Authors: Haksoo Lim, Myeongjin Lee, Wonjoon Chang, Jaesik Choi
Abstract: Diffusion models have achieved remarkable success across diverse domains, with performance closely related to the denoising backbones that parameterize the score function. In this paper, we present a systematic, phase-aware analysis of diffusion components and show that abrupt, early-stage fluctuations in deep latents are strongly associated with artifacts. Guided by these findings, we introduce DUNE (Diffusion Unified Network refiNEr), a training-free refinement framework that detects abrupt deviations in deep low-noise internal latents using a shared EMA-based criterion, and applies backbone-specific suppression to the detector-selected entries. Although derived from U-Net, the same detect-suppress principle extends naturally to Transformer-based diffusion models by acting on the latents of deep self-attention blocks. Extensive experiments across multiple backbones indicate that DUNE improves fidelity while reducing hallucinations, offering new insight into where and when diffusion backbones should be controlled.
Authors: Mohammad Hosseini, Eray Erturk, Saba Hashemi, Maryam M. Shanechi
Abstract: Large-scale, multi-subject widefield calcium imaging provides unprecedented access to brain-wide cortical dynamics. However, the high dimensionality, complex spatiotemporal structure, and substantial task-irrelevant activity in widefield recordings have largely restricted modeling efforts to single-session analyses, limiting scalability and generalization. While multi-subject pretrained models have been explored for some neural modalities, multi-subject models for widefield calcium imaging have not yet been demonstrated; further, subject-invariant zero-shot behavior decoding remains elusive for multi-subject models across neural modalities more broadly. As a first step toward foundation modeling of widefield data, we introduce WiCAT, a multi-subject model that leverages self-supervised pretraining to both outperform single-session models and enable zero-shot behavior decoding on unseen subjects. WiCAT introduces an atlas-grounded tokenization scheme without session-specific components and learns globally shared spatiotemporal representations. Across multiple widefield datasets, the pretrained model supports lightweight downstream decoding, transfers across subjects, tasks, and datasets, and outperforms baseline models. Notably, the model also achieves robust zero-shot continuous behavior decoding and left-out brain region reconstruction on unseen subjects.
Authors: Jiaqi Liu, Haidong Kang, Qihui Zhao, Guo Yu
Abstract: Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT); however, the conventional practice of uniform rank assignment ignores the functional heterogeneity of neural layers. Existing rank allocation methods typically struggle with a trade-off between computational intensity and heuristic simplicity: training-based methods suffer from prohibitive overhead, while pre-allocation methods fail to capture the dynamic task-specific representation manifold. In this paper, we propose RSLoRA (Representational Sensitivity LoRA), a training-free and gradient-free rank allocator driven by activation-space geometry. We identify a "sensitivity regime shift" across layers, observing that static weight analysis and local gradients are insufficient to reflect how updates reshape a model's internal representations. To address this, RSLoRA introduces a virtual representational probing mechanism. By simulating adaptation through structured low-rank noise and measuring the resulting manifold displacement by using Effective Rank and Frechet Distance, we identify high-sensitivity modules that require higher rank capacity. Our framework effectively bridges the gap between expert-crafted heuristics and actual representational impact. Extensive evaluations demonstrate that RSLoRA consistently outperforms state-of-the-art allocators (e.g., AdaLoRA, GoRA) across mainstream benchmarks. By eliminating the need for iterative training-time adjustments and backward gradients, RSLoRA provides a highly efficient, robust, and representation-aware solution for large-scale model adaptation.
Authors: Xiaokang Ma, Yifan Sun, Zhihong Jin, Jie Gu, Yudong Luo, Shenyi Shao, Chu Tang, Jingmin Chen, Li Pu
Abstract: Building assistants that can continually watch the world, remember what they see, and reason over their accumulated experience is a long-standing goal, and recently multimodal agents equipped with long-term memory over video streams have attracted increasing interest. Unfortunately, existing systems either keep their memory inside the model context or in a flat feature store, and organize it around frames rather than around the persistent entities a stream is really about, which confines them to bounded videos and weakens their ability to track who and what reappears over time. In this paper, we propose ReflectWorld-MM, an entity-oriented multimodal memory system for open-ended video streams. It consists of three parts. The first is a perception front-end that turns an audiovisual stream into entity-resolved observations under a bounded short-term memory. The second is a hierarchical long-term memory, grounded in human memory theory, that couples a multi-scale episodic memory, an evolving entity-centric semantic memory, and a procedural memory. The third is a complete realization, built for real-world operation, that ingests arbitrary streams and plugs into off-the-shelf assistants. Across six long-video and lifelong-memory benchmarks, ReflectWorld-MM achieves the best accuracy on all six, outperforming strong memory agents and a frontier model.
Authors: Wenhao Fan, Yuanwei Bin, Jianghan Gu, Wenfa Luo, Jiao Xiang, Yuntian Chen, Shiyi Chen
Abstract: Engineering shape optimization faces challenges in both expert-dependent problem setup and surrogate-model reliability. In practical aerodynamic design, optimization settings such as editable regions, deformation ranges, and design-preservation constraints are typically specified manually by experienced engineers, while surrogate-based optimization may become unreliable for heterogeneous geometry databases and out-of-distribution designs. To address these challenges, we propose a knowledge-constrained shape-optimization framework that translates knowledge-based constraints and user intent into quantifiable parameters of DFFD-based deformation operators, enabling engineering-aware and controllable constrained optimization. We further develop a Mixture-of-Experts Neural Operator (MoE-NO) to improve drag prediction and trend consistency over heterogeneous aerodynamic datasets. Based on the MoE-NO encoder and Mahalanobis distance, an uncertainty-estimation strategy is introduced to detect out-of-distribution geometries and selectively trigger physics-solver feedback for local sample enrichment. Experiments on in-house MPV, SUV, and Sedan datasets show that MoE-NO achieves a test-set MAPE of $1.16\%$ and a trend-prediction accuracy of $94.34\%$, outperforming the best baseline results of $1.52\%$ and $90.34\%$, respectively. Vehicle shape-optimization experiments further yield CFD-validated drag coefficient reductions of approximately $4\%$ to $10\%$.
Authors: Lorenzo Lamberti, Manuele Rusci, Marco Fariselli, Francesco Paci, Luca Benini
Abstract: In this paper, we present the first (to the best of our knowledge) demonstration of a low-power MCU-based edge device for Automatic License Plate Recognition (ALPR). The design leverages on a 9-core RISC-V processor, GAP8, coupled with a QVGA ultra-low-power greyscale imager. The proposed visual processing pipeline uses a multi-model inference approach based on SSDlite-MobilenetV2 for license plate detection and LPRNet for optical character recognition, reaching a 38.9% mAP score for the first task and a recognition rate of >99.13% for the latter on public datasets. On real-world data, the pipeline recognizes registration numbers when the size of LP crops is as small as 30x5 pixels. Thanks to the applied compression and optimization strategies, the multi-model inference (687 MMAC) achieves a throughput of 1.09 FPS at a power cost of 117 mW when running on GAP8. Our solution is the first MCU-class device embedding such a level of network complexity, resulting to be 73x more energy-efficient w.r.t. precedent mobile-class ALPR system featuring a Raspberry Pi3. The proposed design does not resort to any hardwired acceleration engines, thus retaining full flexibility for future algorithmic improvements.
Authors: Pengyu Zhang, Klim Zaporojets, Congfeng Cao, Jia-Hong Huang, Paul Groth
Abstract: Multi-Modal Knowledge Graphs (MMKGs) enrich entities with multiple modalities such as text and images, yet entities with highly similar multi-modal features remain difficult to distinguish. Temporal information of an entity can serve as an additional modality to disambiguate such entities, but existing approaches rarely treat time as a separate modality alongside text and images due to two major challenges: (1) sparse temporal semantics, which hinder alignment with richer modalities, and (2) multiple timestamps, which introduce noise or reduce robustness in representation learning. To address these challenges, we propose Time Imprint, a framework that treats time as an entity-level modality and jointly aligns temporal, textual, and visual representations via a three-view contrastive objective. Additionally, to mitigate multi-timestamp ambiguity, Time Imprint studies a compact timestamp subset selection design space and aggregates the selected timestamps into a discriminative temporal embedding with attention pooling, balancing temporal specificity and robustness. Experiments on three MMKG benchmarks demonstrate that Time Imprint achieves state-of-the-art link prediction performance, improving Hits@1 by up to 6.07\% overall and yielding up to 58\% gains on the subset of the top-1\% ambiguity samples. We further examine different fusion strategies and the sensitivity to timestamp availability and quality, clarifying when and why time-as-modality is most beneficial, while adding only modest training overhead. We release our code at https://anonymous.4open.science/r/Time-Imprint.
Authors: Yunhong Zhang, Changjie Cao, Zhongli Zhou, Bingli Liu, Zongjie Cao, Zongyong Cui, Ying Yang
Abstract: The deep nonnegative matrix factorization (DNMF) technique is proposed to address the low interpretability of deep learning-based methods in extracting multilayer features from synthetic aperture radar (SAR) target samples. However, existing DNMF methods employ a layer-by-layer decomposition strategy, which is prone to causing error accumulation and local optimum, thereby hindering a consistent improvement in recognition accuracy as the number of layer increases. In this paper, a robust multilayer feature extraction method, termed generalized deep non-negative matrix factorization (G-DNMF), is proposed to address the above challenges in SAR automatic target recognition (ATR). The G-DNMF aims global optimality and derives the update rules for each parameter using lagrangian multiplier method. The new update formula indicates that both the DNMF method based on the encoding matrix and the mixing matrix are special cases of the proposed method, theoretically demonstrating the universality of proposed method. In general, the proposed method discards the layer-by-layer decomposition strategy, thereby effectively mitigating the risk of local optima and eliminating error accumulation, leading to a significant improvement in DNMF's multi-layer feature extraction capability. The experimental results, by presenting the feature images extracted from each layer by G-DNMF and the reconstructed original images, verified the proposed method's pure additive understanding of multi-layer features and demonstrated its interpretability. The experimental results based on MSTAR and OpenSARship datasets show that G-DNMF outperforms existing DNMF algorithms and their derivatives in terms of stability and recognition performance.
Authors: Andrea Boscolo Camiletto, Rishabh Dabral, Eduardo Alvarado, Thabo Beeler, Marc Habermann, Christian Theobalt
Abstract: The modern-day surge in popularity of wearable devices poses a fundamentally unique motion capture problem: reconstructing full-body movement from any set of sensing hardware worn at a given moment. Yet, most research efforts assume fixed sensor configurations (e.g. IMU suits or HMD-centric rigs) and cannot generalize across them. In contrast, we argue that motion capture should prioritize unobtrusive and lightweight devices such as smartphones, smartwatches, smart glasses, and smart insoles, and study the interplay between them. To this end, we make three contributions. First, we present a large-scale multi-modal dataset synchronizing these consumer-grade sensors with ground-truth 3D motion, spanning 50 diverse activities including everyday tasks, sports, and social interactions. Second, we propose WHIP, a baseline generative model that reconstructs motion from arbitrary subsets of available sensors, robustly handling missing modalities and producing physically plausible motions. Third, we conduct a systematic study of sensor complementarity, quantifying how different modalities complement one another. Code and dataset are available at https://vcai.mpi-inf.mpg.de/projects/WHIP/
Authors: Yongseong Park, Joeun Kim, HoEun Kim, Young-Sik Kim
Abstract: Real-image diffusion inversion is governed by a tight quality-cost trade-off, with costs incurred in computation, storage, or per-image optimization. We study this trade-off through the forward Gaussian noise anchor that defines a diffusion trajectory and isolate two mechanisms behind effective stored-noise inversion. First, diffusion noise exhibits an element-wise compression asymmetry: int8 full-dimensional anchors preserve reconstruction, whereas low-dimensional subspace summaries are much less reliable, often collapsing even at comparable or smaller payloads; the element-wise over subspace ordering persists across five stored-noise inversion methods. Second, inversion is trajectory-bound and score-prior coupled: the matched forward anchor and a trained score network are both necessary, arguing against a purely algebraic-identity explanation. Together, these findings specify what to store and how to use it. They lead to Noise-Anchored Reverse Correction (NARC), a training-free inversion primitive that stores a single int8 latent anchor and reuses it with a fixed, noise-level-dependent anchor-weight schedule: strong anchoring when the reverse trajectory is noise-dominated, then relaxed anchoring as image detail emerges. On PIE-Bench++ with Stable Diffusion 1.5, NARC outperforms five modern non-exact baselines and improves PSNR by +3.24 dB over PnP DirectInv while using about 400x less inversion storage than PnP DirectInv. The compression asymmetry, anchor specificity, and editing plug-in also transfer to SDXL 1024^2.
Authors: Sergi Masip, Alicja Dobrzeniecka, Jonathan Swinnen, Joachim Collin, Bart{\l}omiej Twardowski, Szymon {\L}ukasik, Tinne Tuytelaars
Abstract: Traditionally, continual learning has assumed access to labeled data, yet many real-world applications -- such as lifelong robotics -- require models to adapt continuously from unlabeled streams. This has led to the development of continual self-supervised learning (CSSL), a rapidly growing area that lacks a dedicated, systematic review. In this work, we present a comprehensive survey of CSSL for vision, with connections to emerging vision-language settings. First, we analyze existing evaluation protocols and highlight inconsistencies that hinder fair comparison. We then examine why self-supervised objectives exhibit improved robustness to catastrophic forgetting, relating this to task-agnostic representations and smoother loss landscapes. Next, we organize existing methods into a unified taxonomy based on their forgetting-mitigation strategies, including distillation, replay, regularization, architectural approaches, model merging, and objective-level adaptation. Finally, we identify open challenges such as scalability and the need for fast adaptability. We argue that advancing CSSL requires moving beyond small-scale benchmarks towards continual pre-training paradigms for large-scale systems.
Authors: Stavros Bouras, Antonios Makris, Alexandros Gkillas, Aris S. Lalos, Konstantinos Tserpes
Abstract: LiDAR semantic segmentation is a key perception task in autonomous driving, where false predictions can affect downstream planning and safety-critical decision-making. Although adversarial attacks, and specifically adversarial examples, have been widely studied for image classification and 3D point cloud segmentation, unrestricted adversarial examples remain largely unexplored in the space of 2D range images, which are projections of 3D point clouds. The proposed method is, to the best of our knowledge, the first diffusion-based unrestricted adversarial attack against 2D range-image segmentation, using adversarial guidance from a segmentation loss. By applying guidance directly during sampling, the method produces unrestricted adversarial examples that remain close to the learned LiDAR data manifold while inducing structured segmentation errors. Experiments on the SemanticKITTI dataset using RangeNet++ and CENet segmentation networks demonstrate that the attack provides adjustable degradation across guidance strengths and transfers across segmentation architectures. Compared with norm-bounded FGSM and SegPGD baselines, the proposed attack offers a distinct effectiveness-realism trade-off, achieving controllable white-box and transfer degradation while maintaining competitive distributional and visual realism.
Authors: Ni Yao, Zhenxu Wang, Danyang Sun, Chuang Han, Yanting Li, Jiaofen Nan, Fubao Zhu, Chen Zhao, Weihua Zhou
Abstract: Alzheimer's disease (AD) is a common neurodegenerative disorder, and early diagnosis is of great significance for delaying disease progression and enabling timely intervention. Mild cognitive impairment (MCI), which represents an intermediate clinical stage between cognitively normal aging and AD. Structural magnetic resonance imaging (sMRI) provides detailed characterization of anatomical structures and plays an important role in AD-related brain analysis. However, existing sMRI-based brain network methods typically rely on a single graph construction strategy, limiting their ability to jointly capture spatial relationships and morphological similarities between brain regions. To address these issues, this paper proposes an sMRI-based multi-view masked graph neural network model (MVMGNN) for AD diagnosis. A joint node-edge masking mechanism is proposed to simultaneously select radiomics feature dimensions and structural connections, reducing redundancy during graph learning. Furthermore, a patient-level cross-view gated fusion mechanism is proposed to integrate multi-view representations. Experimental results on the ADNI dataset demonstrate that MVMGNN outperforms several competing approaches in AD classification. Interpretability analysis further demonstrates that MVMGNN is able to identify key brain regions associated with AD, providing useful insights into discriminative patterns in sMRI-based brain networks.Our implementation is publicly available at https://github.com/chenzhao2023/MVMGNN_AD
Authors: Sarah Jobalia, Yitong Deng, Carolyn Smith, Ronald Fedkiw
Abstract: We present a framework for understanding and generating feature rich hair strands. Drawing upon both scientific and cultural expertise, we define strand texture as the various distinctive patterns (curling, switchbacks, twist, etc.) that are formed by forces internal to a hair strand. We begin by proposing a novel five-dimensional parameter space, intended to be a bijection with naturally occurring hair strand textures. This encoding is both qualitatively accessible, allowing users to readily locate their own hair in the parameter space, and quantitatively precise, allowing the generation of individual strands from texture inputs. Importantly, strand texture should be independent from the overall strand direction. In order to disentangle strand texture from the overall strand direction, we identify centerline geometry and use it to map strands into a canonical space (a strand texture space). We construct centerlines using a novel method that cleanly distills complex hair grooms, separating the strand texture from the overall style (parameterized by style guides). We enable the creation of new strands conforming to our parametric description of texture via a generative artificial intelligence approach supervised by a separate neural network trained to label candidate strands according to our five-parameter description. The ability to create new strands conforming to any desired texture enables groom editing using either texture transfer or user-provided inputs. We demonstrate results on a variety of hair types.
Authors: Xiaofan Wu (Chance AI), Xi Zeng (Chance AI), Miaoxia Chen (Chance AI), Peishan Chen (Chance AI), Shuyan Li (Chance AI), Jiyun Yao (Chance AI), Hanyong Zhong (Chance AI), Jiahao Zhu (Chance AI)
Abstract: Recognition tells an agent what is in an image; personal memory affects what is worth looking up next. In a camera-first setting the user can send only an image, so the agent must form the lookups. We study whether personal visual memory improves agent-side tool choice and tool arguments, and thereby more user-aligned multi-tool lookups. The design uses a three-layer personal visual memory (profile, short-term focus, observations) that is loaded on each turn to condition an LLM tool-calling loop under camera-first intake, and includes conflict-aware write-back intended to refresh the user model for later captures. On 800 images paired with synthetic memory blocks constructed for controlled ablation, removing the full three-layer memory block reduces tool-query relevance by 0.47 points absolute (4.21 -> 3.74 on a 5-point scale; 11.2% relative) and end-to-end utility by 0.082 absolute (0.842 -> 0.760; 9.7% relative). These results measure memory conditioning of tool policy under image-only intake with fixed synthetic blocks, not multi-session write-back from live user histories.
Authors: Lydia Ouhib (LIASD), Yassine Ouzar (LIASD), Zo\'e Pinseel (LIASD), St\'ephane Bouilland (LIASD), Mehdi Ammi (LIASD)
Abstract: Dysgraphia is a specific learning disability that is prevalent among school-age children. It affects handwriting coherence, quality, fluency, and legibility, often hindering academic achievement and early learning development. This motor coordination disorder is typically diagnosed through subjective assessments based on clinician observation, which can be timeconsuming and prone to variability. In this paper, we introduce a deep learning-based framework for objective dysgraphia detection using online handwriting data captured via digitizing tablets. The proposed framework relies on two complementary branches: the first pipeline extracts both handcrafted and embedding-based kinematic features directly from raw temporal signals, while the second leverages image-based representations of the temporal signals generated using continuous wavelet transforms (CWT) and Gramian Angular Fields (GAF). The resulting features are then fused to leverage the complementary strengths of both representations. The four representations were evaluated separately and jointly using the publicly available DiaGraMo dataset, showing that the fusion of GAF, MOMENT, and hand-crafted kinematic features outperforms each individual representation, as well as other fusion schemes. These findings highlight the potential of the complementarity of image and signal based representations for more objective dysgraphia detection.
Authors: Can Mizrakli, Tolga K. Capin
Abstract: Visual saliency aims to predict the regions of an image most likely to attract human visual attention. While most saliency models assume free-viewing conditions, human attention is often shaped by explicit task goals. In this work, we address task-driven saliency prediction by proposing a model that conditions visual attention on natural-language task descriptions. The model produces task-dependent saliency maps that reflect how attention shifts under different viewing intents. Through quantitative and qualitative analysis, we show that incorporating explicit task semantics enables more faithful modeling of goal-directed visual attention.
Authors: Rakesh Ranjan, Gajanan S. Kothawade, Kata Sharrer, Scott Tsukuda, Christopher Good
Abstract: The recently introduced YOLO26 architecture incorporates NMS-free end-to-end inference and is optimized for deployment on resource-constrained CPU-based devices, making it well-suited for edge-based aquaculture applications. However, its performance, operational efficiency, and deployment suitability have not been systematically validated in aquaculture-specific scenarios. This study presents a comprehensive benchmark of YOLO26 against three Ultralytics predecessors (YOLOv5u, YOLOv8, and YOLO11) across nano, small, and medium model scales for fish mortality detection, a critical indicator of fish population health and welfare. Twelve model variants were evaluated for detection accuracy, training efficiency across seven dataset sizes, and inference performance on high-performance NVIDIA A100 GPUs and a CPU-only Raspberry Pi 5 edge platform. All models achieved comparable performance on the full dataset, with mAP50 differing by only 1.04 percentage points, indicating that architectural generation has little influence on final detection accuracy when sufficient training data are available. However, clear trade-offs emerged in data efficiency and deployment performance. YOLOv8 achieved 90% mAP50 with only 400 training images, whereas the YOLO26 nano and small variants required 1,000 images to reach comparable accuracy. Conversely, YOLO26n achieved the highest inference speed on the Raspberry Pi 5 (7.51 FPS), while YOLOv5mu outperformed all contemporary medium-scale architectures on CPU-based hardware. These results show that architectural novelty alone is insufficient for model selection and that training data availability, target hardware, and inference requirements should be considered jointly when selecting object detection models for practical edge AI deployment in aquaculture.
Authors: Nisreen Albzour, Sarah S. Lam
Abstract: Cervical cytology classification models are typically evaluated on curated, class-balanced benchmarks, but real-world liquid-based cytology (LBC) collections are often small and class-imbalanced. This paper presents a class-imbalance-aware and calibration-aware ensemble classification study on the Mendeley LBC dataset, using its native four-class Bethesda taxonomy (NILM, LSIL, HSIL, SCC) rather than a collapsed binary formulation. Three lightweight architectures (Swin-Tiny, TinyViT-5M, DenseNet121) are trained directly on Mendeley LBC using weighted random sampling to counteract class imbalance, and compared against two soft-voting ensembles (Hybrid-2, Hybrid-3). Post-hoc temperature scaling is fit on a held-out calibration subset carved out of the training portion of each cross-validation fold, distinct from both the training data used to fit model weights and the evaluation fold used for final metrics, avoiding the optimistic calibration estimates that result when the same data is used for both purposes. Calibration substantially reduces expected calibration error, Brier score, and negative log-likelihood for every model and ensemble configuration tested, while discrimination metrics (accuracy, macro-F1, macro-AUROC) remain essentially unchanged. Ensemble size shows no consistent additional reliability benefit over the best individual model once all configurations are properly calibrated. Confusion matrices show that all classification errors, across every configuration, are confined to the boundary between high-grade lesions (HSIL) and carcinoma (SCC); no errors involve the negative (NILM) or low-grade (LSIL) categories. These results suggest that, for this dataset, calibration is the dominant lever for reliability, not ensemble size, though this conclusion should be read in light of the dataset's modest size.
Authors: Valentin Gabeff, Baptiste Maquignaz, Jennifer Shan, Sepideh Mamooler, Gencer Sumbul, Blair Costelloe, Devis Tuia, Alexander Mathis
Abstract: Automatically retrieving videos from large camera-trap datasets remains challenging. Text-to-Video retrieval (TVR) methods based on large video-language models (VLMs) have potential to retrieve events of interest by describing them with simple text queries. However, current methods often lack spatiotemporal understanding and do not generalize well to ecological data. In this work, we introduce Prompting-MammAlps, the first camera-trap TVR benchmark, and propose a fine-grained and interpretable TVR method. Specifically, we trained a vision transformer to perform spatiotemporal action localization, and convert its output to structured text, describing each video. Independently, ethology-inspired queries are processed by a Large-Language Model (LLM) based coding agent to parse the structured text per video and retrieve videos accordingly. We harnessed the LLM to use functions from a custom parsing library to minimize the risk of LLM hallucinations and to improve method interpretability. This retrieval approach applied on the Prompting-MammAlps benchmark achieved a set-based F1-score of 34\% on a test set of 135 ecologically-relevant queries and 775 candidate videos. In comparison the best zero-shot VLM achieved a F1-score of 18\%, while also lacking interpretability. Project page: https://cnai.epfl.ch/prompting-mammalps
Authors: Ismail Kably
Abstract: Ocular biometric systems face sophisticated presentation attacks, including high-resolution video replays and real-time generative deepfakes, which easily bypass static liveness checks. Current Presentation Attack Detection (PAD) frameworks typically rely on isolated physiological metrics, such as gaze tracking or the Pupillary Light Reflex (PLR), which can be spoofed independently. This paper proposes a Spatio-Luminance Sensor Fusion protocol, which introduces a dual-stream challenge-response framework for ocular liveness verification by uniting these metrics into a simultaneous authentication challenge. By generating a randomized, time-varying visual stimulus that fluctuates in both spatial trajectory and luminance intensity, we construct a mathematically coupled state-space likelihood model, termed the Synchronization Matrix, to evaluate the continuous cross-correlation between the expected biological latencies of smooth pursuit tracking and pupillary constriction. Using Monte Carlo simulation grounded in literature-derived latency distributions, we demonstrate theoretical separability between genuine and simulated attack conditions, and show that a multi-round challenge design improves the detection of generative deepfakes when a non-zero rendering-latency gap exists. This work provides a simulation-supported theoretical framework for next-generation dynamic spoofing defense in ocular and iris biometrics; human-subject validation is identified as necessary future work before deployment claims can be made.
