unethical or guideline-violating responses, effectively identifying potential scenarios that could bypass built-in safety mechanisms. Our method finally culminates in a compliance report, delineating the extent of adherence and highlighting any violations. We empirically validated the effectiveness of GUARD on eight LLMs, including Vicuna-13B, LongChat-7B, Llama2-7B, Llama-3-8B, GPT-3.5, GPT-4, GPT-4o, and Claude-3.7, by testing compliance under three government-issued guidelines and conducting jailbreak diagnostics. Additionally, GUARD-JD can transfer jailbreak diagnostics to vision-language models (MiniGPT-v2 and Gemini-1.5), demonstrating its usage in promoting reliable LLM-based applications.
Authors: Zheng Huang, Mingyu Liu, Xiaoyi Lin, Muzhi Zhu, Canyu Zhao, Zongze Du, Ye Lin, Xiaoman Li, Yiduo Jia, Hao Zhong, Hao Chen, Chunhua Shen
Abstract: Vision-Language-Action (VLA) models represent a pivotal advance in embodied intelligence, yet they confront critical barriers to real-world deployment, most notably catastrophic forgetting. This issue stems from their overreliance on continuous action sequences or action chunks, which inadvertently create isolated data silos that disrupt knowledge retention across tasks. To tackle these challenges, we propose the Narrowing of Trajectory VLA (NoTVLA) framework: a novel approach that narrows its focus to sparse trajectories, thereby avoiding the catastrophic forgetting associated with dense trajectory fine-tuning. A key innovation of NoTVLA lies in its trajectory planning strategy: instead of centering on the target object's trajectory, it leverages temporal compression and spatial reasoning pruning specifically for the robot end effector's trajectory. Furthermore, training is conducted using these sparse trajectories rather than dense action trajectories, an optimization that delivers remarkable practical advantages with better performance in zero-shot. In multi-task evaluation scenarios, NoTVLA achieves superior performance and generalization compared to pi0 while operating under two critical constraints: it uses over an order of magnitude less computing power than pi0 and requires no wrist-mounted camera. This design ensures that NoTVLA's operational accuracy closely approximates that of single-task expert models. Crucially, it also preserves the model's inherent language capabilities, enabling zero-shot generalization in specific scenarios, supporting unified model deployment across multiple robot platforms, and fostering a degree of generalization even when perceiving tasks from novel perspectives.
Authors: Alexander Murphy, Michal Danilowski, Soumyajit Chatterjee, Abhirup Ghosh
Abstract: Test-Time Adaptation (TTA) methods are often computationally expensive, require a large amount of data for effective adaptation, or are brittle to hyperparameters. Based on a theoretical foundation of the geometry of the latent space, we are able to significantly improve the alignment between source and distribution-shifted samples by re-centering target data embeddings at the origin. This insight motivates NEO -- a hyperparameter-free fully TTA method, that adds no significant compute compared to vanilla inference. NEO is able to improve the classification accuracy of ViT-Base on ImageNet-C from 55.6% to 59.2% after adapting on just one batch of 64 samples. When adapting on 512 samples NEO beats all 7 TTA methods we compare against on ImageNet-C, ImageNet-R and ImageNet-S and beats 6/7 on CIFAR-10-C, while using the least amount of compute. NEO performs well on model calibration metrics and additionally is able to adapt from 1 class to improve accuracy on 999 other classes in ImageNet-C. On Raspberry Pi and Jetson Orin Nano devices, NEO reduces inference time by 63% and memory usage by 9% compared to baselines. Our results based on 3 ViT architectures and 4 datasets show that NEO can be used efficiently and effectively for TTA.
Authors: Prakhar Srivastava, Farrin Marouf Sofian, Francesco Immorlano, Kushagra Pandey, Stephan Mandt
Abstract: Despite advances in test-time scaling and diffusion finetuning, guidance for Auto-Regressive Diffusion Models (ARDMs) remains underexplored. We introduce an amortized framework that augments a pretrained ARDM with an offline-trained controller. By previewing future rollouts, the controller learns stepwise corrections that anticipate observations under a terminal-cost objective, yielding a reusable policy for guided generation. Motivated by a stochastic optimal control view of ARDM trajectories, our method injects small controls within each denoising sub-step while staying close to the pretrained dynamics. We study this approach for dataassimilation (DA) in chaotic spatiotemporal partial differential equations (PDEs), where existing methods are often computationally expensive and susceptible to forecast drift under sparse observations. At inference, DA becomes a feed-forward rollout with on-the-fly corrections, achieving an order-of-magnitude speedup over strong diffusion-based baselines. Across two canonical PDEs and a compact ECMWF Reanalysis v5 (ERA5) pilot spanning six observation regimes, our method consistently improves stability and accuracy over state-of-the-art alternatives, with similar improvements observed in a larger-scale GenCast study.