Authors: Nusrat Binta Nizam, Fengbei Liu, Sunwoo Kwak, Minh Nguyen, Ruining Deng, Mert R. Sabuncu
Abstract: Multimodal medical models often degrade when inputs are missing, a common scenario in real-world clinical workflows. Separately, even when all modalities are present, modality dominance is observed during training, where optimization over-relies on a highly predictive modality and undertrains complementary sources, resulting in poor robustness under partial availability. While training-time modality knockout improves missing-modality robustness, existing approaches use static masking rates that cannot adapt to evolving modality utility during training. We introduce ShapKO (Shapley-Adaptive Modality Knockout), a dynamic training strategy that learns modality-specific knockout probabilities based on validation utility. ShapKO periodically evaluates performance across modality subsets, estimates modality importance via Shapley values, and updates masking probabilities to suppress dominant modalities more frequently. This adaptive process promotes complementary representations, while requiring no architectural modifications. We evaluate ShapKO on three datasets covering multitask clinical classification, survival prediction, and cancer detection. ShapKO consistently improves performance under modality absence and yields interpretable trajectories of learned masking behavior. Code is available at: https://github.com/sumona00/ShapKO
Authors: Anyi Zhang, Joy Mazumder, Kiril Lomakin
Abstract: Automated product recognition is a cornerstone of modern retail intelligence; however, accurately matching real-world, in-store images against extensive corporate catalogs remains a major scalability bottleneck for large-scale applications. In this work, we address this challenge by reformulating the task as an embedding-based cross-domain retrieval problem rather than a standard closed-set classification task. Specifically, we define the objective as retrieving the most corresponding catalog reference image for a given real-world product query crop from an expansive inventory. To bridge the severe domain gap between pristine studio packshots and noisy in-store queries, we introduce a novel catalog-to-real multi-stage contrastive learning paradigm (Cat2Real). This framework fine-tunes a vision backbone by systematically exploiting both item-level and image-level similarities to drive targeted hard negative mining. Extensive empirical evaluations demonstrate that our paradigm scales seamlessly to unseen products and categories, yielding outstanding zero-shot generalization performance even in the complete absence of real-world training images for novel inventory.
Authors: Lisi Wang, Zhidong Xiao, Jianjun Peng
Abstract: CorrNet is a strong baseline for continuous sign language recognition (CSLR) because it models inter-frame correlations inside the visual encoding stage. In this paper, we study two natural extensions of a reproduced CorrNet system: replacing the BiLSTM temporal head with a Transformer encoder, and injecting motion cues after temporal pooling. We find that the Transformer head does not outperform the BiLSTM baseline, even with a training strategy adjusted for the Transformer, and the two heads have almost the same computational and runtime cost. For the second extension, we design a lightweight module called MotionGate. In our experiments, MotionGate consistently collapses to an identity-like mapping: the gate loses motion selectivity, and the injected residual becomes a weak, non-selective perturbation of the pooled features. These results suggest that explicit motion injection after CorrNet's correlation-based encoding is largely redundant, and that natural-looking architectural extensions in CSLR should be tested carefully instead of being assumed to help.
Authors: Jiarui Li, Joseph Brewington, Qingzhao Zhang, Z. Morley Mao
Abstract: Gimbal-stabilized visual tracking is critical for modern autonomous systems such as Unmanned Aerial Vehicles (UAVs). While prior work shows acoustic signals can disturb gimbal internals, the impact of such attacks on real-world applications like UAV tracking and following remains underexplored. Existing demonstrations largely overlook practical challenges for real-world attacks, such as object-motion uncertainty and runtime latency. To bridge this gap, we present Banshee, the first physically realizable attack that induces target switching in UAV visual tracking systems by exploiting acoustic vulnerabilities in gimbal-camera systems. Banshee generates carefully crafted acoustic waveforms that induce optimized adversarial gimbal oscillations, causing directionally biased camera-view drifts that break inter-frame target associations. Consequently, the onboard tracker is driven to switch from the original target to an attacker-selected object with high probability, with occasional target loss. Banshee achieves a 93.6% success rate in simulation across two commercial gimbal systems and five trackers. Real-world benchtop and in-flight black-box attacks against a commercial drone across varied scenarios show an overall 95.5% attack success rate. Our results reveal a practical cross-domain vulnerability between acoustics and vision, highlighting the need for robust designs of gimbal systems and applications. Our code is available at: https://github.com/U1ltra/Banshee.
Authors: Yang You, Yi Du, Cole Harrison, Leonidas Guibas
Abstract: Object pose estimation is a fundamental problem in 3D vision. Although recent state-of-the-art approaches achieve strong performance, they often overfit to existing benchmarks and exhibit limited generalization to novel categories and unseen scenes. We propose UniPose9D, a category-agnostic foundation model for 9D object pose estimation: given an instance mask/ROI and either an RGB-D observation or an RGB image with predicted depth, the model estimates rotation, translation, and metric size without category labels, CAD models, mean-shape priors, or reference views. Specifically, UniPose9D samples point pairs from the observed object geometry and uses DINOv2 and PointNet features to predict NOCS coordinates for each pair. To improve accuracy, we introduce a point-pair-based RANSAC N-hop Kabsch--Umeyama algorithm with an adaptive threshold. We further employ flow matching to address symmetric ambiguities and construct a large-scale training set by curating and aligning pose annotations from existing public datasets. Experiments across six datasets show that a single unified model can match or surpass specialist methods while generalizing to unseen objects and in-the-wild scenarios. Our code and model are available on https://github.com/qq456cvb/UniPose9D.
Authors: Wenxi Gao, Guanxi Lu, Didi Zhu, Hao Mark Chen, Quan Deng, Zhican Wang, Jiankang Deng, Hongxiang Fan
Abstract: Unified multimodal models (UMMs) with interleaved reasoning, which generate both textual and visual steps as part of intermediate reasoning traces, have demonstrated great potential for visual mathematical reasoning tasks. However, we identify a key insight in this paradigm: generating intermediate visual reasoning steps is not always beneficial and can even be harmful, as self-generated visual steps may introduce erroneous visual evidence that misleads subsequent reasoning. Moreover, frequently triggering visual steps during reasoning incurs substantial computational and memory overhead, degrading inference efficiency. To address these accuracy and efficiency challenges, we observe that the model's internal signals can indicate whether a visual step will benefit reasoning before the entire visual generation is completed. Specifically, this work identifies two internal signals: 1) Generation Intent, which reflects whether the model has a concrete textual plan for what to draw, and 2) Visual Fidelity, which measures whether the visual generation remains grounded in the original input image. Leveraging these internal signals, we propose AdaViG, a training-free adaptive visual gating method for unified multimodal reasoning. AdaViG dynamically evaluates each triggered visual step at an early visual generation stage and aborts it when both signals are weak, thereby preventing misleading visual evidence from entering the reasoning trace while avoiding unnecessary computation. Comprehensive experiments demonstrate that AdaViG improves accuracy by up to 5.7% while reducing visual generation FLOPs by 25.0%-91.0% and wall-clock latency by 15.4%-45.6%.
Authors: Shunsuke Yokokawa, Hironori Kasahara
Abstract: Bird's-eye-view (BEV) perception is a core component of camera-based 3D understanding in autonomous driving, where view transformation (VT) maps multi-camera image features into a unified BEV representation. Sampling-based view transformation (Sampling-VT) is attractive because it supports dense and continuous BEV aggregation for high-resolution and long-range perception. Its deployment bottleneck, however, is systems-level: standard tensorized implementations of Sampling-VT -- which we refer to as Tensorized Sampling-VT -- explicitly materialize large height-dependent intermediate tensors, causing memory and latency costs that scale poorly with vertical resolution and the number of cameras. We revisit Tensorized Sampling-VT from an operator-execution perspective and show that it follows a gather-reduction pattern: each BEV query independently accumulates contributions across cameras and height bins, enabling thread-local accumulation with on-the-fly recomputation that eliminates the need to materialize height- and camera-dependent intermediates. Based on this insight, we propose FlashBEV, a fully fused and IO-aware execution strategy mathematically equivalent to Tensorized Sampling-VT (same operator output) while substantially reducing global memory traffic and kernel-launch overhead. Experiments show that FlashBEV achieves more than an order of magnitude lower peak GPU memory and significant inference-latency speedups, with memory effectively independent of the number of height bins, reducing the operator's peak memory to O(BCXY) (output only). This unlocks higher BEV range/resolution and vertical discretization within fixed deployment budgets on memory-constrained devices. Our contribution is an execution redesign -- same math, different execution -- that removes a key scalability barrier for deployment-ready Sampling-VT. Code available at https://github.com/yokosyun/FlashBEV
Authors: Zhonghua Yi, Hao Shi, Qi Jiang, Yufan Zhang, Kailun Yang, Kaiwei Wang
Abstract: Building pixel-level correspondence between event and image data is a fundamental task for multi-sensor systems. However, existing cross-modal matching methods are largely restricted by their reliance on either matching labels or strictly aligned hardware, which limits them to unlabeled and unconstrained real-world scenarios where neither matching ground truth nor prior sensor relationships are available. To address this, we propose a novel two-stage training paradigm. First, we leverage large-scale data to perform label-agnostic distillation pretraining, upgrading optimization objectives with distribution-based and contrastive losses to learn highly generalizable representations. Second, to tackle unlabeled and unconstrained downstream data, we introduce an epipolar-guided self-distillation framework. By utilizing consistency verification to isolate robust matches and incorporating geometric confidence derived from an external epipolar prior, our model can effectively self-evolve directly on target domains without any supervision. Furthermore, we introduce a rigorous cross-modal evaluation benchmark based on TUM-VIE, featuring physically separated cameras with distinct intrinsic parameters and resolutions. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on both MVSEC and TUM-VIE pose estimation tasks. The source code and benchmark will be made publicly available at https://github.com/ZhonghuaYi/nexus2-official.
Authors: Zhimin Yuan, Ming Cheng, Shangshu Yu, Wen Li, Dunqiang Liu, Xin Huang, Cheng Wang
Abstract: 3D unsupervised domain adaptive (UDA) segmentation mitigates the high cost of manual annotations of the new domain data. Self-training has emerged as the dominant approach in this area, where its success heavily depends on a well-initialized warm-up model to generate reliable pseudo labels. However, existing methods often depend on source supervision or output-level adversarial alignment to obtain the warm-up model, which suffer from limited generalization and training instability due to the large domain gap between domains. Constructing domain-similar representations is an effective way to bridge this gap. In this work, we propose CVKD-UDA, which revisits voxel size as a core design factor to construct domain-similar representations and leverages cross-view complementary cues to balance transferability and discriminability of the warm-up model. First, we generate two complementary views by varying voxel sizes and introduce a cross-view knowledge distillation (CVKD) to enhance generalization and target perception of the model. Second, to balance transferability and discriminability, we design a lightweight Decouple-Adapter and an auxiliary imitation classifier to decouple cross-view knowledge transfer. Extensive experiments on two benchmarks demonstrate that CVKD-UDA effectively improves the performance of self-training methods and provides a new perspective for 3D UDA segmentation. Our code will be available at GitHub.
Authors: Anwar Hussain Sofi, Jung-Hua Wang, Ming-Jer Chen, Tsung-Hsien Lee, Yu-Chiao Yi, Ming-Kuan Lin, Yi-Chung Lai
Abstract: Cleavage-stage embryo assessment in in vitro fertilization requires the integrated interpretation of cytoplasmic fragmentation, developmental stage, and blastomere symmetry. However, conventional visual assessment is affected by observer variability, particularly when fragmented regions are small, irregular, or low contrast. This study presents EMBRACE, a multi-task deep learning framework for jointly performing cytoplasmic-fragmentation segmentation, t2/t4 developmental-stage classification, and blastomere-symmetry grading from static cleavage-stage embryo microscopy images. EMBRACE combines a shared ResNet-50 backbone, a concatenation-based multi-scale feature-fusion (C-MSFF) module, a U-Net-style segmentation decoder, and two task-specific classification heads. After predefined inclusion and exclusion criteria, 9,137 annotated embryo images were divided into 7,309 training, 914 validation, and 914 held-out test images. On the held-out test set, EMBRACE achieved a Dice coefficient of 0.781 and an intersection over union of 0.677 for fragmentation segmentation. Developmental-stage classification achieved an accuracy of 0.995, macro-F1 of 0.994, and AUC of 1.000. Blastomere-symmetry grading achieved a balanced accuracy of 0.901, macro-F1 of 0.907, and quadratic weighted kappa of 0.859. These findings support the feasibility of combining spatially inspectable fragmentation localization with embryo-level morphology assessment in a single framework. External and prospective validation is required before clinical deployment.
Authors: Junho Kim, Salman S. Khan, Sara Wan, Tomi Kuye, Ashok Veeraraghavan
Abstract: Face recognition is a ubiquitously used computer vision task that has a wide range of applications ranging from everyday smartphone biometrics to high-stakes security systems. Most face recognition systems rely on traditional cameras, which often suffer from limitations such as bulky form factors, high costs, and limited privacy protection. To address these limitations, lensless cameras have emerged as an alternative. Lensless cameras use thin optical encoders, enabling smaller size, lower cost, and greater design flexibility. These cameras are typically paired with reconstruction algorithms that convert raw captures into recognizable images. However, reconstructed images often contain artifacts, and the reconstruction methods struggle to generalize well to real-world conditions. Furthermore, existing face datasets do not account for the artifacts present in lensless images. To address this issue, we introduce the Lensless Face Dataset (LFD). LFD comprises 21,080 lensless raw measurements, reconstructions, and standard images of faces captured under diverse lighting, angle, and distance. Our key contributions are: (1) Real-world lensless face data: LFD focuses on capturing a diverse face dataset with varying levels of artifacts introduced under different environments; (2) In-the-wild captures: 4,976 images are captured in outdoor settings with varying intensities of natural light and different background patterns; (3) Multiple lensless devices: LFD includes face images collected from three different types of lensless cameras, each with a unique optical encoder. We use this hardware diversity to demonstrate generalization across different lensless cameras. Through comprehensive evaluations and analysis, we show that LFD effectively captures shared features and artifacts across different lensless imaging devices, making it a valuable dataset for advancing lensless face recognition.
Authors: Ziyang Zhang, Jie Liu, Luca Mottola
Abstract: Modern satellite edge systems, including those performing remote sensing tasks such object detection and tracking, are characterized by severely limited bandwidth and intermittent connections, making continuous data transmission to the cloud impractical. Existing edge-cloud systems, however, either require heavy pre-processing before analysis, for instance, full decompression of imagery data, or transmit all compressed data regardless of relevance. To address these challenges, we design DynaFilter, a dynamic filtering technique that enables satellite edge devices to perform selective region-of-interest (RoI) inference directly in the compressed-domain, without full decompression. Our key insight is that low-level compression syntax, specifically DC coefficients/AC energy in JPEG images and motion vectors in video streams, exhibits strong correlations with high-level semantic queries. By establishing a precise mapping between cloud query semantics and multimodal compressed-domain features, DynaFilter enables the edge to identify and transmit only relevant data associated to RoIs. Extensive evaluations show that DynaFilter reduces the total volume of pixel data for decoding and subsequent inference by 1.6x-7.1x for images, and achieves 92.0% bandwidth savings for video streams compared to state-of-the-art baselines. Furthermore, it decreases energy consumption by 43.1-88.6% on target devices and achieves a 1.6x-3.0x speedup in inference latency.
Authors: Xianzhi Ma, Shujun Wang, Xiaohan Li, Hao Liu, Changhua Pei, Jianhui li
Abstract: Ultra-High-Resolution (UHR) remote sensing image understanding requires Vision-Language Models (VLMs) to capture both the global scene layout and sparse yet task-critical local details under limited computational budgets. Existing methods mainly follow two paradigms. One is passive perception, which relies on resolution expansion or token compression and may therefore discard fine-grained details. The other is active perception, which depends on multi-round zooming and search, but suffers from high latency, contextual fragmentation, and error accumulation. We argue that a more effective path toward UHR understanding lies not in accessing more, but in organizing better. To this end, we propose WeaveEarth, a training-free framework that reformulates UHR understanding as a problem of structured evidence construction and reasoning under global context constraints. Specifically, WeaveEarth first employs Global-Aware Evidence Construction to select a compact, low-redundancy, and spatially complementary Minimal Support Evidence Set. It then introduces Structured Evidence Reasoning, which weaves local evidence, spatial metadata, and relative topology into a unified reasoning interface, thereby enhancing the VLM's ability to perform global-local joint reasoning. Extensive experiments show that WeaveEarth consistently outperforms strong baselines and existing UHR methods across multiple UHR remote sensing benchmarks and multiple frozen VLM backbones. Code is available at https://github.com/XianZhi-Ma/WeaveEarth.
Authors: Junhui She, Fei Wang, Kun Li, Yiqi Nie, Yuxin Liu, Zhangling Duan, Xun Yang
Abstract: Gaze target estimation aims to infer the position of a person's gaze within a scene. Within mainstream design logic, multi-branch methods require extra supervision and annotations, while streamlined designs prioritize low-level visual saliency over true gaze intent. The former leads to a high annotation burden and hinders domain transfer, whereas the latter causes misalignment between predicted attention and actual gaze targets. To address this issue, we propose TextGaze, a unified cross-modal architecture that leverages a Large Vision-Language Model (LVLM) as scalable semantic guidance to balance the two design paradigms. The model extracts visual features from a frozen encoder and utilizes an LVLM to obtain gaze-aligned textual cues. We design a transformer-based fusion module with hierarchical text supervision to preserve task semantics. Lightweight decoding heads enable the joint prediction of gaze heatmaps and in-/out-of-frame status. We evaluate our method on four mainstream datasets, and the results show competitive performance across key metrics with robust cross-dataset generalisation without extra fine-tuning. Overall, we provide a streamlined alternative to traditional designs and highlight the potential of LVLMs as accessible auxiliary guidance for gaze estimation.
Authors: Yuang Meng, Chenyang Wu, Xianshun Liu, Chun-Le Guo, Zichen Liang, Lina Lei, Jie Liang, Hui Zeng, Chongyi Li, Lei Zhang
Abstract: Existing optical flow methods broadly follow two paradigms: iterative optimization and diffusion-based estimation. Iterative methods, exemplified by RAFT, achieve high accuracy through recurrent refinement, but remain challenged by large displacements and complex motion. Diffusion-based methods introduce generative modeling and show promise in such ambiguous regions. However, existing diffusion models usually denoise the entire dense flow field from Gaussian noise, including simple regions where reliable motion can already be estimated by a lightweight network. This increases the denoising burden and may cause slow convergence and unstable training. To address this issue, we introduce FlowPainter, a diffusion-based optical flow framework that reformulates dense-flow generation as confidence-guided soft inpainting. FlowPainter employs a lightweight confidence-aware network to predict a rough flow and a pixel-wise confidence mask, distinguishing reliable simple regions from uncertain hard regions. The resulting simple-flow prior is used for confidence-based initialization and further injected into iterative denoising through confidence-gated residual guidance. With dynamically decaying guidance strength, FlowPainter stabilizes early denoising while preserving the flexibility of the diffusion model for late-stage detail refinement. Extensive experiments on public benchmarks, including Sintel, KITTI, and Spring, show that FlowPainter achieves strong accuracy under comparable training settings and converges more efficiently than existing diffusion-based optical flow methods, with notable gains on challenging benchmark splits. Our approach offers a practical way to integrate reliable discriminative priors with diffusion-based refinement for optical flow estimation. Our code is publicly available at https://github.com/mya012/FlowPainter.
Authors: Li Guo, Anas M. Tahir, Z. Jane Wang
Abstract: Automated chest X-ray report generation has recently benefited from reinforcement learning (RL) and large language models. However, RL training often suffers from instability or limited exploration due to fixed Kullback-Leibler (KL) regularization and a static reference policy that accumulates KL pressure over time. We propose Response-Weighted and Validation-Anchored Policy Optimization (REVA-PO), a RL framework that stabilizes long-term training via Response-Weighted Regularization (RER) and Validation-Anchored Policy Reset (VAPR). RER dynamically adjusts per-response KL weights based on advantage and reference-policy entropy, relaxing constraints for high-quality responses while tightening them for low-quality ones. Complementarily, VAPR periodically synchronizes the reference and current policies to the best validation checkpoint, resetting accumulated regularization pressure to expand the viable exploration space. To ensure a robust starting point, we employ a three-stage pipeline consisting of warm-up training, classifier-guided supervised fine-tuning, and RL. Extensive evaluations on MIMIC-CXR and IU-Xray demonstrate that REVA-PO sets new state-of-the-art benchmarks in both linguistic quality and clinical accuracy. Notably, BLEU-4 improves by 5.1% on MIMIC-CXR and 3.6% on IU-Xray, while CheXpert F1 and RadGraph F1 scores increase by 4.5% and 12.8%, respectively, over prior leading methods. The code is publicly available at https://github.com/LiGuo12/REVA_PO/.
Authors: Dexiang Hong, Yijie Guo, Weidong Chen, Xinyan Liu, Zixuan Zou, Zhendong Mao, Yongdong Zhang
Abstract: Emotion-aware artistic image generation requires an image to match the input prompt, follow the specified artistic style, and convey the target emotion. In this challenge, the main difficulty is that the visual and affective attributes available in the training data are not explicitly provided at test time. Without these attributes, the generator has to decide not only what to depict, but also how the target emotion should be expressed through color, lighting, brushwork, composition, line, and layout. This creates a control gap between the available test prompt and the fine-grained conditions needed for emotion-aware artistic generation. To bridge this gap, we propose EmoStyle, a Z-Image-based framework that converts the input prompt into a structured generation state. An LLM reasoner first predicts affective cues (valence-arousal, dominant emotion, and therapeutic-effect labels) and an aspect-ratio decision. Instead of using these predictions only as additional prompt text, we encode the affective fields into an affective condition vector and inject it into the denoising blocks through AdaLN-style modulation. This allows the inferred control variables to directly guide the generation of intermediate features. Since emotional expression is also style-dependent, we further train a dedicated LoRA adapter for each artistic style bucket and select the corresponding expert during inference, enabling the same affective cues to be rendered with bucket-specific priors for color, texture, brushwork, and composition. Finally, a lightweight VLM-guided candidate selection step ranks the generated images based on prompt alignment, style consistency, emotional expression, and visual quality. In Track 1 of the AffectiveArt Challenge 2026, our USTC\_PI\_LAB\_TEAM submission achieved first place.
Authors: Abu Fatema Mohammad Abdun Noor, Md Imam Ahasan, Md Samiul Ahasan, Kah Ong Michael Goh, S M Hasan Mahmud, Raihana Zannat
Abstract: Breast cancer remains the most commonly diagnosed malignancy among women worldwide, yet accurate detection and characterization of breast masses in mammography remain challenging due to subtle intensity variations, heterogeneous tissue densities, and indistinct lesion boundaries that complicate radiological interpretation. To address these limitations, we propose BiLoG-Net, a deep learning framework that jointly performs breast mass segmentation and malignancy classification through bi-context location-aware feature modeling and segmentation-guided attention mechanisms. Our architecture integrates a novel encoder-decoder paradigm with Fire-based feature extraction, lightweight global and local feature enhancement modules, and adaptive location-aware gating to simultaneously capture long-range contextual dependencies and fine-grained boundary-sensitive details. Unlike conventional multi-stage pipelines, our tightly coupled multi-task design enables mutual reinforcement between pixel-level localization and image-level diagnosis, reducing error propagation while producing spatially grounded malignancy predictions. Evaluated on CBIS-DDSM and INBreast benchmarks, BiLoG-Net achieves state-of-the-art performance with Dice scores of 94.20% and 93.10%, classification accuracies of 95.20% and 93.60%, and AUC values of 97.10% and 96.00%, respectively, substantially outperforming existing CNN and transformer-based baselines. By combining precise boundary delineation with reliable malignancy assessment in a single end-to-end model, this work holds strong potential for clinical computer-aided detection systems, helping radiologists prioritize suspicious cases and improve screening efficiency in busy clinical settings.
Authors: Sachin Ranjan, Hoon Kim
Abstract: Surface scratch defects in semiconductor manufacturing pose significant challenges due to their irregular shapes, low contrast, and varying scales. Traditional inspection methods often struggle to detect such defects reliably, especially in complex imaging scenarios. While deep learning approaches based on Convolutional Neural Networks (CNNs) have improved accuracy, they often fail to capture fine-grained edge details. To address these limitations, we propose ScratNet, a novel end-to-end scratch segmentation framework that integrates a modified Swin Transformer backbone with a tailored decoder. The decoder incorporates a Multi-Scale Dilated Aggregation (MDA) module to capture both local and global context, a Stem Integration Module (SIM) to restore spatial detail, and a Precision Refinement (PR) branch that enhances boundary sharpness using anisotropic convolutions. Through this stage-adaptive feature aggregation and boundary-aware refinement, ScratNet achieves superior accuracy on thin and irregular defects. Extensive experiments demonstrate that ScratNet consistently outperforms existing methods, providing a scalable and robust solution for automated scratch inspection in high-precision manufacturing.
Authors: Taimur Khan
Abstract: Tree crowns are a challenging target for resilient AI because they are not static objects: their spectral response, internal texture, translucency, and apparent boundaries change substantially across the growing season. We develop PhenoEmbed, a self-supervised crown-centric temporal embedding model trained with contrastive and masked reconstruction objectives on HeideBench, an 18-date UAV multispectral time-series benchmark for forest crown phenology in D{\"o}lauer Heide. The model treats seasonal crown dynamics as phenological appearance change driven by leaf emergence, canopy closure, senescence, and leaf-off conditions. Segmented tree crown polygons are retained as object anchors to extract aligned crown-centered crops through time, allowing one 256-dimensional vector summarizing seasonal crown appearance to be learned per tree. On 5,885 crop-safe crowns, the exported embeddings show structured low-dimensional organization, with the first two principal components explaining 25.1\% of variance and nearest-neighbor retrieval producing a median top-1 cosine similarity of 0.946. Compared with handcrafted temporal features and a learned mean-pooling baseline, PhenoEmbed yields substantially more compact nearest-neighbor structure, while ablations show that the contrastive loss, masked reconstruction loss, and explicit seasonal time features each affect the structure of the learned embedding space. These results support PhenoEmbed as a reusable forest crown representation learner and motivate future downstream tests of whether such features improve tree-level models under seasonal change.
Authors: Yuang Jia, Jinlong Wang, Junhong Lin, Ruiting Dai, Wei Gao
Abstract: Open-vocabulary 3D scene understanding is commonly achieved by embedding 2D vision-language features such as CLIP into a 3D Gaussian Splatting scene, turning it into a text-queryable semantic field. However, attaching a high-dimensional feature to each of millions of Gaussians inflates a single scene to gigabytes, which makes storage and deployment the real bottleneck of these fields. Existing compact methods each learn and ship a per-scene codec, an autoencoder, a quantized codebook, or a distilled feature field, entangling field construction with field storage and never compressing the per-Gaussian assignment that holds the bulk of the cost. We argue that construction and storage should be decoupled, and that storage is a rate-distortion problem over the per-Gaussian binding to a small anchor table, a structure no prior open-vocabulary method compresses. We present CoSAG, which constructs the field without any per-scene training through a closed-form transmittance-weighted lift, spatially grounded semantic anchors, and multi-view denoising, and stores it with a spatially predictive entropy coder that ships no decoder. Because the anchors are spatially grounded, the binding is predictable and therefore highly compressible. The transmittance-weighted lift and multi-view denoising yield a clean, view-consistent assignment, so the entropy coder spends almost no rate on correcting noise and instead codes only the residual against its spatial prediction. CoSAG reaches sub-megabyte storage while matching or exceeding the state of the art across the 2D-rendered, 3D-selection, and dense-LSeg protocols, reducing field size by 37 to 76x relative to LangSplatV2 at higher accuracy.
Authors: Zhiyan Zhang, Peipei Song, Jinpeng Hu, Jingyang Jia, Xun Yang, Xiaojun Chang
Abstract: Video emotion analysis is typically framed as a static classification problem, treating each clip as an independent labeled unit. However, such a formulation overlooks a key psychological fact: emotions change as a result of cumulative reactions to consecutive causal events. To bridge this gap, we introduce Dynamic Affective Reasoning, the first large-scale benchmark for viewer-centric affect transitions and causal reasoning over consecutive video events. DAR contains 15,087 videos and 36,908 event-aligned affective segments annotated with 27 emotion categories. Unlike existing video-based emotion datasets, DAR presents a new viewer-centric perspective on fine-grained emotional expressions and transitions, and provides dense, temporally grounded, and causally explicit reasoning chains. Based on DAR, we formally define three challenging tasks: affective segmentation, fine-grained emotion classification, and affective reasoning. Complementing this benchmark, we propose DAR-R1, a two-stage framework that combines supervised fine-tuning with Group Relative Policy Optimization. Experiments across 10+ MLLMs show that DAR-R1 sets a new state-of-the-art for dynamic affective reasoning, in terms of both emotional localization and affective reasoning. Project page: https://github.com/Zhang-Zhiyan/DAR.
Authors: Guanhua Ye, Niu Jingbin, Yan Li, Meiyu Liang, Zhe Xue, Yingxia Shao, Yawen Li
Abstract: Short-answer VQA benchmarks conflate two distinct quantities: whether a model's answer is semantically correct, and whether that answer matches the surface form expected by the automatic evaluator. We study this conflation across six vision--language models and six benchmarks, using a human-validated semantic judge (97.6% precision) to audit over 37k official errors. A second text-only judge reproduces the same benchmark-level false-negative pattern, showing that the effect is not an artifact of a single audit model. On text-rich benchmarks, up to half of these errors are semantically acceptable answers penalized purely for surface-form mismatch. This instability is structured by answer type: extractive and multi-span answers are far more evaluator-sensitive than scalar answers. Benign prompt and context rewrites further destabilize official outcomes, flipping item-level correctness at substantial rates without changing the underlying task. A deterministic CPU-only contract repair confirms that the undercount is partially recoverable. These findings imply that official short-answer VQA scores should be accompanied by semantic audits and answer-type diagnostics to remain interpretable.
Authors: Yating Li, Cheng Ye, Nenan Lyu, Weidong Chen, Zhendong Mao
Abstract: Accurate cervical cytology image classification is a key component of automated cervical cancer screening, where reliable recognition of normal, precancerous, and cancer-associated cellular patterns from Pap smear images can improve screening efficiency and diagnostic consistency. However, this task remains challenging because cervical cells exhibit complex morphology, subtle intra-class variations, and strong inter-class similarities. Existing convolution-based models capture local texture well but have limited ability to model long-range relationships, whereas attention-based models provide broader context but often lack explicit structural guidance. To address these limitations, we propose a geometry-aware classification framework for cervical cancer screening-oriented cytology image analysis, incorporating semantic abstraction and structural priors learned from pre-trained vision-language features. The method uses Gaussian expert modules to generate axis-wise priors from global semantic information, capturing structural regularities such as nuclear alignment and cellular spatial organization. These priors are embedded into an axial self-attention module to modulate similarity computation along horizontal and vertical directions, improving long-range dependency modeling and structure-sensitive feature interaction. Experiments on the Mendeley liquid-based cytology and SIPaKMeD datasets show that the proposed method achieves 99.48% accuracy on the former and 96.08% on the latter, with balanced gains in recall, precision, and overall classification performance. Visual analysis further shows that the learned priors highlight diagnostically relevant cellular regions, demonstrating the potential of the proposed framework as a screening-oriented decision-support tool for cervical cytology.
Authors: Yichen Peng, Jyun-Ting Song, Chen-Chieh Liao, Kris Kitani, Hideki Koike, Erwin Wu
Abstract: Human-pet interaction estimation and generation remain underexplored due to the absence of a high-quality large-scale dataset. We present InterPet4D, the first multimodal dataset capturing natural interactions between humans and dogs. Using a synchronized multi-view capture system, we record human-dog obedience tasks and provide annotations for both humans and dogs, including multi-view and egocentric videos, segmentations, 2D and 3D keypoints, meshes, and audio tracks. InterPet4D consists of 6.8 million frames collected from 13 dogs of 11 breeds interacting with 23 human participants. We further introduce the InterPetMoGen framework for human-pet interaction motion generation. Our proposed model achieves an FID score of 11.21 and substantially outperforms the Seq2Seq and DiT baselines, demonstrating the effectiveness of InterPet4D for modeling realistic human-pet interactions.
Authors: Chenglizhao Chen, Tianxiang Nan, Wen Li, Xinyu Liu, Guisheng Zhang, Mengke Song, Xiaomin Yu
Abstract: Weakly supervised video anomaly detection relies solely on video-level labels for training, making it difficult to accurately localize anomalous events in complex scenes. In real-world videos, anomalous behaviors exhibit large variations in appearance and temporal duration, while scene appearance and action dynamics are often tightly entangled. Consequently, existing models tend to rely on scene-related statistical cues rather than true behavioral deviations, resulting in unstable detection performance. To address this challenge, we propose a Structured Evidence Selection framework (SESAD) that reformulates anomaly detection as a structured reasoning process over clip-level visual evidence. Instead of directly mapping aggregated features to anomaly scores, SESAD reorganizes clip representations into semantically structured candidate evidence and performs context-conditioned selection under scene and action constraints. This mechanism adaptively emphasizes anomaly-relevant semantics while suppressing scene interference, thereby alleviating semantic entanglement under weak supervision. Furthermore, we introduce a lightweight geometric discrimination module that constructs a dual-prototype structure in the embedding space, enabling anomaly decisions through relative geometric relations. Extensive experiments on UBnormal, ShanghaiTech, and UCF-Crime show that SESAD achieves 67.92, 97.99, and 88.46 AUC, respectively, while maintaining high computational efficiency and overall consistently stable anomaly discrimination.
Authors: Jiakang Yu, Yixuan Chai, Tianci Wang, Rihui Jin, Guangkai Xu, Hongtao Deng, Xun Zhu, Wang Gao, Xinrun Guo, Haipang Wu
Abstract: Generative image editing models struggle with structured statistical charts when data modifications require geometric synchronization. We formalize this task as Visuo-Logical Cascading Editing (VLCE). However, existing methods remain confined to localized text substitutions and struggle with dependency-aware cascading updates. To systematically evaluate this capability, we introduce ChartSync, an expert-validated benchmark constructed via a programmatic rendering pipeline that guarantees deterministic visuo-logical coupling for the ground truth. ChartSync comprises 870 triplets across 9 chart categories and 4 task types, including 235 geometry-coupled VLCE instances that specifically test cascading text-to-geometry synchronization. We further evaluate these instances via a two-tier framework combining objective visual metrics with a vision-language model judge paradigm to assess low-level fidelity alongside multimodal comprehension and reasoning. Evaluating 14 image editing models and one code-mediated pipeline reveals a nuanced capability gap: most open-source models suffer severe drops in geometric synchronization, while only two frontier proprietary models show emerging VLCE capability, with their residual errors mainly involving semantic isolation and background corruption. Our detailed error analysis deconstructs these failure paradigms to identify core meta-abilities for guiding future multimodal architectures. The ChartSync dataset and code are publicly released at https://github.com/kaka-yjk/ChartSyncCodebase.
Authors: Shihao Yuan, Yuanze Li, Ruyi Zhang, Ming Liu, Wangmeng Zuo
Abstract: Despite the advancements of Large Multimodal Models (LMMs) in RGB vision, their ability to generalize to unseen visual modalities remains a largely unexplored challenge. We argue that different visual modalities are merely distinct samplings of the same physical world. Therefore, effective generalization requires models to possess both modality-agnostic perception of scene semantics and the adaptability to modality-specific characteristics. To achieve this, we propose a training framework, VVM-Tuning, to equip LMMs with these capabilities through modality synthesis and modality contexts. Specifically, we synthesize diverse appearance-varied images from RGB scenes, training the model to disentangle invariant semantics from varying visual appearances, and align these appearances with language for visual concepts decoupled from modalities. We then introduce modality contexts in the prompt and use instruction tuning to assist the model in mapping these appearance variations back to modality-related attributes, enabling zero-shot adaptation to unseen modalities during inference. To facilitate research in this direction, we introduce VVM-Bench, a comprehensive benchmark featuring 6 real and synthetic modalities to evaluate semantic perception and modality understanding. Experiments demonstrate that, via our training on synthetic modalities, 5 tested models exhibit consistent improvements on both real-world and novel synthetic modalities without in-modality training. Source code and data will be publicly available at https://github.com/Hunter-Will/VVM-Tuning.
Authors: Qi Lu, Ziqi Zhou, Yufei Song, Zijing Li, Lulu Xue, Minghui Li, Shengshan Hu, Leo Yu Zhang
Abstract: Vision Language Models (VLMs) offer powerful multimodal ability but also expose users to text-based privacy attacks where adversaries crawl online photos and query VLMs to extract sensitive attributes. Existing reversible adversarial example (RAE) methods protect images in purely visual tasks but fail in multimodal settings, and current adversarial examples on VLMs rely on high frequency noise that severely degrades visual quality. We propose CloakDiff, the first framework for reversible, high fidelity privacy protection against text-based query attacks in VLMs. CloakDiff produces imperceptible adversarial examples by combining diffusion based adversarial editing with an invertible network that embeds the original image for lossless recovery. It perturbs both pixel space embeddings and manipulates latent cross attention maps to ensure strong cross-model and cross-prompt transferability while preserving global visual structure. To further enhance fidelity, we design EDM Heuristic Sampling, a principled diffusion schedule for adversarial guidance. Experiments on multiple datasets and VLMs demonstrate that CloakDiff delivers multimodal privacy preservation with high visual quality and reversibility.
Authors: Yash Shah, Omar Todd, Philipp Seeb\"ock, Georg Langs, Ben Glocker, Raghav Mehta
Abstract: The automatic detection and classification of cardiovascular disease (CVD) from computed tomography (CT) images plays an important role in clinical practice. Recently, a hybrid pipeline (GRC-Net) for CVD classification was proposed, which leverages a deep-learning-based segmentation and registration method to extract radiomic and geometric features. However, GRC-Net relies on a deterministic segmentation mask, without considering the inherent ambiguity associated with cardiac anatomy. In this paper, we propose GRC-ProbNet, which takes advantage of a deep ensemble to produce multiple segmentation masks for a given input. From these masks, we extract multiple uncertainty features. We analyze these uncertainty features for both their correlation with segmentation error and their propagation effects on downstream CVD classification performance. Our experiments on the publicly available MM-WHS and ASOCA datasets show that the uncertainty measure that best reflects segmentation quality is not necessarily the one that provides the strongest signal for downstream CVD classification. Overall, our results demonstrate that GRC-ProbNet utilizing uncertainty features substantially improves CVD classification AUROC (92.92\) compared to the baseline GRC-Net model (91.25%). Our code is publicly available: https://github.com/biomedia-mira/GRC-ProbNet.
Authors: Giang Nguyen, Raghav Mehta, Emma A. M. Stanley, Tian Xia, Thi Hao Nguyen, Hieu Pham, Ben Glocker
Abstract: Foundation models are increasingly used as image feature extractors for mammography, but their robustness under external domain shift remains unclear. We benchmark 15 foundation-model backbones across breast density, BI-RADS severity, and cancer status using a unified frozen-backbone linear-probe protocol, training on 3 source datasets and evaluating on 12 task-compatible out-of-distribution (OOD) datasets after label harmonization. Mammography-specific vision-language models (Mammo-FM and MaMA) provide the strongest mean OOD performance, but robustness is not explained by mammography exposure alone. DINOv3 remains a competitive vision-only baseline, and mammography-adapted pretraining does not consistently improve generalization. Dataset-level analysis further shows that even leading models show heterogeneous performance across datasets. Feature-space inspection reveals that useful representations can preserve clinical signal while retaining dataset and acquisition structure. These findings highlight dataset-level OOD evaluation as a central criterion for assessing mammography representations. Our code is publicly available: https://github.com/biomedia-mira/mammo-ood.
Authors: Christopher Buratti, Michele Marchetti, Federica Parlapiano, Davide Traini, Domenico Ursino, Luca Virgili
Abstract: Vision Transformers (ViTs) are difficult to interpret because current methods of relevance propagation and attention flow do not fully consider some key architectural features, such as the uneven importance of attention heads and residual connections. Prior approaches typically assume uniform importance across attention heads; furthermore, they model skip connections as identity paths, leading to inaccurate relevance attribution. To address these issues, we introduce GradSkip, a novel relevance propagation method for ViTs based on adaptive head weighting and skip-aware propagation. GradSkip models the different importance of the attention heads and dynamically distributes relevance between the attention and residual paths. Experiments on ImageNet1K and BloodMNIST demonstrate a state-of-the-art faithfulness of GradSkip while requiring over 14 times fewer GFLOPs than the best-performing existing approaches. Additional evaluations using transformer-based segmentation confirm improved localization and alignment with ground-truth regions.
Authors: Luca Cazzola, Giulia Martinelli, Nicola Conci
Abstract: Motion blending in character animation enables the synthesis of new motions by interpolating between existing examples. Current methods are typically restricted to fixed skeleton topologies, requiring identical or near-identical skeletal structures across characters. We present a novel framework for motion blending across heterogeneous skeletons. The proposed architecture combines a semantic encoder, which extracts per-frame latent representations of the motion state, with a diffusion-based decoder, which reconstructs character-specific motion conditioned on this latent code. At inference, blended motions are obtained by interpolating the latent representations of two input motions. We train and evaluate the method on the Truebones Zoo dataset using motions defined on both same and distinct skeleton topologies, demonstrating the ability to achieve smooth and plausible blending in a variety of scenarios.
Authors: Ruiyan Gong, Yingnan Guo, Junjun Hu, Jintao Kong, Xiaoxu Leng, Tianlun Li, Weize Li, Fei Liu, Zhicheng Liu, Jia Lu, Minghua Luo, Chenlin Ming, Yanfen Shen, Jiyue Tao, Zhengbo Wang, Mingyang Yin, Minqi Gu, Zihao Guan, Wei Guo, Guoqing Liu, Huachong Pang, Menglin Yang, Zeqian Ye, Xiaoxiao Geng, Zhining Gu, Honglin Han, Di Jing, Hongyu Pan, Mingchao Sun, Kuan Yang, Jianfang Zhang, Yanghong Chen, Ye He, Wei Mei, Jiahao Shi, Xiangpo Yang, Yanqing Zhu, Yang Cai, Jingjing Ma, Shihui Su, Zixiao Tang, Linbo Zheng, Zedong Chu, Xiaolong Wu, Ziqiao Li, Mu Xu
Abstract: Visual Language Navigation foundation models aim to unify deep reasoning for grounded spatial decisions with broad versatility for diverse embodied tasks. Current approaches typically achieve this integration via monolithic policies that map observations directly to actions, yet they often suffer from coordinate drift and poor handling of long-tail semantics. Furthermore, these black-box mappings lack interpretability, hindering the simultaneous achievement of generality, robustness, and transparency. We present ABot-N1, a step toward a general Visual Language Navigation foundation model, that addresses these challenges by decoupling cognition from control via a slow-fast architecture guided by dual visual-language signals. More specifically, a slow vision-language reasoner performs explicit Chain-of-Thought reasoning while producing a pixel goal. This compact set of image-space anchor points serves as a universal interface for diverse tasks, including point-goal, object-goal, poi-goal, instruction-following, and person-following. Subsequently, a fast action expert leverages both the textual cues and the pixel guidance to generate continuous waypoints at the native control frequency. By bridging high-level intents and low-level control through pixel-grounded anchors paired with explicit linguistic traces, our approach ensures robust, generalizable, and interpretable navigation across simulation and real-world benchmarks. ABot-N1 establishes new state-of-the-art records, delivering massive gains specifically in urban-scale navigation: boosting POI arrival by 35.0% (to 77.3%) and achieving 95.4%/92.9% SR in complex indoor and outdoor scenes. It also maintains superior robustness across object-reaching, person-following, and instruction-following tasks. New Point-Goal/POI-Goal benchmarks are released as open source to advance the field of urban-scale navigation.
Authors: Francesco Di Salvo, Shyam Nandan Rai, Hamed Damirchi, Ignacio Meza De la Jara, Sebastian Doerrich, Marco Lents, Christian Ledig
Abstract: Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is considered for downstream tasks. We challenge this convention by introducing the notion of recoverability: the capacity of intermediate representations to correct last-layer failures. By evaluating independent classification probes at every model depth across 16 datasets, we observe that intermediate probes correctly classify 18% to 76% of samples that the last-layer probe misclassifies. We show that these gains are not primarily driven by predictive diversity, but by a redundancy-correctness correspondence, where the internal hierarchy acts as a series of stable, redundant probes of a shared discriminative signal. While established horizontal ensemble strategies (i.e., across multiple models) can improve performance, they incur high computational cost and ignore this vertical signal within a single model. To bridge this gap, we propose VFusion, a principled vertical aggregation strategy employing a learnable mapping into a low-dimensional latent space that synthesizes features across the internal ViT hierarchy. VFusion substantially outperforms established aggregation baselines in both in-distribution and out-of-distribution settings, notably closing 45% of the accuracy gap between the best individual layer and a theoretical oracle performance. Our gains consistently generalize across model sizes and pre-training regimes, confirming that VFusion offers a robust and efficient alternative to horizontal ensemble methods. The code is available at https://github.com/francescodisalvo05/vit-vertical-fusion.
URLs: https://github.com/francescodisalvo05/vit-vertical-fusion.
Authors: Xiaonan Hu, Zhiyuan Lu, Jingdong Zhao, Hao Lu
Abstract: High-quality alpha mattes are notoriously expensive to annotate, creating a fundamental data bottleneck for deep image matting. While prior work attempts to reduce annotation cost using coarser labels like trimaps or masks, they remain reliant on costly per-pixel supervision, limiting scalability and generalization. In this work, we push the boundary further and ask: can we train an automatic matting model using only RGB images, with no manual annotation at all? We answer this by presenting SSMatte, a self-supervised framework that for the first time achieves performance on par with fully-supervised automatic matting. Our key insight is to decompose the problem into semantic anchoring and detail matting. SSMatte first generates a semantic matting prompt from frozen self-supervised ViT features by propagating class-token seeds via a novel, training-efficient semantic anchoring loss based on a generalized Rayleigh quotient. This prompt then anchors a detail matting network, which is optimized via a fixed-point-based loss that enforces alpha-RGB consistency. Extensive experiments show SSMatte outperforms prior weakly-supervised methods, matches the performance of fully-supervised models on portrait benchmarks, and demonstrates favorable scaling and generalization behaviors with additional data. Our work pushes automatic matting to an fresh, fully annotation-free paradigm. Code will be available.
Authors: Abhigya Verma, Khyati Mahajan, Amit Kumar Saha, Shruthan Radhakrishna, Sagar Davasam, Vikas Yadav, Sai Rajeswar Mudumba
Abstract: Vision language models (VLMs) have achieved strong performance on visual document understanding benchmarks such as DocVQA, ChartQA, and MMLongBench-Doc. However, real-world documents combine multiple factors such as length, layout complexity, modality, and question difficulty, which makes it difficult to attribute model failures to specific causes. We introduce SynthDocBench, a fully synthetic benchmark for long-context visual document understanding that systematically controls factors including document length, layout structure, modality composition, and question type. The benchmark is constructed using a combinatorial design, each factor is varied independently across generated documents, enabling controlled analysis of model behavior. Documents are generated end to end using an LLM pipeline across six layout archetypes, with a 40 percent random override to prevent models from exploiting spurious correlations. Additionally, SynthDocBench spans long-context documents with substantially greater length and structural diversity than existing benchmarks. Evaluating seven frontier VLMs, we uncover three failure modes that existing benchmarks cannot surface: sharp degradation with document length, a systematic positional sensitivity in which the middle third of a document is hardest for five of six models and five of six models show a negative Early-to-Late trend (steepest decline: 8.3 percentage points), and breakdown of chart comprehension in long-document settings. These results suggest that current models may be overfitting to benchmark artifacts rather than achieving robust long-context visual document understanding.
Authors: Ramesh Naidu Laveti, Jaya Sreevalsan-Nair, T K Srikanth
Abstract: Self-supervised learning (SSL) has emerged as an effective paradigm for learning transferable representations from large-scale unlabeled whole slide images (WSIs). However, existing SSL methods primarily learn generic visual features and often fail to explicitly capture pathology-specific morphological patterns that are critical for disease characterization. To address this limitation, we propose Tiny Vision Transformer with Pathology-Aware Prototype Distillation (TVT-PAPD). This self-supervised pathology representation learning framework integrates a Tiny Vision Transformer (TVT) with a novel Pathology-Aware Prototype Distillation (PAPD) module. PAPD employs a learnable pathology prototype bank to discover and preserve representative tissue morphology patterns, encouraging semantically similar pathological regions to learn consistent and discriminative representations. The proposed framework enhances pathology-aware feature learning while maintaining computational efficiency with 90M parameters. Experiments on the Cancer Genome Atlas (TCGA) low-grade glioma (LGG)/glioblastoma (GBM) dataset and the Indian Pathology Brain (IPD-Brain) dataset demonstrate that TVT-PAPD achieves weighted F1-scores of 93.02% and 90.23%, respectively, for LGG-GBM classification, while exhibiting strong cross-cohort generalization across independent glioma datasets.
Authors: Gonzalo G\'omez-Nogales, Marc Comino-Trinidad, Andr\'es Casado-Elvira, Dan Casas
Abstract: Creating realistic 3D human-human interactions in virtual environments is challenging due to the high degrees of freedom in the human body and the need for physically accurate poses that do not collide with each other. Traditional methods for human-human interaction are based on motion tracking or 3D body reconstruction, but lack generative capabilities. Recent generative methods enable the synthesis of individual or interacting motions via text or image input, but generally fall short in modeling close interactions. This paper introduces a novel generative model for close 3D human-human interactions using a conditional variational autoencoder (cVAE), which generates poses for one human conditioned on the pose of another, allowing for controlled and diverse interaction synthesis. To train our model, we address two underlying long-standing challenges in the field of human-human interaction: data scarcity, for which we propose an automated supervised data augmentation strategy that generates synthetic yet realistic interaction poses; and collision awareness in generative approaches, for which we propose a self-supervised loss based on a collision resolution technique using volumetric proxies to ensure physically correct interactions. We extensively evaluate the capabilities of our model, and demonstrate a wide variety of plausible and physically correct interactions, not possible to generate with current state-of-the-art methods.
Authors: Yaoyuan Guo, Zhibin Gu, Songhe Feng, Yuhui Zheng, Bing Li
Abstract: Prototype-based Incomplete Multi-view Clustering has recently attracted increasing attention by exploiting prototypes as semantic anchors for missing-view imputation. However, existing approaches are still limited in three aspects. First, they typically focus on enforcing cross-view prototype consistency, while ignoring view-specific information embedded in prototypes, thus limiting multi-view expressiveness. Second, most methods rely on instance-level contrastive learning that only aligns paired samples across views, failing to preserve cluster-level relational structures. Third, missing-view imputation is usually performed using global prototypes alone, without considering local geometric neighborhood structures, leading to inaccurate recovery of missing representations. To address these limitations, we propose a novel framework termed Structure-aware PrOtotype disentanglement foR incomplete multi-view clusTering (SPORT), which explicitly disentangles shared and view-specific components of prototypes while preserving cluster-level relational structures. Specifically, we decouple prototypes into orthogonal shared and view-specific components, aligning only shared components to capture consensus semantics while de-correlating view-specific components to preserve complementary information. Meanwhile, a structure-aware contrastive learning mechanism is incorporated to explicitly model cluster-level relationships during cross-view representation learning. Furthermore, a hybrid imputation strategy integrates global prototype matching with local neighborhood matching, enabling joint exploitation of semantic prototypes and manifold structures for missing-view recovery. Extensive experiments on six benchmark datasets show that SPORT achieves superior performance over state-of-the-art methods under various missing rates.
Authors: Kuan-Lin Chen, Yuan-Kang Lee, Cheng-Yuan Chiang, Jian-Jiun Ding
Abstract: Local motion blur detection requires pixel-level localization of blurred regions. Existing benchmarks let models rely on gradient shortcuts that fail to transfer. We introduce BOCCHI (Blurred Objects Captured across Cameras with Human-annotated Imagery), a real-captured benchmark whose sharp regions overlap the blur gradient distribution and defeat these shortcuts, and propose MSDCT-UNet (Multi-Scale Discrete Cosine Transform UNet), a frequency-aware encoder-decoder injecting multi-scale DCT priors through DCT Attention and FiLM. MSDCT-UNet ranks first in in-domain mIoU and boundary localization on BOCCHI, and BOCCHI-trained models outperform every other training source on cross-dataset transfer with only 633 training images.