Authors: Xi Yu, Yang Yang, Qun Liu, Yonghua Du, Sean McSweeney, Yuewei Lin
Abstract: Cellular image segmentation is essential for quantitative biology yet remains difficult due to heterogeneous modalities, morphological variability, and limited annotations. We present GenCellAgent, a training-free multi-agent framework that orchestrates specialist segmenters and generalist vision-language models via a planner-executor-evaluator loop (choose tool $\rightarrow$ run $\rightarrow$ quality-check) with long-term memory. The system (i) automatically routes images to the best tool, (ii) adapts on the fly using a few reference images when imaging conditions differ from what a tool expects, (iii) supports text-guided segmentation of organelles not covered by existing models, and (iv) commits expert edits to memory, enabling self-evolution and personalized workflows. Across seven cell-segmentation benchmarks spanning diverse microscopy modalities (4,718 images), this routing consistently matches or exceeds the best individual tool on every dataset and outperforms all baselines in overall accuracy. On out-of-distribution organelle data, GenCellAgent substantially outperforms specialist models that were not trained on the target domain, recovering structures that dedicated tools fail to detect. It also segments novel objects such as the Golgi apparatus via iterative text-guided refinement, with light human correction further boosting performance. Together, these capabilities provide a practical path to robust, adaptable cellular image segmentation without retraining, while reducing annotation burden and matching user preferences.
Authors: Wanqing Cui, Wei Huang, Yazhi Guo, Yibo Hu, Meiguang Jin, Junfeng Ma, Keping Bi
Abstract: Visual document retrieval requires understanding heterogeneous and multi-modal content to satisfy implicit information needs. Recent advances use screenshot-based document encoding with fine-grained late interaction to encode holistic information and capture nuanced alignments, significantly improving retrieval performance. However, retrievers are still trained with coarse global relevance labels, without revealing which regions support the match. As a result, retrievers tend to rely on surface-level cues and struggle to capture implicit semantic connections, hindering their ability to handle non-extractive queries.To improve fine-grained relevance modeling, we propose a Attention-Grounded REtriever Enhancement (AGREE) framework. AGREE leverages cross-modal attention from multimodal large language models (MLLMs) as proxy supervision to guide the retriever in identifying relevant document regions. Specifically, AGREE extracts attention maps from the MLLM that highlight which document regions are attended to based on the query. These attention scores serve as local, region-level relevance signals. During training, AGREE combines local signals with the global document-level relevance label to jointly optimize the retriever. This dual-level supervision enables the model to learn not only whether documents match, but also which content drives relevance. Experiments on the challenging visual document retrieval benchmark, ViDoRe V2, show that AGREE significantly outperforms the global-supervision-only baseline by 12.82\% and 5.03\% in terms of average nDCG@1 and nDCG@5. Quantitative and qualitative analyses further demonstrate that AGREE promotes deeper alignment between query terms and document regions, moving beyond surface-level matching toward more accurate and interpretable retrieval. Our code is available at: https://github.com/VickiCui/AGREE.
Authors: Yanhao Wu, Haoyang Zhang, Fei He, Rui Wu, Yanhu Shan, Congpei Qiu, Liang Gao, Wei Ke, Tong Zhang
Abstract: Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. While state-of-the-art (SOTA) methods use parallel planning architectures, they fail to explicitly couple speed decisions with agent behavior along the driving path, leading to suboptimal coordination. To address this, we propose a cascaded framework that transforms longitudinal planning from an independent prediction task into a path-conditioned reasoning process. On the model side, we introduce an anchor-based regression design that conditions longitudinal prediction on the lateral drive path, and reformulate longitudinal planning as 1D displacement prediction along the path. This reduces geometric uncertainty and sharpens the model's focus on interaction-driven dynamics. On the data side, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events by programmatically inserting agents and relabeling longitudinal targets to enforce collision avoidance. Evaluated on the challenging Bench2Drive benchmark, our method achieves SOTA performance with a driving score of 89.07 and a success rate of 73.18%, demonstrating significantly improved coordination and safety. Further evaluation on Fail2Drive confirms strong generalization to rare edge cases where parallel formulations typically fail. Project page:https://yanhaowu.github.io/AlignDrive/.