Authors: Benjamin Friedman
Abstract: Layout-based 3D scene synthesizers place each object using two human-annotated channels: a categorical class label and a canonical-pose convention. We ask whether a single self-supervised token derived from object geometry can replace both, and study such tokens directly as a representation, decoupled from any synthesizer. A Finite Scalar Quantization (FSQ) point-cloud autoencoder is chamfer-trained on placed 3D-FUTURE furniture with no labels or pose annotations. Diagnostic probes recover fine-category (62.6 +/- 0.5%), super-category (85.6 +/- 1.3%), and yaw (52.7 +/- 0.5 deg) from the codes alone. Swapping the chamfer target from the rotated to the un-rotated point cloud collapses the yaw signal while raising class recovery, showing the codes' rotation content can be set by the training objective. Scaling across asset libraries needs codes that transfer; on an unseen dataset (ShapeNet), alignment is category-dependent: box-like furniture transfers, organically-shaped furniture does not, and a target-blind augmentation partly closes the gap.
Authors: Nuray Toganas, Adilet Yerkin, Elnara Kadyrgali, Muragul Muratbekova, Aron Karatayev, Pakizar Shamoi
Abstract: Color naming is an important part of human color perception. Its task is to allow people to describe continuous colors using discrete color categories. However, the boundaries between color categories are often unclear, and some colors may be perceived differently depending on their saturation and brightness. While certain color categories remain recognizable across a wide range of shades, others may be associated with different color names when their appearance changes. This study investigates the consistency of color naming for red, yellow, and green color categories using a free color-naming experiment. A set of 18 color samples was selected from the COLIBRI dataset to represent different shades of these colors. Participants (n = 92) were asked to freely assign color names to each sample in Kazakh, Russian, or English without being limited to predefined categories. The results show that color categories differ in their consistency. Green shades were consistently identified as green despite variations in appearance, whereas yellow shades received a wider variety of names, including gold- and brown-related descriptions. Red shades showed moderate naming consistency. Our findings suggest that some color categories occupy broader perceptual regions than others and may therefore be more robust to visual variations. The study results can be used to develop perceptually meaningful color models and color naming systems.
Authors: Petter Reijalt, Sander Gielisse, Rickard Karlsson, Jan van Gemert
Abstract: Real-world deployment of vision models to broadly benefit society is arguably a main research objective. In optical flow, however, the difficulty to obtain the ground truth has focused research mainly on synthetic data and domain-specific benchmarks. Here, we investigate the severity of this mismatch. We study how well modern optical flow estimation models generalise to real-world video and question if accuracy on synthetic benchmark proxies actually predicts accuracy on real-world optical flow. To address this, we build a real-world evaluation benchmark and evaluate the real-world generalisability of a broad set of recent optical flow models using standard checkpoints. Our benchmark contains 8,204 frame pairs across TAP-Flow, Slow Flow, and our own dataset FlowFactor. FlowFactor is a manually annotated real-world benchmark of 1,000 HD frame pairs organised into four confounding factors: large displacements, repetitive textures, occlusions, and lighting variation. Each setting mainly varies only one factor, enabling diagnostic, confounder-specific analysis. Using FlowFactor, we reveal that performance on varying lighting and large displacements correlates most strongly with real-world accuracy, and that improvements on large-motion regimes can trade off against robustness in small-motion, stationary scenes. Our experiments show that progress on Sintel, KITTI and Spring only weakly predicts accuracy on real-world data, highlighting the need for a broad real-world optical flow benchmark. Interestingly, scaling up the amount of training data does not necessarily resolve the gap, calling for new innovative research instead of simply scaling data and compute.
Authors: Aaron Maurice Berman, Shantanu Dave
Abstract: We introduce Grassmannian splatting, a dynamic scene representation whose primitives are Gaussians supported on 3-planes in spacetime $\R^4$: generically, spatial 2-planes in uniform translation along their normals. Each primitive carries a unit normal $n \in \mathbb S^3/\{\pm 1\} \cong \mathrm{Gr}(3,4)$ and an unconstrained factor $L \in \mathbb R^{4 \times 3}$, with covariance \[ \Sigma_{4\mathrm{D}} = (P_n L)(P_n L)^T, \qquad P_n = I - n n^T. \] For generic $L$ and $n \neq \pm e_0$, conditioning on time returns a rank-2 surfel at every frame. The normal of the disk and its velocity along that normal are read off from $n$; the disk shape and the tangential drift of its center are set by $L$. Existing native 4D Gaussian splatting methods [\it{Yang et. al. 2023,Duan et. al. 2024}] slice full-rank spacetime covariances, so their per-frame primitive is a volumetric ellipsoid; since conditioning lowers rank by exactly one, a rank-2 surfel in the slice requires a rank-3 spacetime covariance, and the parameterization above realizes exactly these. The motion model is closed form, i.e. no deformation field is learned, and no custom CUDA is required: the conditioned disk feeds a standard 3DGS rasterizer through its precomputed-covariance interface. A soft clamp in the Schur denominator regularizes the static orientation and continuously bridges rank-3 static and rank-2 dynamic behavior, so static and moving primitives form a single continuous family. On the 17 HyperNeRF scenes of MonoDyGauBench, training is fastest among all compared methods (4.9 to 5.6 times faster than the strongest quality baselines), while ranking second in PSNR, MS-SSIM, and LPIPS. Code: https://github.com/PaulCelanCoding/grassmannian-splatting
URLs: https://github.com/PaulCelanCoding/grassmannian-splatting
Authors: Filip Pawlicki, Marcel Ka\'ndu{\l}a, Marcin Pucek, Kamil Dobies
Abstract: Recent Video Super-Resolution (VSR) methods rely heavily on transformers and explicit optical flow, creating computational overhead and custom operations that hinder deployment on hardware accelerators like TensorRT. To address this, we introduce NanoVSR, a scalable, fully convolutional architecture designed for resource-constrained edge devices. Using structural reparameterization, NanoVSR collapses into standard convolutions during inference, ensuring seamless hardware compatibility and negligible runtime overhead. Furthermore, despite lacking explicit motion compensation, it maintains competitive restoration quality by implicitly learning spatio-temporal alignments through progressive training. Evaluated on the REDS4 benchmark, NanoVSR demonstrates an exceptional balance between accuracy and computational efficiency, significantly improving the trade-off for compact architectures. Our NanoVSR-644k baseline yields 28.64 dB PSNR while delivering 27.2 FPS on the NVIDIA Jetson Orin NX 16GB (25W), offering massive speed gains over heavier models. The scaled NanoVSR-1.7M variant reaches 29.15 dB with a throughput of 19.58 FPS, providing superior, edge-optimized upscaling. Code is available at https://github.com/filippawlicki/nanovsr.
Authors: Shengyuan Liu, Jia-Xuan Jiang, Boyun Zheng, Cheng Wang, Zipei Wang, Wentao Pan, Hongtao Wu, Houwen Peng, Yu Gu, Lichao Sun, Yixuan Yuan
Abstract: Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by coupling planning, code execution, debugging, and empirical feedback. Translating this capability to medical imaging remains difficult because each task imposes modality-specific experimentation and strict requirements for validation protocols and prediction artifacts. Here we introduce AMID, an autonomous multi-agent framework for medical imaging model development. AMID first proposes Data-Conditioned Method Planning, which refines coarse task-level search spaces into executable, parallelizable method lanes grounded in task-specific data analysis and runnable medical-imaging resources. It then develops Verification-Guided Two-Stage Optimization, moving from broad early exploration of diverse method lanes to selective exploitation of promising candidates while enforcing strict verification of validation protocols, metric computation, and prediction artifacts throughout the optimization. Across 20 medical imaging challenge tasks spanning diverse modalities and prediction types, AMID outperformed evaluated general-purpose MLE systems and, on several tasks, approached or matched strong human-designed challenge solutions. These results suggest that AMID can turn task-specific medical imaging model development from bespoke manual engineering into an agentic workflow for producing high-performing and auditable model artifacts across heterogeneous tasks.
Authors: Trang Nguyen, Shuang Wu, Runyan Tan, Phillip Howard
Abstract: While diffusion models achieve state-of-the-art image quality for text-to-image (T2I) generation, recent work has demonstrated that they suffer from sample diversity collapse. In this work, we investigate whether autoregressive (AR) image generation models can push the Pareto frontier between image quality and sample diversity. With recent advances in quality and efficiency, AR models have emerged as a viable alternative to diffusion-based image generation. Beyond enabling new use cases such as interleaved image-text generation, their sequential generation process makes them compatible with a wide range of token-based decoding strategies originally developed to improve diversity in text generation. Motivated by the potential of a better diversity-quality tradeoff in the AR paradigm, we present the first systematic study of sample diversity in AR image generation models. We show that two key properties of AR image generation, persistently high token-level entropy and substantial redundancy in visual token spaces, limit the effectiveness of existing token-level decoding methods for diversity enhancement. We therefore propose $p$-less cluster, a new decoding strategy that performs entropy-based truncation sampling at cluster level rather than at token level. We evaluate our approach and baseline decoding methods across four autoregressive T2I models and two datasets using a comprehensive suite of metrics spanning image quality, prompt alignment, and diversity. Our results show that $p$-less cluster unlocks the greatest diversity across most evaluated autoregressive T2I models and datasets while maintaining image quality and prompt alignment.
Authors: Jian Ning, Qin Zou, Linchun Wu, Yuanhao Yue, Kunmo Li, Shoubin Chen, Zhongyuan Wang
Abstract: 3D point cloud anomaly detection plays a vital role in industrial manufacturing, yet it faces significant challenges due to the scarcity and high acquisition cost of real anomalous samples. The inherently anomaly-free training data further hinders detection methods from effectively learning discriminative features between normal and abnormal instances. To address these issues, we propose PA3AD, a novel framework that introduces a physics-inspired pseudo-anomaly generation strategy to create physically plausible anomalous samples from normal data. Additionally, we incorporate prototype features via a weight-sharing mechanism to guide the model in capturing the distribution shifts between normal and anomalous samples. Specifically, PA3AD introduces two key innovations to tackle the scarcity of real anomalies. First, a physics-inspired module generates diverse pseudo-anomalous point clouds from normal data via multi-physics modeling. Second, momentum-updated prototypes and a difference-aware fusion block capture stable normal representations and their discrepancies with pseudo-anomalies. This design effectively learns distribution shifts, achieving superior detection performance. Extensive experiments on the Anomaly-ShapeNet and Real3D-AD datasets demonstrate that our method consistently outperforms existing state-of-the-art approaches. Our code will be made publicly available at https://github.com/NingxiaoJian/PA3AD.
Authors: Yuwen Zhang, Yujie Liu, Ao Wang, Yikuang Yuluo, Shuangyang Zhong, Haijun Yu, Yixing Huang
Abstract: Objective. Existing quadratic unconstrained binary optimization (QUBO)-based sparse-view computed tomography (CT) reconstruction neglects photon-counting statistics and anatomical heterogeneity. We address both limitations within the QUBO framework.Approach. We propose a quantum compressed-sensing CT method combining penalized weighted least squares (PWLS) and guided total variation (GTV). PWLS weights projection residuals by photon-count reliability, whereas GTV uses gradients from a prior image reconstructed by the simultaneous algebraic reconstruction technique (SART) to preserve edges and suppress noise in homogeneous regions. After binary encoding, both terms form a unified QUBO model. Experiments used four 40 times 40 CT images under a 10-view fan-beam geometry with Poisson noise. Comparisons included conventional reconstruction methods, QUBO variants, gradient descent, simulated annealing, and a D-Wave hybrid quantum-classical solver.Main results. PWLS-GTV achieved the best reconstruction quality across all cases. In the representative chest case, it reached a peak signal-to-noise ratio (PSNR) of 36.64 dB, compared with 22.48 dB for SART, the best conventional baseline. GTV consistently outperformed conventional total variation. Simulated annealing and the D-Wave hybrid solver produced similar reconstructions, whereas gradient descent was ineffective. Repeated hybrid-solver runs showed stable performance.Significance. The framework incorporates photon-statistical weighting and structure-guided regularization into QUBO-based CT reconstruction without changing its quadratic form, providing a proof of concept for quantum-assisted sparse-view CT reconstruction.
Authors: Melanie Wille, Dimity Miller, Tobias Fischer, Scarlett Raine
Abstract: Underwater object detection is strongly affected by domain shift, where performance can vary significantly across different locations, habitats, and deployment conditions. However, detector performance is typically evaluated using aggregate metrics that hide failures in specific environments, while existing domain generalization benchmarks often rely on synthetic variations that do not reflect real-world conditions. We introduce a framework that characterizes underwater images by appearance, scene composition, and acquisition geometry to assign domain labels. Using this framework, we perform the first systematic study of how domain factors influence both human annotation quality in underwater object detection datasets and deep learning-based detector performance, revealing substantial domain-dependent discrepancies. By incorporating physically meaningful domain labels, domain shift becomes something we can characterize, measure, benchmark, and act on. We highlight how this can be used to guide data collection and annotation, design more informative benchmarks, and assess detector robustness across diverse underwater environments.
Authors: Syed Irfan Ali Meerza, Oktay Ozturk, Amir Sadovnik, Jian Liu
Abstract: AI models are increasingly trained on personal images scraped from social media and public platforms, often without consent, leading to serious privacy violations, such as unauthorized facial recognition and targeted advertising. To counter this, researchers have developed unlearnable examples (UEs), images modified with imperceptible noise to prevent AI models from extracting meaningful information. However, existing UE methods primarily rely on pixel-space noise, which can be bypassed by relearning strategies such as adversarial training, image transformation, and compression. While some techniques improve robustness, they often come at the expense of significant degradation in image utility and perceptual quality. In this paper, we introduce DiffUE to overcome these limitations by injecting noise into the semantic space of images instead of the pixel space. Instead of corrupting pixel values, DiffUE modifies high-level semantic features of images, ensuring robust unlearnability while preserving visual quality and utility. By leveraging a diffusion-based autoencoder framework to manipulate semantic features, DiffUE generates purposeful, natural-looking modifications that effectively resist advanced relearning strategies. Extensive experiments on four datasets, CIFAR-10, CIFAR-100, CelebA-HQ, and ImageNet, as well as a subjective user study, demonstrate that DiffUE significantly enhances the trade-off between image quality and unlearnability, offering a more robust and effective solution for safeguarding personal data in an increasingly exploitative AI landscape.
Authors: Vu Minh Tran, Khang Nguyen
Abstract: UAV-based vehicle re-identification (ReID) has emerged as a promising technique for traffic surveillance, urban monitoring, and public-safety applications thanks to the flexible viewpoints and wide-area coverage provided by unmanned aerial vehicles. However, despite recent progress on UAV-based vehicle ReID benchmarks, the robustness of existing methods under adverse weather remains insufficiently studied. This is important because weather degradation can significantly affect the fine-grained appearance cues required for reliable vehicle matching in aerial imagery, especially under small object scale, viewpoint variation, and complex backgrounds. In this paper, we present a controlled comparative study of three representative recent vehicle ReID methods, namely CLIP-ReID, MSINet, and AdaSP, on two UAV-based benchmarks, VRU and UAV-VeID. To ensure consistent robustness evaluation, we generate synthetic foggy and rainy variants of both datasets using an analytical weather-effect pipeline while preserving the original identities and data splits. All methods are then trained and evaluated under matched clean, foggy, and rainy conditions. Experimental results show that adverse weather consistently degrades retrieval performance across both datasets, with rain causing larger drops than fog in nearly all settings. Among the evaluated methods, AdaSP demonstrates the strongest robustness, achieving 93.0% and 88.5% mAP on VRU-Large, and 88.7% and 76.2% mAP on UAV-VeID-Test under foggy and rainy conditions, respectively. Overall, our findings show that simulated adverse weather substantially increases the difficulty of UAV-based vehicle ReID, reveals clear robustness differences among recent methods, and highlights the need for weather-aware model design and evaluation protocols in future aerial ReID research. The code is released at https://github.com/tranminhvu945/Benchmarking-ReID.
Authors: Ryo Sakai, Yongpeng Cao, Nobutaka Kimura
Abstract: Maintenance of critical infrastructures, such as railways and power plants, is essential for operational safety and reliability. However, the declining number of skilled maintenance workers poses a serious challenge to sustaining these operations, highlighting the need to effectively transfer expert know-how to less experienced workers. Although traditional interview-based approaches have been used to elicit maintenance skills, they struggle to capture know-how that experts themselves may not consciously recognize. To address this gap, we proposed a method that detects anomalous frames of candidate actions including know-how by comparing a video of manual-based work with that of expert maintenance workers. In a simulated maintenance experiment involving a distribution board, our method targeted 11 types of actions not described in the manual and achieved a 66.9% extraction rate, marking a 50-percentage-point improvement over conventional techniques. These findings underscore the effectiveness of our approach in revealing hidden maintenance knowledge, thereby contributing to enhanced skill transfer and workforce development in critical infrastructure maintenance.
Authors: Payel Sarmah, Ayush Ranjan, Piyush Kaushik Bhattacharyya, Anil Kr. Shaw, Pradip Kr. Das
Abstract: In recent years, Unmanned Aerial Vehicles (UAVs) or drones have gained rapid response in terms of security, search and rescue (SAR), border surveillance, etc. Existing monitoring frameworks often struggle to maintain detection consistency when targets undergo significant scale variations due to altitude changes, leading to critical information gaps. To address this issue, this work proposes an integrated real-time detection pipeline for detecting targets through the wireless live drone video feed. Build upon YOLOv8-nano architecture, extensive flight experiments were conducted to determine the detection performance across multiple flight altitudes. Trained on VisDrone2019 dataset, the results of YOLOv8-nano model achieves 57.4%, 41%, 44.8% and 20.3% in precision, recall, mAP and mAP50:95 respectively. While demonstrating on real environment, this analysis revealed that the algorithm achieves near-total detection reliability at altitudes between 16 and 25 meters with the detection frame rate consistently maintained above 41 FPS and reaching a peak of 50 FPS. However, the goal of this work is to enable real-time person detection from an aerial platform via wireless transmission. This approach effectively addresses the dual challenges of identifying targets at varying scales and ensuring near-to-accurate localization during aerial observation.
Authors: Khush Kataruka, Harshit Maurya, Anuja Vats, Murari Mandal, Kiran Raja, Praveen Kumar Chandaliya
Abstract: Efficient waste segregation is critical for sustainable urban management and environmental governance. Existing automated systems are limited by single-modality visual processing, insufficient contextual understanding, and weak regulatory alignment. To address these issues, we propose a language-guided vision-AI framework that integrates vision-language models and multimodal large language models for joint visual-linguistic reasoning. This framework implements a visual question answering paradigm aligned with India's Solid Waste Management Rules 2016. We construct a new WasteVQA dataset with 13,500 question-answer pairs across 21 waste categories. Experiments show that the BLIP-based model achieves a BLEU score of 0.8291 and a BERTScore of 0.9273, outperforming traditional CNN-based methods. This work improves source-level segregation accuracy, ensures regulatory compliance, and supports scalable deployment for municipal and citizen-facing waste management, promoting multimodal AI in sustainable urban infrastructure. The source code and dataset are available at: https://github.com/Khushkataruka/WasteAssistant
Authors: Haoqing Li, Jun Shi, Mingchao Li, Zehua Zhu, Qiwei Jia, Jiong Shi, Hong An
Abstract: We present Spectral Consistent Flow (SC-Flow), a 3D medical image translation framework with a single function evaluation (1-NFE) in the latent space. This approach reformulates medical image translation as a stochastic Brownian bridge process that directly constructs a mapping between source and target modalities by predicting the support regularized mean velocity field. To mitigate modality entanglement, over-smoothing, and artifacts induced by the implicit low-pass modulation of the latent average velocity, we introduce a Spectral Consistency Corrector that dynamically regularizes the evolution of the power spectral density via learnable frequency-domain gain modulation. This mechanism establishes an explicit bridge between spatial textures and spectral energy flow, enabling the model to recover fine-grained anatomical fidelity while maintaining global structural coherence. Extensive experiments on four datasets demonstrate that SC-Flow delivers significantly more accurate, consistent, and robust performance across various translation scenarios.
Authors: Zhaoyang Li, Yanjun Li, Wangkai Li, Yujia Chen, Tianzhu Zhang
Abstract: Vision-Language Models (VLMs) are costly at inference time because they must process long sequences of visual tokens. Existing token pruning methods often degrade under high compression by blindly discarding information, breaking spatial structure or collapsing diversity. We propose SpecFlow, a training-free framework that shifts the paradigm from destructive pruning to conservative condensation, strictly enforcing spatial coverage and statistical conservation to ensure stability. Treating visual tokens as nodes in a $k$NN graph, SpecFlow (i) computes a stable importance field via spectral heat flow to preserve structural coherence, (ii) allocates budgets via adaptive spatial partitioning to guarantee coverage, and (iii) aggregates discarded information into coreset sinks to maintain statistical conservation. The method is plug-and-play, requires no fine-tuning, and is compatible with FlashAttention. Experiments confirm that our SpecFlow outperforms SOTA methods across tasks, VLM architectures, and pruning ratios. Notably, LLaVA-1.5 with SpecFlow retains 95.6\% of original performance despite pruning 88.9\% of visual tokens, offering an exceptional efficiency-accuracy balance. Code is available at https://github.com/Lzy-dot/SpecFlow
Authors: Shubham Rao
Abstract: Deploying AI-based visual inspection in manufacturing is hard because requirements change often, new defect types appear, and large labeled datasets are rarely available. We propose answer-conditioned chain-of-thought (CoT) distillation for rapidly adapting small vision-language models (VLMs) to new industrial tasks using minimal labeled data. A frontier VLM receives each training image along with its correct label and generates a justified visual explanation. A 3B-parameter model is then fine-tuned on these reasoning-augmented examples via LoRA. By conditioning on correct answers, we ensure all training reasoning is directed toward the correct conclusion, which is critical because frontier models score as low as 24.1% on our hardest task. We validate on four industrial classification tasks spanning three image modalities using only 18 to 30 labeled images per task. Across 4 seeds per task (32 training runs), our method outperforms direct fine-tuning on all 16 seed-task combinations, with mean improvements of +1.7 to +4.4 percentage points. A controlled equal-budget experiment confirms the improvement comes from reasoning quality, not additional training steps. An unconditioned baseline demonstrates that with out answer-conditioning, wrong reasoning degrades performance by 17.8 percentage points. On weld radiograph classification, the fine-tuned 3B model outperforms GPT-4.1 by 10.0pp using just 24 training images.
Authors: M. Pr\r{u}\v{s}ek, A. Novoz\'amsk\'y, F. \v{S}roubek, T. Volfov\'a, V. Svobodov\'a Pavl\'i\v{c}kov\'a, S. Rimpelov\'a
Abstract: Few-shot spheroid segmentation must adapt to new cell lines, microscopes, and illumination conditions from only a small set of annotated images. While foundation few-shot segmenters can be accurate, their large opaque backbones make it difficult to understand which visual cues drive success or failure. We study this question with HyperBank, a differentiable bank of classical image-processing operators combining Frangi vesselness, a Sauvola threshold pyramid, structure-tensor responses, gradient magnitude, and Laplacian-of-Gaussian filters. HyperBank is fitted on the annotated support images and evaluated on disjoint held-out images across three independently acquired spheroid datasets. We treat it not as a general replacement for foundation models, but as a compact, interpretable few-shot microscopy pipeline and an analytic-prior probe of which classical cues carry the few-shot signal. The results show that, adapted on the same few annotated support images, a compact bank of analytic priors is competitive with, and on small-cluster, contrast-driven data can outperform, much larger foundation models, while those models remain stronger on externally sourced, texture-dominated spheroids. Leave-one-family-out ablations indicate that the useful few-shot signal is distributed across operator families and strengthened by support-set-tuned morphology.
Authors: Yanjin Zhu, Shaofan Liu, Jianke Zhu
Abstract: Incremental scene reconstruction is essential for real-world applications. Although 3D Gaussian Splatting shows strong potential, most existing approaches require offline conversion of the optimized Gaussians into an intermediate implicit field for explicit mesh extraction, which hinders seamless integration with downstream tasks. To address this limitation, we propose a novel online framework that incrementally reconstructs and updates high-fidelity explicit meshes by directly triangulating a dense geometric Gaussian representation, which supports both high-quality rendering and incremental surface reconstruction. Moreover, we present a direct meshing algorithm that efficiently extracts and updates the mesh from the Gaussian set. To ensure mesh accuracy, we enforce a plane-based pulling constraint that dynamically aligns 3D Gaussian primitives to the approximated local surface. Furthermore, our framework significantly reduces memory and computational overhead during long-sequence processing by dynamically freezing fully optimized historical regions. Experiments on public datasets demonstrate that our method outperforms conventional Gaussian-based methods on both rendering quality and reconstruction accuracy.
Authors: Caihui Yan, Gang Cao, Huawei Tian, Zhen Li, Yuhang Zhai
Abstract: The rapid advancement of generative artificial intelligence (AI) has made synthetic images remarkably realistic, posing security threats such as misinformation and fraud. It is significant to detect the synthetic image in the manner of passive and blind image authentication. Most existing detectors rely on supervised training with large labeled datasets, leading to high costs and degraded performance on unknown generative models. To attenuate such deficiencies, we propose a training-free detection method. Specifically, noise residual fingerprints are first extracted by a simple yet effective pre-trained Noiseprint++ model. Then multi-scale features are further extracted from such residual by a frozen Vision Transformer (ViT), followed by adaptive weighted fusion. Only a few real image samples are used needed to initialize the clustering centers for unsupervised K-Means, distinguishing real and synthetic images without training. Extensive evaluations on four benchmark datasets show that our proposed scheme achieves an average accuracy of 82.2%, outperforming the state-of-the-art detectors on generalization ability. Superior performance is gained on the popular diffusion type of synthetic images, and the effectiveness of each module is validated by ablation studies. Source code will be publicly available at https://github.com/multimediaFor/NoiseCluSID.