Authors: Anthony Chen, Naomi Ken Korem, Gal Zeevi, Tavi Halperin, Matan Ben Yosef, Urska Jelercic, Ofir Bibi, Or Patashnik, Daniel Cohen-Or
Abstract: Audio-Visual Foundation Models, which are pretrained to jointly generate sound and visual content, have recently shown an unprecedented ability to model multi-modal generation and editing, opening new opportunities for downstream tasks. Among these tasks, video dubbing could greatly benefit from such priors, yet most existing solutions still rely on complex, task-specific pipelines that struggle in real-world settings. In this work, we introduce a single-model approach that adapts a foundational audio-video diffusion model for video-to-video dubbing via a lightweight LoRA. The LoRA enables the model to condition on an input audio-video while jointly generating translated audio and synchronized facial motion. To train this LoRA, we leverage the generative model itself to synthesize paired multilingual videos of the same speaker. Specifically, we generate multilingual videos with language switches within a single clip, and then inpaint the face and audio in each half to match the language of the other half. By leveraging the rich generative prior of the audio-visual model, our approach preserves speaker identity and lip synchronization while remaining robust to complex motion and real-world dynamics. We demonstrate that our approach produces high-quality dubbed videos with improved visual fidelity, lip synchronization, and robustness compared to existing dubbing pipelines.
Authors: Qishuai Wen, Zhiyuan Huang, Xianghan Meng, Wei He, Chun-Guang Li
Abstract: The vanilla self-attention mechanism in Transformers can be viewed as a two-layer fast-weight MLP, whose weights are dynamically induced by inputs and whose hidden dimension is equal to the sequence length $N$. As the context extends, the expressive capacity of such an $N$-width MLP increases, but it becomes unscalable for extremely long sequences. Recently, this fast-weight perspective has motivated the Mixture-of-Experts (MoE) attention mechanism, which partitions the sequence into rigid blocks, treats them as fast-weight experts, and sparsely routes the tokens to them. In this paper, we elevate this perspective to a unifying framework for efficient attention mechanisms, interpreting them as making fast weights scalable through either routing or compression, and organizing them into a five-dimensional taxonomy. Then, we propose Mixture-of-Top-$k$ Attention (MiTA), which employs a small set of landmark queries to gather top-$k$ attended key-value pairs as query-aware and deformable routed experts, while compressing the $N$-width MLP into a narrower shared expert. Consequently, our MiTA improves the flexibility of prior MoE attention from rigid to deformable fast-weight experts, as well as the scalability of prior top-$k$ attention from query-specific set to reusable top-$k$ set. We conduct extensive experiments on vision tasks showing the superior effectiveness and efficiency of our MiTA, and also uncovering intriguing properties such as an emergent token-pruning effect and easy generalization from standard attention. Code is available at https://github.com/QishuaiWen/MiTA.
Authors: Huahua Lin, Katayoun Farrahi, Xiaohao Cai
Abstract: Understanding how neural representations respond to geometric transformations is essential for evaluating whether learned features preserve meaningful spatial structure. Existing approaches primarily assess robustness primarily by comparing model outputs under transformed inputs, offering limited insight into how geometric information is organized within internal representations and failing to distinguish between information loss and re-encoding. In this work, we introduce SEIS (Subspace-based Equivariance and Invariance Scores), a subspace metric for analyzing layer-wise feature representations under geometric transformations, disentangling equivariance from invariance without requiring labels or explicit knowledge of the transformation. Through controlled experiments across diverse architectures, we uncover several consistent patterns. First, convolutional encoders exhibit a depth-wise transition from strong equivariance to increasing invariance, with both properties stabilizing within the first few training epochs. In segmentation decoders, however, equivariance tends to recover in later layers. Second, this trade-off is not intrinsic but is shaped by training decisions: data augmentation actively strengthens both equivariance and invariance simultaneously, and multi-task learning induces synergistic gains in both properties beyond what either task achieves alone. Extending our analysis beyond convolutional networks, we find that transformer-based models exhibit distinct geometric behaviors, while MLP-Mixers display intermediate characteristics.
Authors: Boxiang Zhang, Baijian Yang
Abstract: Transformers achieve strong accuracy but incur high compute and memory cost. Structured pruning reduces inference cost, but most methods rely on retraining or multi-stage optimization, which limits post-training deployment. We propose CORP, a closed-form one-shot structured pruning method that removes MLP dimensions and attention substructures using only unlabeled calibration data without gradients or fine-tuning. CORP formulates structured pruning as a representation recovery problem. It models removed components as affine functions of retained components and derives closed-form ridge regression solutions that fold compensation into model weights. This minimizes a layer-local affine/logit reconstruction objective under the calibration distribution. Experiments on ImageNet with DeiT reveal strong redundancy in both MLP and attention representations. With CORP, models retain high accuracy under aggressive sparsity. On DeiT-Huge, CORP achieves 83.27% Top-1 accuracy after pruning 50\% of both MLP and attention structures.
Authors: Yining Hong, Huang Huang, Manling Li, Li Fei-Fei, Leonidas Guibas, Jiajun Wu, Yejin Choi
Abstract: Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials where mistakes repeat rather than accumulate into experience. Drawing upon human reflective practitioners, we introduce Reflective Test-Time Planning, which integrates two modes of reflection: \textit{reflection-in-action}, where the agent uses test-time scaling to generate and score multiple candidate actions using internal reflections before execution; and \textit{reflection-on-action}, which uses test-time training to update both its internal reflection model and its action policy based on external reflections after execution. We also include retrospective reflection, allowing the agent to re-evaluate earlier decisions and perform model updates with hindsight for proper long-horizon credit assignment. Experiments on our newly-designed Long-Horizon Household benchmark and MuJoCo Cupboard Fitting benchmark show significant gains over baseline models, with zero-shot generalization to photorealistic HM3D environments and real-robot experiments on a Franka Panda arm. Ablations confirm that reflection-in-action and reflection-on-action are mutually dependent, and that retrospective reflection achieves better credit assignment than step-wise external feedback at lower computational overhead. Qualitative analyses further highlight behavioral correction through reflection.
Authors: Ruobing Zheng, Tianqi Li, Jianing Li, Qingpei Guo, Yi Yuan, Jingdong Chen
Abstract: Reasoning post-training improves Large Language Models (LLMs) on complex tasks such as mathematics and coding, but its benefits across diverse multimodal tasks remains uncertain. The trend of releasing parallel "Instruct" and "Thinking" models by leading teams is both resource-intensive and user-unfriendly. Prior work finds that the gains from reasoning training are influenced by multiple factors, such as base model capabilities, task characteristics, and Chain-of-Thought (CoT) data quality. However, principled criteria for determining when reasoning post-training is beneficial and which data should support it are still lacking. In this paper, we propose Dual Tuning, a reasoning efficacy-driven data curation framework for multimodal LLMs training. Given a target task and a base model, Dual Tuning jointly evaluates whether the training data is beneficial and whether reasoning training with current CoT content yields positive gains over non-reasoning alternatives. We apply Dual Tuning across spatial, mathematical, and multi-disciplinary tasks, and further analyze how reinforcement learning and thinking patterns affect reasoning efficacy. The Dual Tuning results guide data curation by identifying data that benefit reasoning training, data better suited to direct-answer training, and data that are detrimental under both training modes. Our work provides quantitative criteria for selecting appropriate training data and matching post-training strategies.