Authors: Changfei Fu, Guangcheng Chen, Wenjun Xu, Hong Zhang
Abstract: Benefiting from the powerful priors embedded in large-scale pre-training data and the emerging commonsense reasoning ability, large language models (LLMs) have shown unprecedented generalization capabilities in many research fields. Recently, projecting visual embeddings into the language space via vision-language models (VLMs) to achieve sim-toreal and cross-scene generalization has become a prevailing paradigm in the field of Vision-and-Language Navigation in Continuous Environments (VLN-CE). VLN requires an embodied agent to navigate through unseen environments following natural linguistic instructions. We emphasize that a VLN task can be decomposed into a sequence of sub-tasks, each corresponding to a process of 3D spatial interaction with the environments described by instructions such as "walk to the end of the sofa and turn left." However, such spatial interactions involving moving into the image along the direction of depth sensing are puzzling for VLMs as they were predominantly trained on conversations with RGB images. Rather than incorporating depth or 3D geometric information-which VLMs rarely encounter during pretrainingwe propose an alternative approach: fine-tuning VLMs to learn navigation interactions directly in 2D pixel space through autoregressive trajectory generation. Given a linguistic instruction and historical observations, our model sequentially predicts a series of pixel coordinates, drawing a trajectory from the bottom center of the current observation. While prior work has proved that pixel-goal supervision outperforms learning of discrete actions, our experiments further verify that the supervision of pixel-space trajectory significantly enhances VLN performance. Moreover, we demonstrate that our flagship model achieves state-of-the-art level performance with relatively limited computational resources and training data.
Authors: Shuxuan Yao, Chengjia Wang, Jianyuan Sun, Junyu Dong, Xinghui Dong
Abstract: Reflections of water pose a significant challenge for computer vision systems, as standard deep learning models frequently confuse objects with their mirror images, producing spurious false positives and negatives in tasks such as object detection and semantic segmentation. As a result, detecting reflection axes in natural-water scenes is pivotal for reliable object detection and scene understanding. To mitigate this issue, we leverage the intrinsic imperfect reflective symmetry of water and introduce a Symmetry-Aware Water Reflection Detection Network, namely, SAWRD-Net, that couples dihedral group-equivariant convolutions with a matrix-decomposition decoder in an end-to-end framework. First, dihedral group convolutional layers extract geometry-consistent feature maps that explicitly encode both rotational and mirror symmetries. A Multi-scale Reflection Equivariant block then aggregates features across scales and employs a symmetric-attention mechanism to highlight reflection-relevant regions. The proposed matrix-decomposition decoder factorizes high-dimensional features into compact low-rank parameter and confidence spaces, after which the network directly regresses keypoints on the reflection axis. Then a robust principal component analysis fits the final axis. Evaluated on the largest available water reflection scene data set, SAWRD-Net achieves a true-positive rate of 0.890 against human annotations, outperforming all existing water reflection detectors.
Authors: Zuzhi Yang, Shuai Wang, Mounir Kaaniche, Ziwei Li, Zhiming Cheng, Zhidong Zhao, Chenggang Yan
Abstract: Category-level object pose estimation is a crucial yet challenging task in both academia and industry, and has achieved remarkable success by leveraging keypoint-based correspondence paradigms. However, most existing methods increasingly rely on stronger feature learning while overlooking whether the established correspondences are geometrically stable across diverse perturbations. This often results in fragile pose recovery under intra-class shape variations and occlusions. To tackle this challenge, we develop a novel Triangle-Invariant Geometric Consistency Learning for Category-Level Object Pose Estimation (TriCons-Pose) to anchor stable keypoints and aggregate pose-invariant cues, yielding reliable canonical mapping and accurate pose estimation. Specifically, a Structure-Consistent Keypoint Detector (SCKD) is designed to identify robust keypoints by enforcing cross-view structural consistency via normalized pairwise distance matching. Moreover, we propose a Pose-Invariant Geometric Aggregator (PIGA) to augment keypoint representations by injecting triangle-based pose-invariant descriptors into a local-to-global attention mechanism. The proposed framework is optimized using standard objective functions while incorporating an additional geometry consistency loss. Extensive experiments on REAL275, CAMERA25, and HouseCat6D datasets demonstrate the effectiveness of the proposed approach.
Authors: Sutharsan Mahendran, Darshana Priyasad, Kaushik Roy, Tharindu Fernando, Sridha Sridharan, Clinton Fookes, Peyman Moghadam
Abstract: Cross-modal distillation from Vision Foundation Models (VFMs) to LiDAR backbones has recently emerged as a self-supervised pretraining strategy that reduces reliance on dense point-wise annotation for 3D scene understanding. However, existing distillation pipelines typically treat the VFM as a frozen feature source and train a heterogeneous 3D backbone to match fixed image embeddings, forcing the student to bridge both the modality gap and the cross-architecture gap between dense ViT token representations and sparse 3D encoders. We propose TOLiD, a self-supervised pretraining method for LiDAR representation learning that addresses this gap by coupling a LiDAR backbone with a student Vision Transformer (ViT) initialized from a frozen VFM teacher and applying supervision over compatible patch-token representations. TOLiD converts the set of point features within each image patch frustum into a token using Frustum Pooling followed by Frustum Attention, and performs token-level distillation with visibility masking. For LiDAR-only deployment, we lift token features back to per-point representations using masked bilinear sampling to avoid patches that have limited LiDAR points. We extensively evaluate TOLiD on five heterogeneous LiDAR datasets and four cross-sensor adaptation pairs, demonstrating improved transfer with frozen backbones and lightweight heads.
Authors: Yan Lin, Ziheng Wang, Shuang Chen, Amir Atapour-Abarghouei, Stephen McGough
Abstract: Medical image classifiers are often trained within one source population, yet clinical deployment requires robustness to patients whose appearance, acquisition style, and disease prevalence differ from the source cohort. Existing fairness and robustness methods often require group supervision or treat appearance variation as an undifferentiated nuisance, which is insufficient when population-correlated low-level cues and lesion evidence share edge and texture structure. We study a strict source-only cross-population setting, where external populations are unseen during optimization, validation, scheduling, hyperparameter and model selection. We propose RED-Sphere, a plug-and-play robustness framework for image classification under unseen population shifts. It estimates shortcut-sensitive nuisance responses with an edge and feature energy prior, attenuates dominant responses through residual soft gating, regularizes masked nuisance views with counterfactual-inspired consistency and separation losses, and predicts labels with normalized spherical prototypes. It favours angular semantic evidence over source-correlated activation magnitude while preserving lesion structure. Although demonstrated on 2D Scanning Laser Ophthalmoscopy (SLO) fundus classification for Age-Related Macular Degeneration (AMD) and Diabetic Retinopathy (DR), RED-Sphere is not tied to retinal anatomy: the same principle can be adapted with modality-specific nuisance priors wherever appearance shortcuts and semantic evidence are entangled. Under a strict White-only Harvard-FairVision protocol, RED-Sphere improves held-out macro-F1 across all 20 task and backbone comparisons, with average gains of 1.28 and 2.98 F1 points on AMD and DR. Gains in AUC and PR-AUC, visual diagnostics, ablations, and sensitivity analyses further support stronger external semantic alignment and more stable angular disease geometry.
Authors: Xiyan Su, Frank Diermeyer, Markus Lienkamp
Abstract: Driving world models built on large video-diffusion backbones generate realistic scenes but are hard to control: enforcing a traffic norm typically means retraining the backbone or conditioning it on hand-built layouts. We ask whether controllability requires training at all. Our experiment shows that a rectified-flow driving world model, which jointly generates future video and a planned ego trajectory, can have its planned trajectory steered entirely at sampling time by differentiable energy functions that encode driving norms, without knowledge-specific retraining of the diffusion backbone. Concretely, we demonstrate that a world model built on Open-Sora 2.0 MM-DiT backbone can be steered to brake at a counterfactual target by injecting energy guidance at sampling time. However, we find that the generated video does not yet follow the steered trajectory through the backbone's joint self-attention and identify the cross-stream coupling as a crucial requirement for end-to-end-controllable rollouts.
Authors: Dung Minh Do, Nhat-Thanh Huynh, Duc Minh Huynh, Doanh C. Bui, Khang Nguyen
Abstract: Whole-slide images (WSIs) provide rich tissue-level and cellular-level information, but storing and transmitting high-magnification pathology data is resource-intensive. Moreover, annotating WSIs at the pixel level is labor-intensive and time-consuming. Therefore, it is important to investigate whether low-magnification pathology images with limited annotations (i.e., image-level instead of pixel-level labels) can achieve performance comparable to high-magnification images. This paper presents a systematic benchmark study on weakly supervised histopathological image segmentation under different low-resolution storage settings. Starting from high-resolution image patches, we simulate lower-magnification inputs and reconstruct them to the original size using interpolation and deep learning-based reconstruction methods before applying the weakly-supervised segmentation pipeline. This framework enables a quantitative evaluation of how weakly supervised methods respond to different levels of resolution degradation. Experimental results show that reconstruction quality metrics alone are insufficient to predict downstream segmentation performance. In particular, the study identifies a critical degradation point where the localization of small-scale structures declines significantly. These findings provide practical guidance for designing efficient digital pathology storage systems while maintaining reliable automated analysis. Code is available at https://github.com/Dung-Dx/LowMagWSS
Authors: Dylan Xinming Hou, Juntian Zhang, Xu Gu, Yichen Wu, Nils Lukas, Gus Xia, Xiuying Chen, Yuhan Liu
Abstract: The evolving realism of AI-generated Videos (AIGC-V) is rapidly rendering traditional artifact-centric detection insufficient, necessitating a paradigm shift from low-level inspection to high-level semantic verification. This paper presents a comprehensive survey of AIGC-V detection, reframing the task as Factual Fidelity Verification, which asks whether the events, entities, and physical processes depicted in a video are consistent with real-world facts. To systematize this rapidly evolving field, we propose a Vision-Language Dual-View taxonomy that organizes existing methods into a hierarchical, four-layer landscape, spanning intrinsic cue analysis, spatiotemporal consistency modeling, cross-modal consistency reasoning, and language-guided world-level reasoning. This dual-view framing highlights a fundamental transition from artifact matching in traditional deepfake detection to evidence-based semantic verification enabled by vision-language models and agentic reasoning pipelines. Based on a systematic review of 221 works, we synthesize AIGC-V generation paradigms, survey the landscape of detection methods, and review evaluation metrics and benchmarks in line with proposed views. Finally, we discuss current challenges and identify promising directions toward robust, explainable, and trustworthy detection.
Authors: Jinqian Yang, Yichen Wu, Wanhua Li, Haokun Lin, Renzhen Wang, Xiangchu Feng, Xixi Jia
Abstract: Reconstructing high-fidelity 3D scenes from sparse-views remains a central problem in generalizable neural rendering. Existing generalizable 3D Gaussian Splatting (3DGS) methods often exhibit geometric artifacts in sparse-view settings, since supervision based solely on 2D photometric losses cannot resolve depth and correspondence ambiguities. To address this issue, we propose MAC-Splat, a training framework built around direct 3D consistency supervision. MAC-Splat builds on the MASt3R geometric backbone and a frozen DINOv3 encoder to obtain semantically informed 2D correspondences, which serve as geometric anchors for 3D supervision. Using these anchors, we define the Multi-Attribute Consistency (MAC) loss. This objective jointly regularizes the 3D attributes of matched Gaussians, including their position, shape, and appearance, by enforcing agreement in a common world coordinate frame. The formulation is robust to outliers and respects the geometry of covariance matrices, which leads to stable training under sparse-view conditions. Experiments on ScanNet++ show that MAC-Splat outperforms strong baselines, with particularly large gains under different overlap regimes. In particular, it improves average PSNR over Splatt3R by more than 4.5 dB, reduces LPIPS, and maintains performance as the camera pose gap increases. These results indicate that a direct, multi-attribute 3D consistency objective, when combined with high-quality correspondences, is effective for addressing the ill-posed sparse-view reconstruction problem.
Authors: Robert Wijaya, Ngai-Man Cheung
Abstract: Large Vision Language Models (LVLMs) require strong reasoning over both visual and textual input. Recent work suggests that cognitive elements, especially diverse representations and metacognition, correlate with better performance. Many of the needed perceptual functions are already provided by specialized domain-specific computer vision models, which act as the perceptual subsystem for detecting objects, localizing them, inferring states, recovering spatial layout, and reading text. The key challenge is to integrate these multi-encoder experts into a trustworthy, interpretable, and coherent representation that improves verifiability and reduces hallucinations. This is difficult because vision-language questions span different cognitive levels, yet most LVLM pipelines apply the same perception-reasoning routing regardless of the demand of each query. We propose an evidence-driven multimodal reasoning framework that utilizes a Bloom-inspired taxonomy as a hierarchical reasoning protocol. The two-stage cognitive verbalization first produces a Literal Evidence Summary by decomposing expert outputs into short, atomic evidence statements. It then performs Bloom Verbalization to turn these evidence items into a staged reasoning trace, and a lightweight Reasoning Trace Module quantitatively analyzes the trace to make evidence usage and reasoning progression explicit. Through this integration, we observed several improvements in perception and reasoning abilities. Moreover, the trace module provides quantitative evidence that different queries induce different cognitive entry levels and evidence-use trajectories that enable fine-grained analysis.
Authors: Hao Zheng, Jinyi Huang, Tiantian Zheng, Xun Xu, Tuka Alhanai
Abstract: Assembly action understanding is a key enabler for effective human-robot collaborative assembly, yet it remains challenging due to subtle motions and fine-grained hand-object interactions. We adapt vision-language models (VLMs) to this challenging domain with Compositional Context Fine-Tuning (CCFT), a method that decomposes assembly actions into semantic elements (Verb, Object, Tool) and fine-tunes VLMs to recognize each action element using templated question-answering pairs. This approach ensures near-deterministic outputs. To enable efficient and effective multi-task learning under limited data, a Layer-Partitioned Alternating Training (LP-AT) method is presented, which assigns distinct model layers to recognize specific action elements through element-specific low-rank adapters. LP-AT alternates weight updates across element-specific adapters, reducing cross-task interference while enabling per-adapter hyperparameter optimization. Furthermore, we create HA-ViD-VQA and IKEA-ASM-VQA datasets from existing assembly video datasets. Extensive experiments on these datasets demonstrate that our method consistently outperforms strong action recognition baselines while providing interpretable element-level predictions that can support diverse downstream applications.
Authors: Zehui Guo, Zhen Wang, Junwei Shu, Yang Li, Changbo Wang, Long Chen
Abstract: Editing images with pre-trained text-to-image flow models typically requires carefully balancing target alignment with the desired prompt and source consistency with the original image. Existing approaches either rely on inversion-based pipelines or heuristic source-to-target trajectory constructions, which often depend on architecture-specific designs or are sensitive to hyperparameters. In this paper, we propose h-Flow, a training-free and theoretically grounded flow-based editing framework. Inspired by Doob's $h$-Transform, we reformulate image editing as conditional generation under multiple terminal events corresponding to source consistency and target alignment. We first extend the classical $h$-Transform from SDE-based models to the deterministic RF framework by constructing an equivalent SDE with identical marginals. Within this formulation, we design dedicated $h$-functions for source consistency and target alignment, yielding closed-form reconstruction guidance and velocity-based semantic editing signals. We further introduce a velocity orthogonal decomposition to decouple reconstruction and editing directions, enabling a controllable trade-off between the two objectives. Extensive experiments demonstrate that h-Flow achieves effective, robust, and flexible editing across diverse scenarios. The code will be released soon.
Authors: Zhenyu Zhao, Nanshan Jia, Jihyeon Je, Yifu Tang, Alvin Chan, Michael Spedden, Michael V. Palleschi, Sui Huang, Jingshen Wang, Zeyu Zheng
Abstract: Automated evaluation is essential for scaling generative 3D systems, where exhaustive human review is costly and slow. However, the reliability of an automated judge depends on the entire evaluation pipeline, not only the underlying vision-language model (VLM), but also how assets are rendered, what visual evidence is provided, how the task is specified, and how human reference labels are constructed. We introduce 3D-DefectBench, a benchmark and framework for systematic analysis of VLM-based 3D defect detection pipelines. It complements holistic ratings and pairwise preferences with nine fine-grained binary defects spanning geometry, texture, and prompt adherence, providing actionable diagnostics for generator development and judge evaluation. Using a balanced factorial design, we vary four pipeline factors, VLM, camera protocol, visual input, and prompt schema, across 84 inference designs and approximately 3.2 million scored defect decisions, followed by staged validation on a broader set of frontier models. Model choice is the largest determinant of agreement with human labels, but the remaining factors also affect performance, interact with model selection, and can change the best configuration. Within the evaluated design space, a compact six-view RGB protocol performs comparably to denser multi-view settings and inputs augmented with depth or surface normals, making it a strong cost-effective default. Under this standardized pipeline, the best of 12 VLM judges still lag behind trained human labelers, while texture agreement drops sharply when expert-consensus labels are replaced by noisier silver labels. These findings show that automated judges should be evaluated as complete pipelines and calibrated across human reference regimes, rather than benchmarked only as standalone models. We release labels, prompts, predictions, and Croissant metadata on Hugging Face.
Authors: Yanqin Jiang, Tengfei Wang, Zhengwei Wang, Chenjie Cao, Junta Wu, Wenhan Luo, Weiming Hu, Jin Gao, Chunchao Guo
Abstract: Previous feed-forward 4D reconstruction methods either predict per-frame static point clouds, ignoring foreground motion, or estimate point cloud trajectories while being limited to small camera motions. This restricts their ability to aggregate observations over time and reconstruct complete dynamic scenes under large viewpoint changes. To address this limitation, we propose OmniX, a feed-forward 4D reconstruction framework that predicts dense 3D point trajectories for every pixel from videos with large camera motion. OmniX decouples dynamic motion modeling from static geometry prediction and represents motion using a compact set of dynamic tokens. By leveraging the sparse and low-rank structure of 3D motion, these tokens generate trajectory fields for all pixels across all images while efficiently preserving global interactions. To facilitate training, we further build an automatic UE5-based 4D data engine and introduce a large-scale dataset containing 80K scenes and 1.28M multi-view videos with full geometric annotations. OmniX achieves state-of-the-art performance on dense 3D point trajectory prediction and 3D point tracking, while also demonstrating competitive results on video depth estimation and camera pose estimation.
Authors: Venkanna Babu Guthula, Oswin Krause, Dimitri Gominski, Hui Zhang, Johan Mottelson, Ankit Kariryaa, Nico Lang, Christian Igel
Abstract: Supervised learning for image segmentation typically requires spatially aligned image and label sets. When images and labels originate from different sources, the pairing may be misaligned, which can significantly deteriorate the performance of the learned models. This is especially common in remote sensing, when aerial or satellite images are co-registered with labels from another source (e.g., OpenStreetMap). In this work, we propose a novel approach for training on misaligned labels, where we simultaneously learn the label alignment. Our align and segment (AnS) approach builds on the spatial transformer module to transform the misaligned labels using an affine transformation to provide a better learning target for a canonical semantic segmentation network. We prevent shortcut learning of misaligned labels in these semantic segmentation networks through a self-supervised regularization loss and show that it is complementary to data augmentation, especially for systematically misaligned training data. A decisive characteristic of our AnS approach is that it learns without requiring any golden labels. We experimentally show on both synthetic and real-world data from different cities that our approach enables high-quality building segmentation and precise label-image alignment at the same time. Code and derived datasets are available at https://github.com/venkanna37/align-and-segment
Authors: Tonmoy Hossain, Atiqur Rahman, Farhana Hossain Swarnali, Miaomiao Zhang
Abstract: Medical image classification models are ideally expected to identify diagnostically relevant regions while making predictions, yet standard classification losses rarely provide spatial supervision. Explicit supervision via anatomical shape information, such as segmentation masks of task-relevant anatomy, has been shown to guide the network toward regions relevant to the target prediction. However, obtaining such masks incurs substantial manual annotation effort and computational overhead. With the advent of segmentation foundation models that exhibit strong localization of anatomical structures across diverse imaging modalities, we leverage this capability to extract anatomical shape priors without the burden of training a dedicated segmentation model. In this paper, we propose a new framework, Locus, an anatomical attention regularization framework that leverages pretrained segmentation foundation models to guide a classifier's attention toward diagnostically meaningful anatomical structures across diverse imaging modalities. Instead of enforcing pixel-wise alignment with the foundation-model-derived mask, we introduce a regularization term that adaptively balances attention between anatomical (foreground) and background regions, penalizing the classifier when background attention dominates. We validate Locus on eight diverse medical imaging datasets spanning dermoscopy, X-ray, histopathology, and cardiac MRI, showing consistent gains in classification performance alongside improved anatomically grounded attention.
Authors: Peizhuo Li, Emre Aksan, Alexandru-Eugen Ichim, Thabo Beeler, Olga Sorkine-Hornung
Abstract: Diffusion models faithfully reproduce their training distribution, but also inherit its imbalances and leave rare or under-represented modes hard to reach. A natural inference-time remedy is to sample from the high-temperature target $p^{(\gamma)}_0(x) \propto p_0(x)^{\gamma}$ for $0 < \gamma < 1$, which flattens dominant modes and lifts rare ones. However, naive score scaling while correctly reweighting modes also inflates the per-mode variance, breaking the reverse diffusion process and degrading sample quality. We introduce variance-corrective time shifting, a training-free fix that queries the network at a shifted timestep and scales the resulting score by $\gamma$, canceling the variance inflation while preserving the mode reweighting. The correction turns simple temperature sampling into a practical diversity knob for pretrained diffusion and flow-matching backbones with no retraining, and we demonstrate consistent gains at minimal cost to sample quality and condition fidelity across DiT, Stable Diffusion and Motion Diffusion models. We further show that the timing of the temperature intervention enables coarse-to-fine control: high-noise stages drive compositional diversity across modes, while low-noise stages drive local appearance variation under a fixed composition.
Authors: Pei-Sze Tan, Sailaja Rajanala, Yee-Fan Tan, Raphael C. -W. Phan, Huey-Fang Ong
Abstract: Micro-expression recognition is limited by the small scale, narrow demographic coverage, and restricted emotion labels of existing datasets. We introduce EquiME, a synthetic micro-expression dataset built from AU-guided image-to-video generation. EquiME contains 75K videos generated from 15K source face images across five target emotions, together with automatically inferred demographic metadata and video-quality measurements. We evaluate EquiME using frame-pair similarity, spatial variation, and no-reference perceptual-quality metrics, together with cross-dataset MER experiments on SAMM and CASME II. Models trained on EquiME achieve competitive cross-dataset performance on SAMM and CASME II and show comparatively low variation across the four evaluated architectures. This paper focuses on the dataset design, the structured AU-conditioning pipeline used for video generation, and the empirical evidence needed to assess EquiME as a synthetic MER resource. Project page: https://kirito-blade.github.io/me-vlm/
Authors: Mingxu Liu, Zixuan Liu, Ruchen Cai, Yu-Chen Ku, Suxi Gu, Amit Jain, Alejandro Martin-Gomez, Mehran Armand
Abstract: Achieving optimal screw placement for orthopedic surgeries requires frequent alignment checks and multiple anatomical views under X-ray -- a process known as "fluoro-hunting" that increases radiation exposure to patients and surgical teams. This work introduces X-GuideAR, an augmented reality (AR) framework for identifying optimal X-ray views, aimed at reducing radiation exposure while ensuring accurate screw placement. To exemplify the benefits of X-GuideAR, we focus on S2 alar-iliac (S2AI) screw placement. Our system provides radiation-free guidance for view acquisition and drilling by generating synthetic X-ray previews that accelerate fluoro-hunting. Once the required anatomical views are identified using these previews, a real X-ray is acquired, and the preview of the drilling trajectory is augmented onto it, facilitating precise screw placement with minimal additional radiation. A preliminary study involving eight S2AI trajectories performed by an expert spine surgeon demonstrated a 62.3% reduction in the number of X-rays. Post-procedure evaluations showed that trajectories done with X-GuideAR supported an average safe screw diameter of 12.95 mm compared to 5.9 mm under the conventional workflow, suggesting improved bony containment and potential biomechanical benefit. X-GuideAR shows great potential to reduce radiation exposure and streamline S2AI screw placement, offering a promising direction toward safer and more efficient surgeries.
Authors: Nadja Gruber, Lukas Neumann, Ander Biguri, Gyeongha Hwang, Markus Haltmeier, Johannes Schwab
Abstract: Self-supervised data splitting has emerged as a promising paradigm for sparse-view CT reconstruction, enabling training from incomplete measurements without fully sampled ground truth. However, the influence of key design choices, including partitioning strategy, preprocessing, and inference, remains insufficiently understood. In this work, we introduce a unified framework that decomposes splitting-based reconstruction into these three components, enabling controlled comparison of existing methods and two incremental extensions: multi-partition splitting and an alternative inference strategy. Experiments on simulated LoDoPaB-CT data under independent and correlated noise, together with validation on the real-world 2DeteCT dataset, show that the optimal partitioning strategy strongly depends on the measurement noise structure. Lattice-based splitting performs favorably under independent noise, whereas angular masking is more robust under correlated noise and real measured data. Multi-partition splitting consistently improves over pure projection-wise splitting in several settings. Complementary perceptual and structural metrics, including LPIPS and HaarPSI, reveal differences between masking strategies that are less apparent from PSNR and SSIM alone. These results provide practical guidelines for designing self-supervised sparse-view CT reconstruction methods and highlight the limitations of common independence assumptions in realistic imaging environments.
Authors: Aqi Dong
Abstract: 3D Gaussian Splatting represents scenes as finite mixtures of anisotropic Gaussians whose number of components $K$ is set by heuristic density control or user caps. Variational Bayes Gaussian Splatting (VBGS) recast splat fitting as conjugate variational inference, but $K$ remains fixed. We replace the finite symmetric Dirichlet over mixture weights with a truncated stick-breaking Dirichlet-process prior -- and, as a theory-backed alternative, a sparse overfitted finite Dirichlet -- so that the number of occupied components adapts to the data while every update remains a closed-form coordinate-ascent step; a natural-gradient stochastic variant makes the per-step cost independent of the number of points. We give an exact monotonicity guarantee, a rigorous truncation-error bound correcting an anti-conservative large-$\alpha$ approximation in common use, and an honest account of what the fitted number of components estimates. Empirically: (i) the effective complexity $\hat{K}$ adapts to scene complexity and recovers the true $K$ within $\pm 1$ on well-separated synthetic data with regime-appropriate concentration; (ii) a deconfounded comparison shows the DP prior's contribution is complexity selection, not per-component efficiency -- converged DP fits exceed single-pass fixed-$K$ VBGS by +2.7 dB at matched budgets yet tie an equally converged fixed-$K$ baseline, and on 3D scenes DP-Splat matches or exceeds VBGS's held-out color prediction with 5.9-7.6x fewer components; (iii) the posterior-predictive color variance is well calibrated on model-matched synthetic data; and (iv) the ordering suggested by exact-posterior asymptotics reverses under mean-field coordinate ascent: the DP prior resists over-splitting while the sparse finite mixture saturates its truncation, a gap between variational practice and posterior asymptotics documented across three orders of magnitude in $N$.