Authors: Yu Gao, Jijun Wang, Zongzheng Zhang, Anqing Jiang, Yiru Wang, Yuwen Heng, Shuo Wang, Hao Sun, Zhangfeng Hu, Hao Zhao
Abstract: End-to-end (E2E) driving has become a cornerstone of both industry deployment and academic research, offering a single learnable pipeline that maps multi-sensor inputs to actions while avoiding hand-engineered modules. However, the reliability of such pipelines strongly depends on how well they handle uncertainty: sensors are noisy, semantics can be ambiguous, and interaction with other road users is inherently stochastic. Uncertainty also appears in multiple forms: classification vs. localization, and, crucially, in both static map elements and dynamic agents. Existing E2E approaches model only static-map uncertainty, leaving planning vulnerable to overconfident and unreliable inputs. We present UniUncer, the first lightweight, unified uncertainty framework that jointly estimates and uses uncertainty for both static and dynamic scene elements inside an E2E planner. Concretely: (1) we convert deterministic heads to probabilistic Laplace regressors that output per-vertex location and scale for vectorized static and dynamic entities; (2) we introduce an uncertainty-fusion module that encodes these parameters and injects them into object/map queries to form uncertainty-aware queries; and (3) we design an uncertainty-aware gate that adaptively modulates reliance on historical inputs (ego status or temporal perception queries) based on current uncertainty levels. The design adds minimal overhead and drops throughput by only $\sim$0.5 FPS while remaining plug-and-play for common E2E backbones. On nuScenes (open-loop), UniUncer reduces average L2 trajectory error by 7\%. On NavsimV2 (pseudo closed-loop), it improves overall EPDMS by 10.8\% and notable stage two gains in challenging, interaction-heavy scenes. Ablations confirm that dynamic-agent uncertainty and the uncertainty-aware gate are both necessary.
Authors: Yinjie Wang, Xuyang Chen, Xiaolong Jin, Mengdi Wang, Ling Yang
Abstract: Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each action, yet no existing agentic RL system recovers it as a live, online learning source. We present OpenClaw-RL, a framework that employs next-state signals to optimize personal agents online through infrastructure and methodology innovations. On the infrastructure side, we extend existing RL systems to a server-client architecture where the RL server hosts the policy behind an inference API and user terminals stream interaction data back over HTTP. From each observed next state, the system extracts two complementary training signals, evaluative and directive, via a separate asynchronous server so that neither signal extraction nor optimization blocks inference. On the methodology side, we introduce a hybrid RL objective that unifies both signal types in a single update: directive signals provide richer, token-level supervision but are sparser, while evaluative signals are more broadly available. To stabilize distillation under teacher-student mismatch, we propose overlap-guided hint selection, which picks the hint whose induced teacher distribution maximally overlaps with the student's top-$k$ tokens, together with a log-probability-difference clip that bounds per-token advantages. Applied to personal agents, OpenClaw-RL enables an agent to improve simply by being used, recovering conversational signals from user re-queries, corrections, and explicit feedback. Applied to general agents, OpenClaw-RL is the first RL framework to unify real-world agent settings spanning terminal, GUI, SWE, and tool-call environments, where we additionally demonstrate the utility of next-state signals in long-horizon settings.
Authors: Jiao Wang, Chi Liu, Yiying Zhang, Hongchen Luo, Zhifen Guo, Ying Hu, Ke Xu, Jing Zhou, Hongyan Xu, Ruiting Zhou, Man Tang
Abstract: We propose glaucoma lesion evaluation and analysis with multimodal imaging (GLEAM), the first publicly available tri-modal glaucoma dataset comprising scanning laser ophthalmoscopy fundus images, circumpapillary OCT images, and visual field pattern deviation maps, annotated with four disease stages, enabling effective exploitation of multimodal complementary information and facilitating accurate diagnosis and treatment across disease stages. To effectively integrate cross-modal information, we propose hierarchical attentive masked modeling (HAMM) for multimodal glaucoma classification. Our framework employs hierarchical attentive encoders and light decoders to focus cross-modal representation learning on the encoder.
Authors: Sebo Diaz, Polina Golland, Elfar Adalsteinsson, Neel Dey
Abstract: We present MaskGen, a theoretically grounded and deliberately simple approach for domain generalization in 3D biomedical image segmentation. Modern segmentation models degrade sharply under shifts in modality, disease severity, clinical sites, and more, limiting their reliable adoption. Existing generalization methods address this using extreme augmentations, hand-engineered domain statistics mixing, or architectural redesigns that add significant implementation overhead while yielding inconsistent performance across biomedical settings. MaskGen instead presents a principled learning strategy with marginal overhead that utilizes both source-domain image intensities and domain-stable foundation model representations to train robust segmentation models. As a result, MaskGen achieves strong gains in both fully supervised and few-shot segmentation across broad clinical shifts in biomedical studies. Unlike prior approaches, MaskGen is architecture- and loss-agnostic, compatible with standard augmentation pipelines, easy to implement, and tackles arbitrary anatomical regions. Its implementation is freely available at https://github.com/sebodiaz/MaskGen.