Authors: Parikshit Singh Rathore, Vishwajeet Pattanaik, Punit Rathore
Abstract: Turning movement counts are essential for intersection-level traffic management, yet their collection remains predominantly manual due to the cost of per-camera region annotation. This paper presents an unsupervised pipeline that identifies entry and exit regions directly from raw vehicle trajectories extracted via object detection and multi-object tracking, requiring no manual annotation, camera calibration, or prior knowledge of intersection geometry. Unlike trajectory clustering methods that classify individual trajectories using pairwise similarity and must be re-executed on every new batch, the proposed pipeline clusters initial and terminal point locations to produce persistent spatial region polygons that classify future trajectories by point-in-polygon containment at linear cost. The pipeline comprises six sequential steps, each with configurable parameters evaluated through a systematic statistical analysis spanning 19,152 pipeline executions across 25 surveillance cameras capturing dense heterogeneous traffic in Bengaluru, India, and 10 sequences from the UA-DETRAC benchmark dataset. Both parametric and nonparametric testing frameworks identify three consistently significant parameters and yield an empirically grounded recommended configuration. Under this configuration, the pipeline achieves a median classification error of approximately 3% across all 25 cameras, including 16 held-out locations, with GEH values within accepted engineering thresholds. Compared with two trajectory clustering baselines, the proposed pipeline exhibits greater stability across camera views and lower computational cost, at the expense of higher median error. Extended evaluation demonstrates that calibration clips of at least 60 minutes and peak-traffic selection further improve region estimation quality.
Authors: Guoliang You, Hongming Li, Yuanwang Zhang, Yong Fan
Abstract: Medical vision-language pretraining (VLP) from paired CT images and radiology reports enables scalable representation learning, but most existing methods align either whole scans with entire reports or local image regions with text fragments. These formulations underuse a key property of radiology reports: findings are organized around anatomical structures, with abnormalities described by organs, disease concepts, locations, and severity-related attributes. We propose OKA-CT, an organ-hierarchical knowledge-augmented framework for CT-report VLP. OKA-CT first converts free-text reports into organ-conditioned knowledge using radiology report parsing and LLM-assisted semantic structuring. The extracted hierarchy is used across two learning stages. Stage~1 injects anatomy-grounded evidence into the CT visual representation through fine-grained organ-conditioned supervision, while Stage~2 uses organ-specific report evidence to guide structured report-CT contrastive learning, where hierarchy-derived semantic soft targets treat non-paired cases with shared organ-level findings as weak semantic positives rather than uniform negatives. A lightweight query-based global branch further aggregates disease-relevant volumetric evidence for whole-scan representation. On CT-RATE and RAD-ChestCT datasets, OKA-CT achieves zero-shot abnormality diagnosis AUROCs of 84.9 and 72.2, outperforming prior CT VLP baselines. Retrieval and patch-occlusion analyses further show improved report-image alignment and stronger sensitivity to disease-associated anatomical regions.
Authors: Cecilia Curreli, Florian Hofherr, Dominik Muhle, Abhishek Saroha, Riccardo Marin, Daniel Cremers
Abstract: Existing Stochastic 3D Human Motion Prediction models are fundamentally constrained by hard-coding the skeleton kinematics, severely limiting generalization, preventing cross-dataset training, and requiring complex data retargeting. We introduce EquiFusion, the first kinematics-agnostic model to solve this bottleneck, implementing a latent diffusion model with a permutation equivariant architecture. EquiFusion treats the kinematics' connectivity as an explicit input parameter, ensuring its internal computations are inherently agnostic to joint ordering and graph structure. This novel design enables truly cross-dataset generalization to unseen kinematics and unlocks novel zero-shot directions, such as motion prediction from partial or occluded observations and targeted limb generation. EquiFusion achieves state-of-the-art results on major benchmarks, being up to 75% more compact than previous kinematics-specific methods, while achieving faster training and inference. EquiFusion thus establishes a new, flexible standard for robust human motion prediction. Model and training code are available at https://ceveloper.github.io/publications/equifusion/.
Authors: Zheng Zeng, Deepak Sridhar, Nuno Vasconcelos
Abstract: Vision-language models (VLMs) such as CLIP enable zero-shot classification by comparing image features with text prompts in a shared embedding space. A fundamental property underlying this capability is the global comparability of logits across arbitrary candidate classes. However, VLMs are often adapted to fine-grained domains using techniques such as LoRA. While this improves in-domain accuracy, out-of-domain accuracy degrades. This leads to a highly fragmented model ecosystem, with thousands of specialized models. Multi-Expert-Domain classification seeks to address this problem, by merging LoRAs trained independently on specialized domains. However, due to the independent training, the various domain experts no longer produce globally calibrated logits. As a result, when evaluating over the union of multiple domain-specific class sets, heterogeneous logit scales induce cross-domain interference and artificially high confidence for out-of-domain classes, inducing prediction errors. In this work, we identify domain supervision and cross-domain logit miscalibration as the key issue to scalable multi-domain zero-shot recognition. We propose MED-DSLC, combining domain supervised training and domain-wise logit scaling, to explicitly restore global logit comparability. MED-DSLC is a lightweight solution for MED classification, which is shown to preserve within-domain discrimination while reducing cross-domain logit interference with minimal data. Extensive experiments across diverse fine-grained benchmarks demonstrate that it substantially improves mean accuracy (+15\%), cross-domain robustness, and scalability in the size of MED classification problem. Our results show that restoring output-level calibration is essential under highly data imbalanced settings for achieving a truly zero-shot VLM under multi-domain specialization.
Authors: Youngung Han, Induk Um, Kyeonghun Kim, Junga Kim, Hyunsu Go, Jaewon Jung, Woo Kyoung Jeong, Won Jae Lee, Pa Hong, Ken Ying-Kai Liao, Hyuk-Jae Lee, Nam-Joon Kim
Abstract: Perineural invasion (PNI) is a critical prognostic factor in cholangiocarcinoma. Non-invasive prediction from 3D MRI is challenging, demanding models that efficiently capture both fine-grained details and global context. We propose the Multi-window Mixture-of-Head Attention Transformer (MMA-Former), a novel end-to-end 3D architecture featuring a Coarse-Fine Transformer (CFT) structure for parallel multi-scale feature extraction. We advance this structure by integrating a novel Window-Specific Mixture-of-Head attention (WS-MoH) mechanism. Unlike standard Multi-Head Self Attention (MSA), WS-MoH generates a representation for each 3D window and dynamically routes the entire window to specialized or common attention heads. This enables spatially adaptive feature extraction tailored to the local context of each window, enhancing specialization and reducing redundancy without increasing parameters. Evaluated on a retrospective dataset of 168 T1-weighted MRI scans, MMA-Former achieved an AUC of 0.752, outperforming other 3D architectures, including the best CNN (AUC of 0.708) and Transformer baselines (AUC of 0.681).
Authors: Thanh-Nhan Vo, Thanh-Khoi Nguyen, Trong-Thuan Nguyen, Trung-Hoang Le, Minh-Triet Tran
Abstract: Automated understanding of complex soccer scenarios from video remains a significant challenge for contemporary vision-language models (VLMs), which suffer from shallow cross-modal alignment and exhibit fundamental limitations in multi-step reasoning and coordinated tool integration. We present TreeSoc, a structured reasoning framework that reformulates soccer video question answering as a hierarchical search problem rather than a single-pass prediction. Specifically, TreeSoc employs a dynamic depth-first search (DFS) mechanism that decomposes complex queries into sequentially ordered sub-tasks, enabling iterative reasoning refinement through explicit intermediate states. This tree-structured decomposition naturally supports adaptive tool routing, wherein domain-specific modules are selectively activated and their outputs incorporated at each reasoning node to produce contextually grounded predictions. On SoccerBench, TreeSoc achieves state-of-the-art performance, with accuracies of 85.2%, 87.4%, and 82.2% on TextQA, ImageQA, and VideoQA, respectively. Additionally, TreeSoc further demonstrates strong cross-domain generalization, attaining 74.16% accuracy on NExT-QA. These results establish structured, tool-augmented tree reasoning as an effective paradigm for robust video understanding. Code is available at: https://github.com/thanhnhan29/TreeSoc.
Authors: Youngung Han, Hyunsu Go, Kyeonghun Kim, Induk Um, Junga Kim, Jaewon Jung, Woo Kyoung Jeong, Won Jae Lee, Pa Hong, Ken Ying-Kai Liao, Hyuk-Jae Lee, Nam-Joon Kim
Abstract: Perineural invasion (PNI) is a clinically relevant indicator of tumor aggressiveness and can influence surgical decision-making, motivating interest in reliable preoperative assessment. The subtle MRI features of PNI, however, often resemble nearby anatomy, complicating noninvasive prediction. These fine perineural cues are easily attenuated by routine downsampling or overly global feature aggregation, reducing the effectiveness of conventional volumetric models. We present LoSA-Net, a localized and scale-adaptive architecture for boundary-sensitive PNI prediction in 3D MRI. Talking Neighborhood Attention (TNA) preserves nerve-aligned detail through localized self-attention with head-wise mixing, and Scale-Adaptive Feature Mixing (SAFM) modulates the receptive field using multi-scale depthwise processing. Cross-Scale Refinement and Alignment (CSRA) maintains consistency between semantic context and high-resolution boundaries across stages. In contrast-enhanced MRI scans from 168 patients with cholangiocarcinoma, LoSA-Net achieves an AUC of 0.7567 and outperforms representative convolutional and transformer baselines under matched preprocessing and optimization settings.
Authors: Yi Tang Soon, Jun-Wei Hsieh
Abstract: Foundation models such as CLIP have enabled open-vocabulary object detectors that generalise to novel categories via vision-language similarity. However, the confidence scores these detectors produce are not reliable localization probability estimates: they conflate visual scale and semantic query specificity with the true detection signal. Through controlled experiments on COCO across three foundation-model-based detectors (GroundingDINO, OWL-ViT, YOLO-World), with the scale-bias finding further replicated on LVIS (1,203 categories) using GroundingDINO, we show that s=cos(v,t) is a biased mixture of two effects. Scale bias (alpha = +0.064, r = 0.579, p = 1.29 x 10^-58) systematically inflates scores for large objects. Semantic bias (beta = -0.705, p = 5.23 x 10^-41) suppresses scores for generic queries. Both biases are structurally inevitable from CLIP's image-level pretraining. Threshold adjustment cannot remove them: oracle per-scale thresholding yields Delta F1 = +0.001 for small objects versus +0.102 for large. A parameter-free temperature scaling correction improves small-object Recall@10 by 19.6% (p < 0.01) without retraining. This comes at a modest, measurable cost to pooled-ranking precision, so the bias is partially, not freely, reversible at inference time. These findings reveal a fundamental limitation of adapting image-level foundation models to region-level detection tasks.
Authors: Yingji Zhong, Dave Zhenyu Chen, Fuzhao Ou, Youyu Chen, Zhihao Li, Lanqing Hong, Dan Xu
Abstract: Recent generalizable 3D Gaussian Splatting models have advanced long-sequence novel view synthesis (NVS), but at the cost of substantial redundant computation. We identify that the redundancy can be mitigated based on two observations: (i) high-precision geometry is not strictly required for high-quality NVS; (ii) appearance learning is generally easier than geometry recovery. Motivated by these insights, we propose an asymmetric architecture that decouples geometry and appearance modeling. The geometry branch processes coarse-grained tokens with most of the parameters for multi-view reconstruction, while the appearance branch operates on fine-grained tokens to capture details using significantly fewer parameters. The two branches interact through bilateral connections, enabling mutual guidance for their respective tasks. This task-aware asymmetry reduces the computational redundancy and allocates the computation more judiciously, thereby increasing parameter efficiency and enabling smaller models to achieve strong performance. On 32-view 960P inputs, our model matches optimization-based methods while delivering nearly 800x speedup, and surpasses the zero-shot performance of state-of-the-art generalizable models with markedly fewer parameters and reduced training/inference overhead, achieving an overall efficiency improvement.
Authors: Hao Xu, Xinyu Wei, Sam Wells, Sunil Aryal
Abstract: Precise Event Spotting (PES) requires distinguishing visually similar yet semantically distinct adjacent frames, making it fundamentally different from image classification and coarse action recognition. Although self-distillation methods such as DINO have shown strong representation learning ability in images, we find that directly applying them to PES is ineffective: without supervised guidance, subtle but crucial motion cues are often suppressed as noise, leading to representations that are insensitive to precise event boundaries. To address this, we propose Temporal Feature Distillation, a semi-supervised objective that aligns temporally informative backbone features, rather than projection-head outputs, to preserve motion-sensitive and boundary-aware cues for frame-level localization. A supervised warm-up with a ramp-up schedule further stabilizes training by ensuring that meaningful event cues are learned before unlabeled distillation begins. We also introduce Transformer Gate Shift, a multi-scale gated shifting module that injects motion-aware temporal information into Vision Transformers. Experiments on four fine-grained sports benchmarks show consistent improvements over fully supervised and semi-supervised baselines. Under 10\% supervision on FSPerf, our method improves mAP by 4.54 points over the strongest competing approach, and with only 80\% labeled data, it matches or surpasses the fully supervised 100\% baseline on two of the four datasets.
Authors: Mingjie Xie, Guangjun He, Dongli Xu, Youtian Lin, Hongjue Li, Pengming Feng, Jian Guan, Yue Deng
Abstract: Open-vocabulary dense perception (OVDP) aims to localize objects unseen during training by leveraging textual knowledge. Despite the remarkable progress of recent CLIP-based approaches, we identify a critical limitation: synonym-induced grounding inconsistency, where semantically equivalent expressions yield disparate spatial attention patterns. This inconsistency undermines the robustness and performance of existing methods in real-world OVDP applications. To address this issue, we propose SynCLIP, a Synonym-Coherent Language-Image Pretraining framework that enhances synonym-robust grounding for OVDP. SynCLIP introduces a Semantic-consistent Spatial Attention alignment (SSA) module to enhance spatial attention consistency by minimizing discrepancies between attention maps of original and synonymous expressions. Furthermore, a Spatial Attention Refinement (SAR) module selectively strengthens the most semantically relevant spatial regions within aligned maps for more precise and stable grounding. To support synonym-coherent pretraining, we also construct a Synonym-Enriched Visual Corpus (SEViC), which augments each category with multiple synonyms and textual definitions. Extensive experiments on multiple benchmarks demonstrate that SynCLIP substantially improves grounding consistency under diverse linguistic variants and achieves state-of-the-art performance among CLIP-based OVDP methods. Code is available at https://github.com/Justlovesmile/SynCLIP.
Authors: Varun Ramesh Jois, Antonella DiLillo, James Storer
Abstract: Face super-resolution is the task of increasing the resolution of an image containing a face thereby adding finer detail. It is a ubiquitous task in many computer vision applications and quite often the user isn't even aware that it is being performed. However, doing it with high fidelity is challenging as it is an ill-posed problem. In this paper we present a reference-based solution for face super-resolution that uses higher resolution reference images to aid in the task. We show an alignment module based on the spatial transformer that is considerably more stable than the popular deformable convolutions. We also show an aggregation function that can take good quality information from the reference images when available or suppress the function when such information is unavailable. Finally, we show that our relatively smaller model can achieve state of the art results on multiple datasets. The source code is available at https://github.com/varun-jois/FSRST.
Authors: Varun Ramesh Jois, Antonella DiLillo, James Storer
Abstract: There's been a surge in adoption of video conferencing applications for both personal and business use cases. However, the bandwidth limitations faced by many users worldwide may restrict the optimal use of such applications. Although deep learning offers a solution for enhancing low bit rate videos, most models today are either hard to incorporate with modern compression standards or require specialized hardware to run such as significant GPUs making these models impractical. To address these issues, we introduce the Realtime Face Video Enhancement (RTFVE) model which can be easily incorporated with any video decoder and can run in realtime on ordinary CPUs. Experiments show that our model improves perceptual quality over the compressed video baseline at multiple low bitrate settings. The source code will be made available at https://github.com/varun-jois/RTFVE.
Authors: Varun Ramesh Jois, Antonella DiLillo, James Storer
Abstract: Videocalling has become a popular form of communication in the world today, with many companies providing free services for it. However, there are still millions of people around the world that experience poor quality videocalls due to limitations in bandwidth. This despite, most people having the required hardware. In this paper we present a novel framework for enhancing highly compressed videocalls. We show, that with as little as 10 frames of the face, we can rapidly (in under 100 seconds) train a model to enhance that instance of the videocall. The model can be trained either prior to or during the call, enhancing the rest of the call by producing better quality video. The video conferencing application need not be modified - it can be off the shelf with our system as a layer on top that trains quickly then simply lets the video conferencing application (e.g. Zoom) run as usual, where our system intercepts and improves images before they are displayed. The model is designed to run in realtime on low-compute devices such as a typical laptop CPU. Experimentally, we show that the model significantly improves quality of compressed face video both quantitatively as well as perceptually. Code can be found at https://github.com/varun-jois/FSFVE.
Authors: Doeon Kim, Jungyoon Lee, Seongsin Kim, Seong-heum Kim
Abstract: WiFi Channel State Information (CSI) enables privacy-preserving human pose sensing in camera-denied environments, but existing WiFi-based pose estimators often fail under environment shifts and rely on costly camera-based annotation pipelines that limit scale. We propose WiFi-JEPA, a self-supervised framework that learns CSI-native representations by predicting masked latent embeddings instead of reconstructing raw CSI signals that may contain hardware-specific artifacts. WiFi-JEPA makes three contributions: (i) CSI-specific tokenization and link masking tailored to the CSI tensor over channel, time, and link (C,T,L); masking entire Tx-Rx antenna links forces the model to predict one spatial link view from others, capturing cross-link correlations informative of 3D spatial structure. (ii) A ray-tracing CSI simulation pipeline that generates diverse unlabeled CSI from randomized geometric primitives, providing scalable pre-training data without pose annotations. (iii) State-of-the-art results on Person-in-WiFi-3D: WiFi-JEPA outperforms prior WiFi-CSI baselines on both single- and multi-person 3D pose estimation under the same evaluation protocol. We also show that simulated CSI provides complementary pre-training signal to real CSI, and that four vision-native SSL objectives degrade performance below training from scratch, whereas WiFi-JEPA consistently improves downstream pose estimation.
Authors: Xinye Zheng, Ye Yu, Qiang Lu, Jinsheng Luo, Yiran Cui, Yongbin Cheng
Abstract: Single-image dehazing aims to recover clear scenes from haze-degraded images. It remains challenging due to the atmospheric scattering and the complexity of real-world haze distributions. Although recent end-to-end networks have achieved promising performance, two issues still limit their effectiveness: insufficient feature refinement at the bottleneck stage and weak local structural representation in encoder-decoder architectures. Thus, we propose a Haze-Aware Dual-Domain Refinement Network (DDR-Net) for single-image dehazing. Our method is built upon three modules: Haze Prior Extractor (HPE) provides multi-scale haze-aware priors by operating directly on downsampled hazy images; Detail-Enhanced Blocks (DE Blocks) serve as the core feature extraction units, capturing multi-scale structural information and enhancing edge and texture recovery via gradient-aware convolutions; and Spatial-Frequency Bottleneck Refinement (SFBR) at the bottleneck jointly exploits spatial and frequency information to refine bottleneck features. DDR-Net achieves more effective feature representation and reconstruction for haze removal. Extensive experiments on real-world benchmarks demonstrate that our method outperforms existing dehazing approaches. It achieves competitive performance on synthetic datasets.
Authors: Mohammad Al-Ratrout, Shayla Sharmin, Aditya Raikwar, Roghayeh Leila Barmaki
Abstract: Can a Video Large Language Model (Video-LLM) follow one person through a long video, keeping track of who they are well enough to report, in order, how their outfit changes across a full TV episode? Benchmarks increasingly score this kind of task, and the strongest open-source 7--8B models now reach 37--38% on InfiniBench's global appearance task, which asks exactly that. But does that score come from tracking the named character, or from something easier? We test this with a nine-condition diagnostic protocol applied to three architecturally distinct open-source Video-LLMs, with Gemini~2.5~Flash as a frontier reference, and find the accuracy does not come from character tracking. When we change the character named in the question to a different cast member, leaving the video and answer options untouched, the models change their answer only 4--31% of the time, so they are largely ignoring who the question asks about. Breaking that test down by the gender of the swapped name shows why: the models react more when the name is changed to a different-gender character than to a same-gender one (a 13--28 point gap), picking up coarse gender cues but unable to tell same-gender individuals apart. This shallow processing surfaces again when we drop the multiple-choice options and ask the same questions open-endedly: open-source accuracy drops 18--25 points, with none of 151 answers fully correct, versus a 12-point drop for Gemini. Further checks rule out the obvious innocent explanations, adding subtitles, using the most informative frames, or doubling the number of frames all leave character tracking unimproved, so the bottleneck is not how much video the model sees but how it ties that video to the person the question names. We release a diagnostic toolkit for auditing what such benchmark scores actually measure.
Authors: Sunyoung Jung, Jiwoo Park, Yoonseok Choi, Kyobin Choo, Ming-Hsuan Yang, Seong Jae Hwang
Abstract: Diffusion Transformers (DiTs) have advanced video generation with high-quality, temporally coherent results. However, extending them to motion transfer, which requires following reference motion while aligning with a target prompt, remains challenging due to limited understanding of motion and structure representations within DiTs. We analyze video DiTs at the attention-head level and identify distinct heads specialized for motion and spatial structure. Based on this insight, we propose a head-aware controllable motion transfer framework that requires no parameter updates. Our method refines motion cues from motion-specialized heads via semantic correspondence guidance and preserves structure through selective feature injection. This head-level control not only enables accurate motion transfer but also provides an interpretable foundation for controllable video generation with DiTs.
Authors: Jeongsoo Kim
Abstract: Recently, Vision Transformer (ViT)-based models have exhibited remarkable performance in image super-resolution. However, the quadratic computational complexity of ViTs with respect to spatial resolution severely constrains their efficiency, leading to high latency and massive memory consumption. To alleviate this, various window-based attention mechanisms have been proposed; yet, they inherently compromise the long-range dependency modeling that is the primary advantage of ViTs. To overcome these limitations, we propose the Clustered Unit-level Similarity Transformer (CUST), a novel architecture that efficiently integrates global and local information. Specifically, CUST enables each patch to aggregate and attend to similar patches within a broadened regional scope outside its local window, thereby capturing extensive contextual understanding. Furthermore, it employs overlapping attention windows to capture local dependencies, while explicitly extracting high-frequency details by computing the residual difference between the original features and their downsampled-upsampled counterparts. Comprehensive experiments demonstrate that our proposed model achieves a practical balance between computational efficiency and restoration performance. It achieves a lower memory footprint and faster inference speed compared to recent global context or lightweight models under realistic constraints. Code is available at [https://github.com/jwgdmkj/CUST].
Authors: Mohammad Mohammadi, Sina Honari, Stavros Tsogkas, Tristan Aumentado-Armstrong, Michael S. Brown, Iqbal Mohomed, Konstantinos G. Derpanis, Alex Levinshtein, Igor Gilitschenski
Abstract: Raw images inherently suffer from noise due to the stochastic nature of light and sensor hardware imperfections. As real photon counts fall, the ratio of this noise to the signal degrades; consequently, for low-light conditions, robust denoising is especially vital for high-quality results. While recent data-driven methods achieve strong performance, they typically rely on large-scale noisy-clean image pairs that are costly and difficult to collect. Alternatively, parametric noise models can generate synthetic training data, but this necessitates precise camera calibration, which is often impractical for unknown devices. In this work, we propose a camera-agnostic, calibration-free paradigm for low-light raw denoising. We identify that color bias from black-level error is a primary source of performance degradation and causes severe color shifts. To mitigate this, we introduce a bias estimator network that predicts the black-level error as a global feature of the noisy input. We evaluate our approach across the ELD, SID, and LRID datasets, demonstrating superior performance among blind denoisers, particularly in terms of color correction. In many cases, we are competitive with-or can even surpass-methods with stronger supervision. Furthermore, we reveal that the widely used SIDD dataset contains significant color bias in its ground-truth images, which yields unrealistic color reproduction in trained models. We introduce a new ground-truth extraction framework to resolve this issue and provide a benchmark of existing methods on the corrected dataset.
Authors: Kai Li, Xuechao Zou, Jiashen Fu, Zijun Yan, Xintong Wang, Xiaolin Hu
Abstract: The U-Net style models have been widely used in many applications. A critical step in these models is to reconstruct the lower-level features using a top-down decoder. This reconstruction requires precise fusion of high-level semantics and low-level details. Existing attention-based fusion methods typically derive attention weights from the top-down decoder features (global) alone or the correlation between the top-down decoder features and the bottom-up encoder features (local), then modulate the encoder features using these weights. In this work, we explore a different paradigm: deriving attention weights from the difference between the two feature streams. To this end, we propose two difference-based gating approaches: Feature-difference gating (FDG), which directly uses the absolute difference between global and local features to generate adaptive gating maps, and Entropy-difference gating (EDG), which measures the representational certainty of each stream via information entropy and uses their signed entropy difference to derive the attention weights. Both methods produce coupled gating maps that simultaneously modulate the global and local features. Experiments on different tasks including medical image segmentation, remote sensing image cloud removal and speech separation showed that both methods outperformed existing attention-based fusion methods, and EDG performed better. The results suggested a new paradigm for multi-scale feature fusion in the U-Net style structures.
Authors: Seungjin Jeon, Jongwoo Lim, Changhee Won
Abstract: In this paper, we propose a training strategy for confidence estimation in omnidirectional stereo, targeting the ambiguous matches that frequently occur in wide-baseline setups. Reinterpreting the matching responses produced by the 3D encoder decoder block, we show that their expectation values provide intrinsic confidence signals. Building on this, our method directly penalizes ambiguous responses without auxiliary heads, multi-pass inference, or additional modules, resulting in more efficient and generalized predictions. Beyond confidence, we introduce swept feature volume resampling, where response features produced by 3D CNNs are resampled using regressed positive matching indices and then processed by 2D CNNs to predict meta-information such as surface normals. This joint learning introduces auxiliary geometric regularization and improves depth coherence by leveraging additional contextual cues during response aggregation stage. Experimental results demonstrate that our approach enhances both confidence estimation and surface normal prediction while maintaining deployment practicality for autonomous mobility applications.
Authors: Zheng Zhang, Hao Tang, Yingying Hu, Zhanli Hu, Jing Qin
Abstract: Low-count Positron Emission Tomography (PET) reconstruction is severely hindered by the dissipative nature of prevailing generative models, where the inherent phase-space contraction leads to the numerical extinction (``wash-out'') of weak but diagnostically critical lesion signals. To overcome this geometric limitation, we propose \textbf{FlowPET}, a physics-informed framework that reformulates reconstruction as volume-preserving transport in a symplectic phase space. By parameterizing the posterior dynamics via a Separable Hamiltonian System, our approach guarantees a divergence-free vector field by construction, theoretically immunizing weak signals against probability mass collapse. To steer this conservative flow, we introduce conjugate boundary conditions based on the Range-Null space decomposition of the PET operator; this strictly enforces data consistency in the range space while confining stochastic uncertainty injection to the unobserved null space. We train the model via symplectic flow matching and perform inference using a symplectic leapfrog integrator. Extensive experiments on BrainWeb, clinical pediatric, and UDPET datasets demonstrate that \textbf{FlowPET} not only surpasses state-of-the-art deterministic and stochastic baselines in SSIM and PSNR but, more crucially, exhibits superior recovery of low-contrast lesions. The results confirm that imposing Hamiltonian structural constraints offers a robust geometric safeguard for medical inverse problems in high-noise regimes.
Authors: Xiuwei Chen, Quanlin Chen, Wentao Hu, Zisheng Chen, Kun Xiang, Zehua Ma, Mingyang Zhang, Jianhua Han, Hanhui Li, Hang Xu, Xiaodan Liang
Abstract: Recent multimodal large language models (MLLMs) have made remarkable progress on fine-grained perception tasks under the "Thinking with Images" (TwI) paradigm by iteratively performing various visual tool operations. However, this paradigm relies heavily on frequent external tool calls and repeated image re-encoding, which leads to substantial computational overhead and inference latency. To address these issues, we propose Beyond the Eye (BEE), a novel implicit visual tool paradigm centered on self-regulated capability. BEE directly incorporates visual tool invocation behaviors into the training objective and encourages the model to develop a self-regulated invocation mechanism. This design enables the model to adaptively balance internal knowledge and implicit tools, avoiding redundant tool usage while substantially reducing inference latency. Specifically, BEE involves a two-stage training process: (1) Formalized Chain-of-Thought (CoT) Supervised Fine-tuning (SFT). We construct CoT trajectories with structured tool slots and mixed invocation states. This stage activates the model's implicit tool representations and adaptive switching capability. (2) Self-regulated Reward-Driven Alignment. To address redundant tool usage caused by ambiguous cognitive boundaries, we first introduce the Net Tool Gain (NTG) metric to quantify this phenomenon. Based on this observation, we further propose a self-regulated reward mechanism. This mechanism penalizes ineffective tool dependency and encourages the model to perform knowledge routing, ensuring that implicit tools are invoked only when the model's internal knowledge is insufficient. BEE achieves state-of-the-art performance in fine-grained visual perception while remaining competitive in general reasoning tasks and achieving substantial gains in inference efficiency.
Authors: Langxu Zhao, Zuan Gu, Tianhan Gao
Abstract: Transparent objects pose a fundamental challenge for depth estimation and 3D reconstruction due to their violation of Lambertian assumptions, leading to severe geometry degradation in downstream tasks. To address this, we propose a novel geometry-guided preprocessing framework \textbf{GHOST} that leverages visual foundation models to transform transparent regions into opaque, structurally consistent representations without requiring downstream model retraining. Specifically, our pipeline utilizes (1) \textbf{TransDINO} and (2) \textbf{TransDecomp} to disentangle masks and transparency physical properties, while (3) \textbf{DAF-Net} recovers surface normal priors to encode geometric curvature. Subsequently, (4) \textbf{GeoSemTransNet} integrates these multi-modal cues to synthesize a texture-rich opaque RGB image that preserves the transparent object's 3D structure. Extensive experiments demonstrate that our method significantly enhances the accuracy of state-of-the-art depth estimation and reconstruction models on transparent objects by restoring essential photometric cues.
Authors: Vikas Kumar, Aditya Mishra, Haroon R. Lone
Abstract: We address ambivalence and hesitancy (A/H) recognition in the ABAW 2026 BAH Challenge: given a short interview video, predict whether the person shows signs of A/H. Our system combines affect-specialised text, audio, and visual representations with a small set of readable linguistic hesitation cues, fused by a reliability gate we call Affective Marker Fusion (AMF), and finished with a simple AP-weighted ensemble at a fixed decision threshold. We also introduce \emph{ASR-erased time}: speech recognisers delete fillers and hesitation pauses from the transcript, but the chunk timestamps keep the time those events took, and sixteen features built from these gaps form the strongest and most independent non-verbal channel we measured (AP $0.718$, correlation $0.11$--$0.36$ with all other members). Across controlled experiments we find three things: cross-modal conflict design does not reliably help on BAH; language is by far the strongest channel while affect-specialised audio is a useful second; and calibration matters more than architecture. Fitting ensemble weights and a threshold on the small validation split overfits: it scores $0.741$ macro-F1 on validation but only $0.690$ on the untouched test set. AP-weighting at a fixed threshold instead reaches $\mathbf{0.731}$ on test.
Authors: Soohan Abbasi, Shahid Munir Shah, Rafia Shaikh, Mahmoud Aljawarneh
Abstract: Recommendation systems help users recommend relevant items from a large collection of choices. Present work on transformer-based sequential recommendation learns user preferences from interaction logs, but it mostly focuses on item identifiers and doesn't fully use the semantic meaning of items. This limitation becomes a major challenge in sparse and cold-start scenarios where historical interaction data is limited. To solve this problem, we introduce SISA-Rec (Semantically Integrated Sequential Recommendation), a transformer-based framework that embeds semantic context directly into sequential modeling. Our approach fuses item ID embeddings with BERT-based text embeddings via a gated fusion module, injects semantic similarity into the self-attention mechanism, and leverages an attention-based aggregation module to construct comprehensive user representations. Finally, a joint learning objective which combines Bayesian Personalized Ranking (BPR) and contrastive alignment loss, aligns the underlying behavioral and semantic spaces. Experiments were conducted on the two highly sparse Amazon Beauty and Amazon Toys \& Games datasets, both having 99.93\% sparsity. The results show that SISA-Rec outperforms state-of-the-art baseline models across all evaluation metrics. Compared with the BERT4Rec \cite{petrov2022systematic}, SISA-Rec improves HR@10 by 16.6\% and NDCG@10 by 10.3\% on Amazon Beauty, and HR@10 by 23.1\% and NDCG@10 by 17.9\% on Amazon Toys \& Games. Cold-start analysis further shows that the proposed model achieves the largest improvements for users with limited interaction historical records. This showcases the value of semantic information when user behavior data is scarce. Overall, the results demonstrate that integrating semantic information into the attention mechanism leads to more accurate and reliable recommendations.
Authors: Ming Deng, Sijin Sun, Xiaochuan Hu, Xing Wu
Abstract: Multimodal anomaly detection benefits from complementary RGB and 3D evidence, yet auxiliary RGB reconstruction is not equally reliable across product categories and class-wise test-time policy selection is usually unavailable. We propose TC-MAF, a base-anchored multi-evidence fusion design that combines a multimodal detector, complementary Dinomaly evidence, and a small cross-modal consistency cue under one fixed pixel-level fusion formula. A lightweight training-dispersion confidence (TDC) term scales auxiliary participation using only normal training statistics. On MVTec-3D, TC-MAF reaches 0.979 image-level AUROC and 0.990 pixel-level AUPRO, achieving the best mean results on both detection and localization among the compared multimodal methods. Systematic ablations show that the fusion structure itself is the dominant factor, while TDC provides a smaller but reproducible calibration gain over no calibration or arbitrary calibration. Additional experiments show that the same design remains effective under a pooled-statistics variant, auxiliary-branch and backbone substitutions, few-shot settings, a missing-3D setting, and cross-dataset evaluation on Eyecandies. Code is available at https://anonymous.4open.science/r/TC_MAF-C3BB.
Authors: Quynh Vo, Phuc Dao, Cong-Duy Nguyen, Thong Nguyen
Abstract: Vision-language models (VLMs) are expected to reason about physical space -- which object is closer, what lies behind what, and how objects are arranged in 3D -- yet they still struggle with such spatial judgments. A natural remedy is to show the model a depth map, but we find that this can make performance worse. We show that depth is not absent: it reaches the language model, but becomes difficult to access for downstream reasoning, while rendered pseudo-depth maps act as noisy auxiliary images that frozen VLMs cannot easily regulate. We propose Depth-Ordinal Prompting (DOP), a training-free method that converts monocular depth into a single question-targeted ordinal text cue at the queried objects, without adding a depth image, training a module, injecting features, or using labels. Our key finding is form dependence: the same depth signal can hurt when shown as an image but help when told as text.Across benchmarks, models, and depth estimators, DOP improves spatial reasoning when pseudo-depth provides reliable object-level ordering and remains largely neutral in strong original-image regimes. It is also competitive with the strongest training-free depth-prompting alternative while being simpler and more targeted.
Authors: Suhaas Garre, Emily Ritchie, Sushant Mehta, Edwin Chen
Abstract: A large share of day-to-day work in professional domains happens inside PDF files: benefits packets, leases, datasheets, clinical guidelines, construction plans. Benchmarks for document AI have generally measured the required capabilities in isolation: OCR, layout analysis, chart reasoning, table QA, document VQA. A high score on any one of them does not necessarily reveal whether a model can answer a realistic question that someone in the field would actually ask about a specific PDF. GDP_pdf is a benchmark built to measure this directly. It consists of question-document pairs authored by working professionals in ten fields, and a candidate question was kept only when at least two frontier multimodal models failed it in a way that mattered: a wrong answer, missed decisive evidence, or a fabricated claim, rather than a superficial difference such as style. Each item comes with a rubric of atomic criteria, so we can report a graded rubric score as well as a strict task-level pass rate, and each item is tagged against a taxonomy of eleven capabilities in three tiers, spanning text extraction and grounding, table and chart comprehension, cross-referencing, spatial reasoning, and abstention on unsupported queries. We evaluated seven frontier models on the 100-item benchmark. The best model passed only 15% of the items and the worst passed 1%. Most errors trace back to a small set of recurring loss patterns: misaligned tables, misread charts, skipped footnotes and exclusions, miscounted floor-plan symbols, scan noise, and amendments that supersede earlier text.
Authors: Alexandre Chapin (LIRIS), Emmanuel Dellandrea (LIRIS), Liming Chen (LIRIS)
Abstract: Deploying object-centric models for real-world scene understanding typically requires complex pipelines to achieve both robust scene decomposition and high-fidelity generation. Recent diffusion-based approaches have improved visual quality, but they almost universally rely on heavy, pretrained generative priors (e.g., Stable Diffusion) and external VAE latent spaces. In this paper, we propose Slot-RAE, a much simpler, fully integrated framework that operates directly within the continuous semantic feature space of visual foundation models (e.g., DINOv3). Slot-RAE employs a feature-space diffusion process using a Diffusion Transformer (DiT) decoder and a Representation Alignment (REPA) head. Unlike existing diffusion-based objectcentric methods that rely heavily on subsidized text-toimage priors, the generative core of Slot-RAE (Slot Attention and the DiT) is trained from scratch within the frozen VFM feature space. This eliminates the need for VAE bottlenecks and task-agnostic generative pre-training. Experiments on the COCO dataset demonstrate that despite its architectural simplicity, Slot-RAE achieves state-of-the-art results. It delivers comparable unsupervised object discovery, higher-fidelity image reconstruction, and robust zero-shot compositionality, all while being significantly faster and more computationally efficient than existing object-centric latent diffusion models.
Authors: Shyam Marjit, Dheeraj Baiju, Anuj Shikarkhane, Akhil Sakthieswaran, Sayak Paul, Anirban Chakraborty
Abstract: Recent advances in text-to-image (T2I) generation have led to models capable of producing highly realistic images. Yet, reliably evaluating their outputs remains challenging, especially at scale. Existing automatic evaluators, often relying on a static prompt set, struggle to capture subtle failure modes such as partial prompt misalignment, compositional errors, or visually plausible but semantically incorrect generations. In this work, we introduce DynEval, a Dynamic Evaluation framework designed to jointly assess text-to-image alignment and image quality of T2I models. To support scalable training beyond limited human-annotated data, we construct two large datasets. First, we build GenDB, a collection of 500K prompt-image pairs generated from human-written prompts drawn from DiffusionDB using a tiered prompt-model generation strategy. Second, building upon GenDB, we construct DynEvalInstruct, a 250K instruction dataset comprising prompt-image-response triplets distilled from a structured evaluation pipeline that decomposes evaluation into text-image alignment and visual quality reasoning. Using this dataset, we perform full fine-tuning of a compact evaluator through a curriculum learning strategy to effectively distill the superior evaluation capabilities of a larger teacher vision-language model, resulting in DynEval-2B and DynEval-4B. In extensive comparisons against existing evaluators across 11 benchmarks, our evaluator achieves a higher overall correlation with human judgments. Furthermore, it provides fine-grained analysis of the capabilities and failure modes of 36 T2I models across 42 subcategories and 9 semantic dimensions.
Authors: Xin Cai, Jiawen Chen, Lars Jebe, Tianfan Xue, Zhoutong Zhang
Abstract: Image matting is highly ill-posed, especially when both the foreground and background are richly textured. While single-image matting methods learn strong priors from data, they often struggle on these challenging cases. Existing approaches improve results by requiring additional signals such as green screens, polarized lighting, or clean background images, but these typically rely on specialized capture setups. We present Parallax Portrait Matting, a practical two-frame matting method that uses a second image captured with slight viewpoint change. Such a setting arises naturally in burst photography, where small camera motion induces foreground-background parallax and provides complementary observations for matting. Our pipeline estimates trimaps and foreground/background motion, then constructs aligned views for prediction. To handle imperfect motion estimation, the network uses the background-aligned pair for direct fusion and the foreground-aligned cue through cross-attention for error compensation. Experiments show that our method recovers finer details and more accurate foreground colors than strong single-image matting baselines on challenging portrait cases.
Authors: Natasha Randall, Gernot Heisenberg
Abstract: Labels are critical for both training and evaluating deep learning segmentation models, but are often inconsistent, noisy, or ambiguous at class boundaries. Many approaches have been developed to support training models on weak labels, but few to none currently exist to facilitate evaluating models on unreliable labels. We therefore introduce a method called "Adaptive Resolution Label Aggregation", or "ARLA", which dynamically adapts the resolution of both the label and the model prediction at inference time before the evaluation metrics are computed. We demonstrate how ARLA can be used to better analyse model behaviour with a practical application to a real flood prediction model, where ARLA was able to overcome issues with inconsistent labelling of forested areas and errors in labels within regions of heavy cloud cover. Our work presents a new approach to evaluating segmentation models, with adjustable parameters to adapt the aggregated resolution to the precision of the label or the level of label noise. Fundamentally, ARLA exploits the information encapsulated by a label but minimises the label error, extracting from the noise a clearer signal of a model's true performance.
Authors: Mingxi Xu, Bowen Duan, Yi Gu, Zhengyang Shen, Renjing Xu, Yutao Yue
Abstract: Accurate monocular 4D hand reconstruction remains challenging. Per-frame discriminative regressors lack temporal context and often produce jittery predictions. Temporal models improve consistency by aggregating information across frames, but they are typically deterministic regressors, making them vulnerable to ambiguous observations caused by occlusion and motion blur. Generative modeling offers a natural alternative by learning a prior over plausible hand motion sequences, enabling coherent hand-state recovery when visual evidence is incomplete or unreliable. Motivated by this observation, we present HandFlow, a fully generative flow-matching framework for temporally coherent 3D hand pose and shape estimation from monocular video. Given visual and skeletal observations, HandFlow denoises an entire temporal window of MANO parameters through a single ODE integration. To support this, we use a Flux-style dual-stream transformer that attends across the full sequence to capture long-range dependencies without autoregressive decoding, and a confidence-aware continuous masking mechanism that blends observed features with learnable mask tokens to handle noisy or missing observations. Experiments on DexYCB and HOT3D show that HandFlow achieves state-of-the-art performance, with particularly large gains in world-space accuracy and temporal smoothness. It reduces world-space pose error by over 30% compared with the strongest baseline and achieves the lowest acceleration error among all evaluated methods, while remaining competitive in per-frame pose accuracy. Moreover, on a single GPU HandFlow reconstructs a 150-frame sequence at 47 fps, about 12x faster than the fastest prior video-based method, with reconstruction itself accounting for only a small fraction of the end-to-end latency.
Authors: Lu Yang, Xiaonan Hu, Yanan Li, Daqi Liu, Xiang Bai, Hao Lu
Abstract: Virtual try-on (VTON) is a bi-conditional image generation problem that requires not only accurate person preservation but also faithful garment deformation and detail synthesis. Diffusion-based VTON methods can jointly model these factors in a compressed latent space, but suffer from high-frequency detail loss due to inherent latent compression, even with costly multi-step denoising. Recent visual autoregressive (VAR) models offer a promising alternative for high-quality generation with faster inference, yet remain unexplored for VTON due to the lack of effective bi-conditioning mechanisms. To bridge this gap, we first introduce VAR-VTON, a VAR-based VTON model that incorporates garment conditioning and structural guidance for efficient latent-space VTON. Despite its efficacy, latent-space generation still struggles to preserve fine-grained garment details. We argue that different VTON sub-tasks should be addressed in different representation spaces: structural synthesis such as garment warping and person layout is suited to the latent space, whereas fine-grained detail recovery should be tackled in the pixel space. Motivated by this insight, we further propose STAR-VTON, a Two-Stage AutoRegressive framework that builds upon VAR-VTON by decoupling latent-space structural synthesis from pixel-space detail recovery. Our idea is to resort to a matching-informed refiner to establish dense correspondences between the stage-one generation and the source garment to directly map fine-grained pixel-space details. Extensive experiments show that STAR-VTON achieves an impressive efficiency-fidelity trade-off: VAR-VTON runs at least $4\times$ faster than diffusion-based counterparts without degrading quality, and the pixel-space refiner effectively restores fine details and acts as a plug-and-play module that can benefit existing VTON approaches.
Authors: Vincenzo Lavorgna, Martina Pulcinelli, Andrea Polimadei, Rosaria D Amato, Carlo Massaroni, Michele Arturo Caponero, Emiliano Schena, Daniela Lo Presti
Abstract: Distributed optical fiber sensing (DOFS) combines the advantages of fiber optic sensors, including flexibility, small size, immunity to electromagnetic interference, and high metrological performance, with the capability to transform a single optical fiber into a continuous sensing element for spatially resolved mechanical measurements. Optical frequency domain reflectometry (OFDR), based on Rayleigh backscattering, enables high spatial resolution DOFS measurements, broadening the range of potential sensing applications. However, OFDR based DOFS remains largely unexplored for biomedical applications, despite the need for sensitive, spatially resolved, and conformable sensing interfaces. This study presents a soft DOFS based mat as a large-area interface for physiological monitoring. A single-mode optical fiber was embedded in a flexible silicone matrix and arranged in a serpentine layout to distribute sensing over the mat surface. With a gage pitch of 2.6 mm, the system provided 2250 sensing sites across the active area at a sampling frequency of 50 Hz. The mat was assessed on six healthy volunteers in a seated nearable configuration on the backrest of a standard office chair. The distributed output enabled two dimensional mapping of the mat response, reflecting back mat mechanical coupling and cardiorespiratory induced perturbations. Respiratory rate and heart rate were therefore estimated and compared with a reference wearable system. The maps revealed physiologically coherent spatial and temporal patterns, while the estimated rates showed good agreement with the reference measurements. These results demonstrate the feasibility of combining large area distributed sensing, spatial mapping, and quantitative cardiorespiratory monitoring within a DOFS based soft nearable interface.
Authors: Gangsu Kim, Won-Ki Jeong
Abstract: Pathology Foundation Models (PFMs) offer powerful Whole Slide Image (WSI) representations but suffer from massive computational costs. While Knowledge Distillation (KD) can create efficient student models, existing multi-teacher methods often use suboptimal uniform weighting that ignores tissue heterogeneity. We propose LaGuadia (Language-Guided Adaptive DistillAtion), a framework that develops a compact pathology image encoder by dynamically integrating expertise from multiple PFMs under clinical linguistic guidance. Our approach utilizes a multi-stage pipeline: first, extracting visually observable clinical keywords from pathology reports; second, aligning visual features with these keywords via a Vision-Language meta-teacher (MedSigLIP) to provide dense semantic guidance; and finally, performing adaptive KD where teacher contributions are weighted based on their semantic alignment with the clinical narrative. Experiments on WSI captioning, visual question answering, and slide-level classification tasks demonstrate that an 87M parameter LaGuadia student model matches or exceeds foundation-scale models such as GigaPath and UNI, achieving strong factual consistency and robust generalization. These results highlight clinical language as an effective semantic anchor for building efficient and reliable digital pathology systems. Code is available at https://github.com/hvcl/LaGuadia.
Authors: Jijie Li, Jiankuo Zhao, Xiangyu Zhu, Zhen Lei
Abstract: Hairstyle transfer aims to synthesize a photorealistic portrait by transplanting the hairstyle from a reference image onto a source subject while preserving the source identity. Recent foundation models show strong generative capability, but they struggle with the zero-shot disentanglement required for precise local editing, often entangling the reference hairstyle with its original identity and pose. Existing diffusion-based pipelines typically decompose the task by first generating a "bald" image from the source and then injecting hairstyle features from the reference. However, we show that this paradigm suffers from a fundamental leakage problem. Identity Leakage in Hairstyle occurs when hairstyle features retain reference identity or pose information, while Flaw Leakage in Bald arises when residual artifacts in the bald image are propagated into the final synthesis. To address both issues, we propose the Dual-Purification Framework (DPF), which introduces two complementary training-time regularizers. Adversarial Hairstyle Purification (AHP) purifies hairstyle features by suppressing identity predictability under a mutual-information-inspired adversarial objective. Contrastive Geometric Purification (CGP) regularizes the ControlNet pathway with a contrastive objective, reducing the model's reliance on geometric artifacts in the bald condition. By jointly purifying the hairstyle representation and geometric pathway, DPF achieves high-fidelity, identity-preserving hairstyle transfer and state-of-the-art performance on diverse benchmarks.
Authors: Tianyu Xiong, Rui Li, Suning Ge, Jiaqi Yang
Abstract: Reconstructing 3D scenes from unordered images remains bottlenecked by expensive Structure-from-Motion (SfM) preprocessing and frozen pose interfaces. We present SalientGS, a unified SfM-to-3D Gaussian Splatting (3DGS) pipeline. Its central contribution is importance-guided Markov Chain Monte Carlo (MCMC) Gaussian allocation, which aggregates multi-view residuals into per-Gaussian underfit and redundancy signals. These signals define a smooth importance-weighted sampling distribution that biases both birth and relocation toward underfit regions. This reallocates capacity from well-fit areas without altering the underlying stochastic gradient Langevin dynamics (SGLD). SalientGS achieves end-to-end reconstruction in 15 minutes with state-of-the-art perceptual quality. The supplementary material provides dedicated sections for Per-Scene Qualitative Comparisons and Per-Image Learned Perceptual Image Patch Similarity (LPIPS) Analysis, including failure cases. Code and evaluation scripts are available at https://github.com/Six-Bit-TX/SalientGS.
Authors: Pooya Mohammadi Kazaj, Leo Fridolin Weber, Wen Xie, Seyed Amir Ahmad Safavi-Naini, Anselm Stark, Giovanni Baj, Ali Mokhtari, Toshiya Yoshida, Christoph Ryffel, Taishi Okuno, Yoshihiro Akashi, Ronny R. Buechel, Thomas Pilgrim, Waldo Valenzuela, George C. M. Siontis, Xiaowei Xu, Moritz Hundertmark, Stephan Windecker, Christoph Grani, Isaac Shiri
Abstract: Comprehensive quantification of cardiac structures from computed tomography (CT) remains limited not by data availability but by the scalability of measurements, which makes routine use impractical. Here we present a unified framework for comprehensive cardiac CT segmentation and phenotyping that combines a human-in-the-loop annotation pipeline, a cardiac CT augmentation technique, and a self-supervised foundation model pre-trained on 60,000 unlabeled cardiac CT scans. Using this approach, we assembled the largest and most comprehensive expert-annotated cardiac CT segmentation dataset to date, comprising 1598 cases and 14 distinct cardiac structures (1000 for training, 598 for the external test set). Across five external datasets, the framework segmented all structures more accurately and comprehensively than existing open-source tools. Self-supervised pre-training improved labeling efficiency, with the most significant gains observed during external evaluation in the low-data regime. Benchmarking across convolutional, transformer, and state-space architectures showed comparable performance, indicating that data quality and pre-training, rather than architecture, drove accuracy. The framework was scaled to population-level phenotyping, with segmented anatomy that carries functionally relevant information about ventricular function and disease severity beyond demographic variables. By openly releasing the largest dataset with human labels, code, model weights, a CT augmentation library, and software, this work provides a reproducible foundation for opportunistic cardiac phenotyping from routinely acquired CT scans.
Authors: Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez, Natalia Glazman, Paul Wright, Mehmet Yigitsoy, Sebastien Ourselin, Jorge Cardoso
Abstract: Magnetic resonance imaging exhibits substantial acquisition variability, where identical anatomy can appear markedly different across scanners and imaging protocols. Consequently, learned representations entangle biological structure with acquisition-dependent appearance, limiting interpretability, generalisation, and clinical deployment. We show that these sources of variation can be separated by jointly modelling MRI images and DICOM metadata. Using large-scale clinical brain MRI data, we learn representations that separate anatomical structure from contrast-dependent appearance. Resulting contrast representations organise heterogeneous acquisitions, support sequence understanding, and detect image--metadata inconsistencies, whereas anatomical representations suppress acquisition-specific variation while preserving biologically relevant information. Building on these disentangled representations, we introduce a unified anatomy-preserving harmonisation model for cross-modality and cross-site adaptation, conditioned on image or acquisition metadata. Our findings suggest that acquisition variability is a structured component of the imaging process that can be modelled, audited, and controlled, providing a foundation for acquisition-aware representation learning in large-scale medical imaging.