Authors: Indar Kumar, Girish Karhana, Sai Krishna Jasti, Ankit Hemant Lade
Abstract: Frozen pretrained image representations are widely used for transfer learning: a backbone is kept fixed, feature vectors are extracted, and a lightweight classifier is trained on top. This pipeline usually feeds the full feature vector to the classifier, even when the target task has far fewer classes than the pretraining task. We revisit a classical alternative: supervised dimensionality reduction with Linear Discriminant Analysis (LDA) before linear probing. We evaluate ten dimensionality-reduction strategies on frozen features from six backbones -- ResNet-18, ResNet-50, MobileNetV3-Small, EfficientNet-B0, ViT-B/16, and DINOv2-ViT-S/14 -- across CIFAR-100, Tiny ImageNet, and CUB-200-2011. Under a fixed logistic-regression protocol, LDA improves accuracy over full features in 11 of 12 coarse-grained configurations, with gains up to 4.5 percentage points while reducing feature dimensionality by 48-87%. The same projection consistently hurts on fine-grained CUB-200, where full features win across all six backbones. This establishes a practical boundary condition: LDA is useful when class-level structure is coarse enough to be captured by mean-separating directions, but it can discard subtle cues needed for fine-grained recognition. We also compare LDA with PCA, PCA+LDA, regularized LDA, Local Fisher Discriminant Analysis, Neighbourhood Components Analysis, and three lightweight LDA extensions. The results show that plain LDA offers the best accuracy-cost tradeoff for most coarse-grained settings, while more complex supervised reduction methods rarely justify their additional cost. Overall, the study provides concrete guidance for when post-hoc supervised projection should, and should not, be inserted into frozen-feature image classification pipelines.
Authors: Puja Saha, Eranga Ukwatta
Abstract: Large volumes of medical data remain underutilized because centralizing distributed data is often infeasible due to strict privacy regulations and institutional constraints. In addition, models trained in centralized settings frequently fail to generalize across clinical sites because of heterogeneity in imaging protocols and continuously evolving data distributions arising from differences in scanners, acquisition parameters, and patient populations. Federated learning offers a promising solution by enabling collaborative model training without sharing raw data. However, incorporating differential privacy into federated learning, while essential for privacy guarantees, often leads to degraded accuracy, unstable convergence, and reduced generalization. In this work, we propose an adaptive differentially private federated learning (ADP-FL) framework for medical image segmentation that dynamically adjusts privacy mechanisms to better balance the privacy-utility trade-off. The proposed approach stabilizes training, significantly improves Dice scores and segmentation boundary quality, and maintains rigorous privacy guarantees. We evaluated ADP-FL across diverse imaging modalities and segmentation tasks, including skin lesion segmentation in dermoscopic images, kidney tumor segmentation in 3D CT scans, and brain tumor segmentation in multi-parametric MRI. Compared with conventional federated learning and standard differentially private federated learning, ADP-FL consistently achieves higher accuracy, improved boundary delineation, faster convergence, and greater training stability, with performance approaching that of non-private federated learning under the same privacy budgets. These results demonstrate the practical viability of ADP-FL for high-performance, privacy-preserving medical image segmentation in real-world federated settings.
Authors: Alvin Kimbowa, Arjun Parmar, Ibrahim Mujtaba, Will Wei, Maziar Badii, Matthew Harkey, David Liu, Ilker Hacihaliloglu
Abstract: Objective: To develop a robust and compact deep learning model for automated knee cartilage segmentation on point-of-care ultrasound (POCUS) devices. Methods: We propose MonoUNet, a novel, highly compact segmentation model consisting of (i) an aggressively reduced U-Net backbone, (ii) a trainable monogenic block that extracts multi-scale local phase features from the input, and (iii) a gating mechanism that injects these features into the encoder stages to reduce sensitivity to variations in ultrasound image appearance. MonoUNet segmentation performance was evaluated on a multi-site, multi-device knee cartilage ultrasound dataset using Dice score and mean average surface distance (MASD). Agreement between MonoUNet and manual cartilage outcomes (thickness and echo intensity) was assessed using Bland-Altman analysis with 95% limits of agreement, and reliability was assessed using intraclass correlation coefficient (ICC$_{2,k}$). Results: Overall, MonoUNet outperformed existing lightweight segmentation models, with average Dice scores ranging from 92.62% to 94.82% and MASD values between 0.133 mm and 0.254 mm. MonoUNet reduces the number of parameters by 10x--700x and computational cost by 14x--2000x relative to existing lightweight models. MonoUNet cartilage outcomes showed excellent reliability and agreement with the manual outcomes: intraclass correlation coefficients (ICC$_{2,k})$=0.96 and bias=2.00% (0.047 mm) for average thickness, and ICC$_{2,k}$=0.99 and bias=0.80% (0.328 a.u.) for echo intensity. Conclusion: Incorporating trainable local phase features improves the robustness of highly compact neural networks for knee cartilage segmentation across varying acquisition settings and could support scalable ultrasound-based assessment and monitoring of knee osteoarthritis using POCUS devices. The code is publicly available at https://github.com/alvinkimbowa/monounet.
Authors: NVIDIA, :, Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki, Matthieu Le, Tyler Poon, Danial Mohseni Taheri, Ilia Karmanov, Guilin Liu, Jarno Seppanen, Arushi Goel, Mike Ranzinger, Greg Heinrich, Guo Chen, Lukas Voegtle, Philipp Fischer, Timo Roman, Karan Sapra, Collin McCarthy, Shaokun Zhang, Fuxiao Liu, Hanrong Ye, Yi Dong, Mingjie Liu, Yifan Peng, Piotr Zelasko, Zhehuai Chen, Nithin Rao Koluguri, Nune Tadevosyan, Lilit Grigoryan, Ehsan Hosseini Asl, Pritam Biswas, Leili Tavabi, Yuanhang Su, Zhiding Yu, Peter Jin, Alexandre Milesi, Netanel Haber, Yao Xu, Sarah Amiraslani, Nabin Mulepati, Eric Tramel, Jaehun Jung, Ximing Lu, Brandon Cui, Jin Xu, Zhiqi Li, Shihao Wang, Yuanguo Kuang, Shaokun Zhang, Huck Yang, Boyi Li, Hongxu Yin, Song Han, Bilal Kartal, Pavlo Molchanov, Adi Renduchintala, Charles Wang, David Mosallanezhad, Soumye Singhal, Luis Vega, Katherine Cheung, Sreyan Ghosh, Yian Zhang, Alexander Bukharin, Venkat Srinivasan, Johnny Greco, Andre Manoel, Maarten Van Segbroeck, Suseella Panguliri, Rohit Watve, Divyanshu Kakwani, Shubham Pachori, Jeffrey Glick, Radha Sri-Tharan, Aileen Zaman, Khanh Nguyen, Shi Chen, Jiaheng Fang, Qing Miao, Wenfei Zhou, Yu Wang, Zaid Pervaiz Bhat, Varun Praveen, Arihant Jain, Ramanathan Arunachalam, Tomasz Kornuta, Ashton Sharabiani, Amy Shen, Wei Huang, Yi-Fu Wu, Ali Roshan Ghias, Huiying Li, Brian Yu, Nima Tajbakhsh, Chen Cui, Wenwen Gao, Li Ding, Terry Kong, Manoj Kilaru, Anahita Bhiwandiwalla, Marek Wawrzos, Daniel Korzekwa, Pablo Ribalta, Grzegorz Chlebus, Besmira Nushi, Ewa Dobrowolska, Maciej Jakub Mikulski, Kunal Dhawan, Steve Huang, Jagadeesh Balam, Yongqiang Wang, Nikolay Karpov, Valentin Mendelev, George Zelenfroynd, Meline Mkrtchyan, Qing Miao, Omri Almog, Bhavesh Pawar, Rameshwar Shivbhakta, Sudeep Sabnis, Ashrton Sharabiani, Negar Habibi, Geethapriya Venkataramani, Pamela Peng, Prerit Rodney, Serge Panev, Richard Mazzarese, Nicky Liu, Michael Fukuyama, Andrii Skliar, Roger Waleffe, Duncan Riach, Yunheng Zou, Jian Hu, Hao Zhang, Binfeng Xu, Yuhao Yang, Zuhair Ahmed, Alexandre Milesi, Carlo del Mundo, Chad Voegele, Zhiyu Cheng, Nave Assaf, Andrii Skliar, Daniel Afrimi, Natan Bagrov, Ran Zilberstein, Ofri Masad, Eugene Khvedchenia, Natan Bagrov, Borys Tymchenko, Tomer Asida, Daniel Afrimi, Parth Mannan, Victor Cui, Michael Evans, Katherine Luna, Jie Lou, Pinky Xu, Guyue Huang, Negar Habibi, Michael Boone, Pradeep Thalasta, Adeola Adesoba, Dina Yared, Christopher Parisien, Leon Derczynski, Shaona Ghosh, Wes Feely, Micah Schaffer, Radha Sri-Tharan, Jeffrey Glick, Barnaby Simkin, George Zelenfroynd, Tomasz Grzegorzek, Rishabh Garg, Aastha Jhunjhunwala, Sergei Kolchenko, Farzan Memarian, Haran Kumar, Shiv Kumar, Isabel Hulseman, Anjali Shah, Kari Briski, Padmavathy Subramanian, Joey Conway, Udi Karpas, Jane Polak Scowcroft, Annie Surla, Shilpa Ammireddy, Ellie Evans, Jesse Oliver, Tom Balough, Chia-Chih Chen, Sandip Bhaskar, Alejandra Rico, Bardiya Sadeghi, Seph Mard, Katherine Cheung, Meredith Price, Laya Sleiman, Saori Kaji, Wesley Helmholz, Wendy Quan, Michael Lightstone, Jonathan Cohen, Jian Zhang, Oleksii Kuchaiev, Boris Ginsburg, Jan Kautz, Eileen Long, Mohammad Shoeybi, Mostofa Patwary, Oluwatobi Olabiyi, Andrew Tao, Bryan Catanzaro, Udi Karpas
Abstract: We introduce Nemotron 3 Nano Omni, the latest model in the Nemotron multimodal series and the first to natively support audio inputs alongside text, images, and video. Nemotron 3 Nano Omni delivers consistent accuracy improvements over its predecessor, Nemotron Nano V2 VL, across all modalities, enabled by advances in architecture, training data and recipes. In particular, Nemotron 3 delivers leading results in real-world document understanding, long audio-video comprehension, and agentic computer use. Built on the highly efficient Nemotron 3 Nano 30B-A3B backbone, Nemotron 3 Nano Omni further incorporates innovative multimodal token-reduction techniques to deliver substantially lower inference latency and higher throughput than other models of similar size. We are releasing model checkpoints in BF16, FP8, and FP4 formats, along with portions of the training data and codebase to facilitate further research and development.
Authors: Yan Zhang, Daiqing Wu, Huawen Shen, Can Ma, Yu Zhou
Abstract: Graphical User Interface (GUI) grounding maps natural language instructions to the visual coordinates of target elements and serves as a core capability for autonomous GUI agents. Recent reinforcement learning methods (e.g., GRPO) have achieved strong performance, but they rely on expensive multiple rollouts and suffer from sparse signals on hard samples. These limitations make on-policy self-distillation (OPSD), which provides dense token-level supervision from a single rollout, a promising alternative. However, its applicability to GUI grounding remains unexplored. In this paper, we present GUI-SD, the first OPSD framework tailored for GUI grounding. First, it constructs a visually enriched privileged context for the teacher using a target bounding box and a Gaussian soft mask, providing informative guidance without leaking exact coordinates. Second, it employs entropy-guided distillation, which adaptively weights tokens based on digit significance and teacher confidence, concentrating optimization on the most impactful and reliable positions. Extensive experiments on six representative GUI grounding benchmarks show that GUI-SD consistently outperforms GRPO-based methods and naive OPSD in both accuracy and training efficiency. Code and training data are available at https://zhangyan-ucas.github.io/GUI-SD/.
Authors: Yao Du, Shanshan Song, Xiaomeng Li
Abstract: Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (SFT) and point-wise regression rewards bias learning toward high-density regions, leading to regression-to-the-mean behavior and poor tail performance. We identify the lack of cross-sample relational supervision as a key limitation of existing MLLM training paradigms. To address it, we propose a distribution-aware reinforcement learning framework based on Group Relative Policy Optimization, which introduces batch-level comparison-based supervision via the Concordance Correlation Coefficient-based reward to align predicted and ground-truth distributions in terms of correlation, scale, and mean. The framework is plug-and-play, requiring no architectural modification. Experiments on a unified suite of long-tailed regression benchmarks show consistent improvements over SFT and existing MLLM regression methods, with particularly strong gains in medium- and few-shot regimes.