Authors: Baofeng Jia, Xiaoyu Chen, Jingyuan Zhang, Zongze Wu, Haochen li, Jing Han, Lianfa Bai
Abstract: Event cameras offer microsecond-level temporal resolution and high dynamic range for low-altitude UAV perception. However, long-range UAVs often produce sparse, fragmented, and noise-contaminated event responses, where one semantic target may appear as multiple spatially separated blobs. Direct blob-level asynchronous tracking therefore suffers from duplicate trajectories and unstable identities. We propose ASUMOT, a motion-consistency-based asynchronous UAV detection and tracking framework operating directly on raw events. ASUMOT models each UAV as a set of motion-consistent event blobs. A local motion-consistency estimator triggers reliable candidates, a lightweight multi-task verifier provides UAV confidence and motion-direction cues, and motion-consistency clustering aggregates fragmented blobs into identity-consistent UAV tracks. We also introduce ES-UAV, a high-definition event-level UAV benchmark with dense semantic annotations. Experiments on public UAV tracking data and ES-UAV show that ASUMOT improves the accuracy--efficiency trade-off while preserving asynchronous event processing. Code and Dataset will be released.
Authors: Yudong Yang, Guangzhi Sun, Yixuan Li, Chao Zhang
Abstract: We introduce Skill Learning from Video Memory (SLVMBench), the first benchmark that jointly evaluates whether video large language models (video-LLMs) can learn skills from long video memory and apply them to real-time tasks. SLVMBench presents models with 2-3 hour video streams that contain a tutorial video embedded in a stream of arbitrary irrelevant videos, resembling real-world human learning practices. Video-LLMs are asked to apply the acquired skill to answer real-time questions about an ongoing video. Unlike long-video understanding benchmarks that emphasize passive comprehension and skill-learning benchmarks that rely on short, immediate demonstrations, SLVMBench tests the full pipeline of memorizing and extracting procedural knowledge, as well as transferring it to real-time tasks. Moreover, rigorous human annotations feature sub-second-level temporal calibration, manually engineered questions eliminating common-sense guessing, and collated tutorials to ensure coverage of the required skills. Evaluations on state-of-the-art proprietary and open-source video LLMs show that video-LLMs struggle substantially with learning and applying skill knowledge from videos. Moreover, performance degrades markedly when the skill knowledge is placed within a long video memory. These results reveal a key limitation of existing video LLMs and position SLVMBench as the first benchmark for studying real-time skill acquisition and application from long-context video memory.
Authors: Jimin Xu, Tianbao Wang, Tao Jin, Zhou Zhao
Abstract: Recent text-to-CAD approaches have shown promising results by leveraging large language models, but they often struggle with maintaining structural consistency in complex designs and accurately grounding geometric parameters. To address these issues, we propose HierCAD, a hierarchical text-to-CAD framework that improves both structural reasoning and parameter prediction. HierCAD reformulates CAD generation as progressive reasoning by decomposing CAD construction trees into object-level procedural reasoning and part-level topology reasoning trajectories. To further improve generation fidelity, we introduce a unified Structure Alignment and Parameter Grounding (SAPG) learning strategy. Structure alignment aligns topology reasoning trajectories with their corresponding parametric CAD spans, while parameter grounding mitigates shortcut learning through structure-preserving parameter perturbations and ranking-based supervision. Experiments demonstrate that HierCAD outperforms prior state-of-the-art methods on both CAD sequence generation and reconstructed CAD model evaluation. Our code is available at https://github.com/Collab-Gen/HierCAD.
Authors: Solveig Thrun, Zijun Sun, Suaiba A. Salahuddin, Kristoffer Wickstr{\o}m, Elisabeth Wetzer, Stine Hansen, Robert Jenssen, Michael Kampffmeyer
Abstract: Accurate breast cancer risk prediction from screening mammography is critical for enabling personalized screening intervals and early detection. Recent deep learning methods have shown the value of longitudinal data and explicit temporal alignment. However, existing approaches either perform explicit alignment using a single mammographic view or model multiple views without explicit longitudinal alignment, limiting their ability to exploit the complementary spatial-temporal information used in clinical practice. To address this gap, we propose LMV-Net, a longitudinal multi-view breast cancer risk prediction model that jointly analyzes anatomically complementary CC and MLO views within an explicitly aligned longitudinal framework. We evaluate our approach on the public EMBED and CSAW-CC datasets, comparing it to state-of-the-art breast cancer risk prediction methods. Our model consistently outperforms existing approaches in overall risk prediction performance and across different breast density and cancer subgroups. Importantly, these improvements highlight the potential of longitudinal multi-view modeling to enhance risk stratification, paving the way for future work on personalized screening, earlier identification of high-risk patients, and more efficient screening resource allocation. The code is available at https://github.com/sot176/LMV-Net.
Authors: Miguel Gomez Fernandez, David Castro Boga, Roi Mendez-Rial, Eric Lopez-Lopez
Abstract: Edge deployment is often the preferred solution for industrial machine vision systems when low latency, data security, or limited connectivity are critical requirements. Several frameworks are available to optimise inference on edge devices; however, relatively few studies have systematically compared their inference-time performance under industrial deployment conditions. In this work, we present a comparative study of four widely used approaches for machine vision inference in industrial settings: plain PyTorch, ONNX Runtime, OpenVINO, and TensorRT. The evaluation focuses on inference time, covers several CPU- and GPU-based hardware platforms, and includes both conventional convolutional neural networks and a transformer-based vision model. For the hardware platforms and models evaluated, the results show that OpenVINO achieves the lowest inference time on CPUs, while TensorRT achieves the lowest inference time on GPUs. However, TensorRT does not outperform plain PyTorch for the transformer-based model considered in this study.
Authors: Peng Xia, Junbiao Pang, Muhammad Ayub Sabir
Abstract: Post-training quantization (PTQ) compresses deep neural networks for deployment under limited memory and computational budgets. However, low-bit (i.e., 2-bit or 4-bit) PTQ often suffers from substantial performance degradation. Most existing PTQ methods operate on an unconstrained full-precision (FP) model and primarily address quantization errors through post-hoc reconstruction. We argue that low-bit PTQ accuracy is limited not only by post-quantization error minimization, but also by the quantization-error tolerance of a FP model itself. In this paper, we propose Efficient Tuning Before Quantization (ETBQ), a pre-conditioning tuning stage for Stochastic Gradient Descent (SGD)-optimized models before PTQ. During tuning, the FP model is optimized under perturbations sampled from the error distributions of weight and activation quantization, guiding the model toward a loss-landscape region that is less sensitive to the subsequent PTQ. Unlike QAT, ETBQ does not train a fake-quantized deployment model, which is computationally and memory intensive. Instead, ETBQ outputs a FP model that can be used by any PTQ backend. Experiments on CIFAR-100, Tiny-ImageNet, ImageNet, and Cityscapes provide consistent evidence that ETBQ improves low-bit PTQ across diverse tasks. Under W2A4 settings, e.g., ETBQ improves over naive PTQ by 2.14\% top-1 accuracy on Tiny-ImageNet and by 5.80\% mIoU on Cityscapes. Code is available at https://github.com/xpxpxp2001xpxpxp/ETBQ.
Authors: Leon-Friedrich Thomas, Mikael \"An\"akk\"al\"a, Antti Lajunen
Abstract: Although self-supervised learning (SSL) offers a promising way to reduce annotation effort in close-range remote sensing, its effectiveness for high-resolution multispectral unmanned aerial vehicle (UAV) imagery remains underexplored due to limited data. This study evaluated SSL pretraining for precision agriculture using cm-scale multispectral drone imagery collected across multiple sensors, years, and regions. Transformer-based encoders were pretrained with Momentum Contrast v3 (MoCo-v3) and Masked Autoencoders on a harmonized dataset combining msuav500K with newly collected multi-year UAV imagery from agricultural fields in Finland. Pretraining used four spectral bands (Green, Red, Red-Edge, Near-Infrared) for cross-sensor compatibility. The models were evaluated on crop-weed semantic segmentation using the WeedMap dataset with 5--100% training data. The following two subsets served as downstream tasks: Task A (Germany, RedEdge-M), where all pretrained models were compared under partial and full fine-tuning, and Task B (Switzerland, Sequoia), where the best encoder from Task A was assessed. Our Swin Transformer pretrained with MoCo-v3 achieved the strongest performance on both tasks, surpassing the Swin Transformer model of Doornbos et al. pretrained on a pre-release of msuav500K. Our pretrained Swin Transformer further demonstrated cross-sensor and cross-region generalization. We additionally provide a public multi-year multispectral UAV dataset from Finland to support future research.
Authors: Ritu Yadav, Andrea Nascetti, Yifang Ban
Abstract: Earth Observation regression tasks such as building height, canopy height, and above-ground biomass estimation underpin critical applications in urban planning, forest monitoring, and climate policy, where both accuracy and reliability are critical. Yet most deep learning models yield only deterministic predictions, providing no indication of per-pixel reliability. These regression tasks are inherently challenging due to heterogeneous land surfaces, skewed target distributions, sensor noise, and signal saturation at high target values, making uncertainty (UC) estimation essential for reliable inference. We address this gap by modeling aleatoric uncertainty using year-long Sentinel-1 SAR and Sentinel-2 MSI time series, proposing two complementary approaches: (i) Gaussian UC, which jointly predicts mean and standard deviation under a Gaussian assumption, and (ii) Quantile UC, which estimates the 10th, 50th, and 90th quantiles to capture asymmetric and heteroscedastic error distributions. Both models are evaluated on three representative EO regression tasks at 10 m spatial resolution. Results show that both approaches match or surpass deterministic benchmarks and existing global products, while delivering well-calibrated, interpretable, and operationally useful confidence estimates. Notably, both models outperform the current 10 m state-of-the-art uncertainty-aware model for canopy height estimation. Our implementation will be available at: https://github.com/RituYadav92/EO-Regression-Uncertainty-Estimation
URLs: https://github.com/RituYadav92/EO-Regression-Uncertainty-Estimation
Authors: Joris Voerman, Nicolas Sidere, Jean-Christophe Burie
Abstract: Remote identity authentification using Identification Documents has been a major challenge for several years. DeepFakes advent and the development of AI-guided tools helps fraudsters creating counterfeit ID Documents. Ensuring the authenticity of ID Documents has become a real clue in the seurization of remote authentification. This need is all the more pressing given the increasing digitization of administrative and transactional processes. To ensure widespread accessibility, the system should rely solely on video captured via mobile devices. In this specific context, confirming the authenticity of ID is a real challenge as many security features needs specific device like infrared sensor for instance. Among underutilized but promising security features, holographic printings hold a special place. Difficult to counterfeit, they produce distinctive visual effects according enlightment, making them both detectable in a video captured by a smartphone camera and difficult to imitate. In this paper, we propose a Remote Identity Document Verification System (RIDVS) and an approach based on a video transformer for detecting holograms in simple videos captured by smartphones. Our system is designed for a smartphone-based capture process, followed by a server-side verification. The hologram detection method builds on a robust model previously validated in a related research domain. We demonstrate that it outperforms existing SotA methods, achieving near-perfect accuracy even when trained on medium- to small-sized datasets. In particular, we report improvements of +26.86\% in Recall and +17.93\% in accuracy over the best MIDV-Holo baseline. This study includes several experiments that evaluate the model adaptation to frugality, both for training samples and computational resources.
Authors: Hao Kong, Di Liu, Xiangzhong Luo, Shuo Huai, Ravi Subramaniam, Christian Makaya, Qian Lin, Weichen Liu
Abstract: In this paper, we propose TECO, a multi-dimensional pruning framework to collaboratively prune the three dimensions (depth, width, and resolution) of convolutional neural networks (CNNs) for better execution efficiency on embedded hardware. In TECO, we first introduce a two-stage importance evaluation framework, which efficiently and comprehensively evaluates each pruning unit according to both the local importance inside each dimension and the global importance across different dimensions. Based on the evaluation framework, we present a heuristic pruning algorithm to progressively prune the three dimensions of CNNs towards the optimal trade-off between accuracy and efficiency. Experiments on multiple benchmarks validate the advantages of TECO over existing state-of-the-art (SOTA) approaches. The code and pre-trained models are available at https://github.com/ntuliuteam/Teco.
Authors: Fatimah Zohra, Chen Zhao, Shuming Liu, Yahya Al Malallah, Bernard Ghanem
Abstract: Gaussian Splatting has emerged as an effective representation for video, but existing methods rely on per-video optimization. This leads to slow encoding and limits generalization across videos. To amortize this optimization, we propose HyperGS, a feedforward, optimization-free approach that directly predicts Gaussian representations from any video in a single forward pass, speeding up encoding and decoding by orders of magnitude while generalizing to out-of-distribution videos at higher resolutions. In HyperGS, we design a factorized spatiotemporal Transformer to extract tokens from video, and a learnable query-based Transformer to obtain 8-parameter Gaussian representations for each video frame. We find that naively predicting Gaussians across diverse videos induces a needle-like degeneration that collapses training, and address this with a rank-based geometric regularizer whose strength adapts dynamically to stabilize optimization. HyperGS achieves encoding at $10^4$--$10^5\times$ the speed of per-video Gaussian optimization at matched reconstruction quality while generalizing zero-shot to $720p$ video, enabling higher-resolution rendering without re-encoding. HyperGS improves PSNR by +2.9--3.1 dB over the prior video encoders on K400, SSv2, and UCF101 at a smaller video representation size. By predicting explicit 2D Gaussians in a single forward pass, HyperGS combines the fast, flexible rendering of Gaussian Splatting with the speed and generalization of feedforward prediction, advancing Gaussians as a practical direction for fast and generalizable video representation.
Authors: Zihan Nie, Muhao Xu, Wei Feng, Yuan Cui, Hua Wei, Sijie Niu, Yi Wan, Xunbin Wei, Weiye Song, Zongyuan Ge
Abstract: Medical image anomaly detection remains challenging because networks pretrained on natural images often exhibit limited adaptability to medical images, where abnormal patterns appear as fine-grained local shifts, multi-scale contextual mismatches, and orientation-sensitive structural deviations. To address this, we propose the Collaborative Feature Refinement Network (CFR-Net), which combines shared teacher-student feature refinement before decoding with cross-space consistency after decoding. CFR-Net refines frozen teacher features and trainable student features using a Multi-Path Feature Refinement Module (MPFRM) with shared parameters, imposing common multi-path refinement rules on generic visual references and representations adapted to the medical domain, thereby mitigating domain discrepancy while modeling local, multi-scale, and orientation-sensitive feature characteristics. A variance-sensitive objective and dynamic ``homework set'' reorganization further support layer-adaptive consistency learning. Experiments on medical benchmarks show that CFR-Net achieves competitive anomaly classification and strong anomaly localization performance when trained on normal data.
Authors: Gong Sitong, Tianyu Yan, Caixin Kang, Bo Zheng, Xiang Ruan, Huchuan Lu, Kaipeng Zhang, Yoichi Sato, Yifei Huang
Abstract: When should an intelligent assistant speak up without being asked? Continuous egocentric video offers rich, evolving context that enables a new form of assistance: one that is proactive rather than merely reactive. Yet existing approaches either wait passively for user queries or treat every detected event as requiring a response, without considering the user's history, current activity, or whether assistance would actually be welcome. We reframe proactive assistance as a context-dependent decision problem: the agent must not only perceive what is happening, but reason over accumulated temporal context to determine when and whether to intervene. To this end, we present Vinci2, a proactive egocentric assistance system that advances the on-device assistant Vinci from reactive response toward proactivity. On the evaluation side, we present EgoServe, the first large-scale benchmark for proactive assistance in continuous egocentric video. EgoServe comprises over 3,000 service instances organized along 4 temporal memory horizons, ranging from immediate safety alerts to long-term habit coaching, across 10 service categories. On the modeling side, we propose EgoMemo, a training-free, memory-augmented agent that maintains three complementary memory representations: multi-scale temporal summaries, a semantic knowledge graph, and visual embedding archives. At each timestep, EgoMemo performs retrieval-augmented reasoning to determine whether assistance is warranted and, if so, produces contextually grounded responses. Experiments demonstrate that EgoMemo establishes strong baselines on EgoServe while remaining competitive on existing egocentric benchmarks. Our benchmark and code are publicly available at \href{https://sitonggong.github.io/EgoServe-page/}{Vinci2}.
Authors: Yu Qi, Hongyu Li, Shaofei Huang, Tianrui Hui, Yaxiong Wang, Lechao Cheng, Zhun Zhong, Si Liu, Meng Wang
Abstract: In this paper, we tackle the Aerial Vision-and-Dialog Navigation (AVDN) task in the training-free setting for resource-efficient high-altitude UAV navigation.Naively applying MLLMs leads to unreliable navigation due to weak directional grounding and the lack of explicit spatial memory.To address these issues, we propose PSC-AVDN, a training-free framework that tightly couples a three-stage Parsing-Search-Confirmation reasoning pipeline with a Structured Spatial Memory (SSM).The parsing stage uses an LLM to convert ambiguous dialogue instructions into stable geometric directional and destination cues.A Search Chain-of-Thought (S-CoT) then performs stepwise target exploration under high-altitude observations, and a Confirmation Chain-of-Thought (C-CoT) conducts fine-grained verification around candidate regions to resolve visual ambiguity.Meanwhile, SSM integrates three complementary sources of spatial cues, including multi-scale visual observation, spatial visual memory, and structured geometric memory to provide global spatial context and long-horizon consistency.Extensive experiments on ANDH and ANDH-Full show that PSC-AVDN establishes new state-of-the-art performance in the training-free setting, matching or surpassing several finetuned methods.Code will be publicly available at: https://github.com/QY6616/PSC-AVDN
Authors: Youngung Han, Dohyun Kweon, Kyeonghun Kim, Hyunsu Go, Jina Jeong, Suah Park, Induk Um, Junga Kim, Anna Jung, Yului Jeong, Sungha Park, Jinyong Jun, Pa Hong, Woo Kyoung Jeong, Won Jae Lee, Ken Ying-Kai Liao, Hyuk-Jae Lee, Nam-Joon Kim
Abstract: Perineural invasion (PNI) is a critical prognostic factor in cholangiocarcinoma. However, its preoperative prediction from magnetic resonance imaging (MRI) remains challenging due to subtle imaging features that extend beyond tumor boundaries into surrounding regions. Conventional convolutional neural networks are limited in capturing long-range spatial dependencies. Transformer-based architectures improve global modeling of volumetric MRI by aggregating spatially distributed contextual cues, yet capturing subtle and noise-sensitive patterns in peritumoral regions remains challenging. Diffusion-based classifiers offer an alternative formulation by leveraging denoising-based class scoring to better capture such subtle patterns. However, these approaches introduce substantial computational overhead due to the combination of transformer-based modeling and iterative denoising processes. To address these challenges, we formulate PNI prediction as a diffusion-based classification problem and implement the denoising network using a transformer-based representation. To improve computational efficiency, we introduce adaptive routing across attention heads, spatial tokens, and MLP width. Experimental results demonstrate that the proposed approach achieves an AUC of 0.731 with 257.57 GFLOPs.
Authors: Seongjin Choi
Abstract: Spatial football metrics such as pitch control assume access to the positions of all 22 players, yet the most widely available source of positional data -- the broadcast main camera -- shows only 10-16 of them at any moment. We quantify the resulting distortion with an open, reproducible benchmark: a simulated broadcast viewport applied to open full-pitch tracking data (Metrica Sports; three matches, one held out from method development). Ignoring off-screen players -- the visible-only baseline implied whenever a video-based game-state-reconstruction (GSR) pipeline adds no imputation layer -- inflates hidden-zone pitch-control error to 25.1-26.9 percentage points and a mean absolute control-share error of 11.1-13.4 points across the three matches. We then evaluate a ladder of training-free, online imputation baselines that use only observations from the match being analysed. The best overall on these decision-relevant metrics, role-anchored centroid voting (each visible player votes for the full-team centroid by subtracting its running role offset, attenuating the viewport-induced subset bias), roughly halves hidden-zone error (to 12.2-13.8 points) and cuts control-share error to 28-48% of the ignore policy at every viewport width from 36 m to 60 m in all three matches. For occlusions <=9.6 s -- the regime of the closest learned prior work -- it reaches binwise median position errors of 3.3-8.9 m; but 50-57% of hidden-player observations lie beyond that regime. Integrated end-to-end into a broadcast-video GSR pipeline, imputation moves a downstream possession-quality score (Space-Creation Index) by 15.6 and 17.2 points on two real World Cup broadcast windows, flipping the verdict class in one.
Authors: Xuyi Yu, Yaohua Liu, Ziming Song, Yinghai Zhao, Huipeng Zhang, Kuizhi Mei
Abstract: Knowledge distillation (KD) typically relies on the fixed perspective of a single teacher, limiting the diversity of supervisory signals. While multi-teacher distillation addresses this by aggregating knowledge from multiple models, it incurs prohibitive computational and storage costs. To balance efficiency and diversity, recent research has focused on generating virtual views from a single teacher. However, existing methods face a trade-off: random perturbation approaches offer efficiency but lack controlled diversity, while structured augmentation methods require multi-stage training and incur linear parameter growth. We observe that this trade-off stems from a common design choice: using the teacher's strong but static features to generate views. Instead, we propose Shift-Augmented Knowledge Distillation (SAKD), a simple yet effective framework that leverages the student's evolving features as a dynamic condition for perturbation generation. This shift in perspective enables single-stage training while producing adaptive, diverse views through a parameter-free cyclic shift. Extensive experiments on CIFAR-100 and ImageNet demonstrate that SAKD consistently outperforms random perturbation methods and achieves accuracy on par with two-stage approaches, while using significantly fewer parameters and eliminating pre-training requirements.
Authors: Tianyuan Zhang, Zonglei Jing, Jiangfan Liu, Ligong Zhang, Ke Ma, Chengzhi Sun, Xiaohai Xu, Zhirui Zhang, Qianqian Xu, Qingming Huang, Hanyu Fang, Junhua Liu, Zheng Wang, Xiaoliang Liu, Yuanbo Li, Shuai Gui, Bin Wang, Menghe Zheng, Jing Nie, Hanyang Meng, Zeyang Zhang, Xiang Zhang, Yongxuan Zhu, Rui Ding, Hainan Li, Yongkang Zhang, Zhilei Zhu, Xianglong Kong, Jin Hu, Zonghao Ying, Yisong Xiao, Lei Chen, Haotong Qin, Jiakai Wang, Aishan Liu, Ruikai Li, Julia Karbing, Yinpeng Dong, Zhenfei Yin, Shao Jing, Xia Hu, Jingyi Xu, Juntao Dai, Xinyun Chen, Vishal M. Patel, Xianglong Liu, Dawn Song, Alan Yuille, Philip H. S. Torr, Dacheng Tao
Abstract: Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning. This report presents the CVPR 2026@AdvML Workshop Challenge on adversarial multimodal attacks against autonomous-driving VLAs. Built on DriveLM-style multi-view visual question answering, the challenge represents each scene with six synchronized camera images and a structured collection of driving-related question-answer pairs. Participants generate adversarial images and suffix-only textual perturbations that induce model responses to deviate from reference answers while preserving image fidelity and limiting textual cost. The competition comprises two phases, with Phase II adding a hidden black-box model to assess transferability. We describe the task design, submission rules, evaluation protocol, and leaderboard results, and then examine five leading submissions for which technical reports were available. Across these reports, several recurring patterns emerge: image-side attacks are favored by the suffix penalty; scene-level, multi-view optimization is more effective than treating views in isolation; QA types and graph structure provide useful priors for allocating attack budget; feature-space objectives can improve black-box transfer; and typographic content embedded in camera images exposes a persistent vulnerability in driving VLAs. These findings provide a practical reference for future robustness evaluation and defense design in multimodal autonomous-driving systems.
Authors: Yuliang Liu, Zhang Li, Ziyang Zhang, Shuo Zhang, Qiang Liu, Jiajun Song, Zidun Guo, Xinhan Wang, Handong Zheng, Yang Liu, Dongliang Luo, Zhiyin Ma, Jiarui Zhang, Xiang Bai
Abstract: Mainstream visual encoders are pretrained on natural images and cannot be effectively applied to document images without document-oriented adaptation, as dense text and fine-grained character strokes demand character-level visual perception. We present MonkeyOCRv2, a visual-text pretrained model for document AI. First, we construct MonkeyDoc v2, to our knowledge the largest document-image pretraining corpus, comprising 113 million images spanning 17 languages. Second, we propose a pretraining strategy that jointly learns image-to-text generation and pixel-level document reconstruction: the former aligns visual representations with textual content, while the latter preserves character strokes and layout details. Extensive experiments are conducted on five representative document analysis tasks, including text recognition, formula recognition, text detection, document tampering detection, and overlapping text segmentation. Replacing the original encoders with MonkeyOCRv2 consistently improves performance across all five tasks. Finally, we validate its effectiveness as the vision encoder of multimodal large language models on the more challenging tasks of document parsing and document understanding. Kept frozen and paired with a lightweight language model, it yields a 0.7B document parsing model that sets a new open-source state-of-the-art on MDPBench, a recent benchmark spanning digital-born and photographed documents across 17 languages, surpassing the previous best 3B dots.mocr by 2.8% absolute with a vision encoder roughly 11$\times$ smaller. The frozen encoder also powers a document understanding model that outperforms counterparts built on CLIP, DINO, and SAM across eight benchmarks under identical training settings. These results suggest that document-oriented visual pretraining can serve as a foundation for document intelligence in its own right.
Authors: Xin Zhang, Haochen Wang, Yikang Zhou, Jason Li, Robby T. Tan
Abstract: This paper introduces Actor as Its Own Critic, a unified reinforcement learning framework, Cycle Group Relative Policy Optimization (CycleGRPO), that jointly optimizes region understanding and localization for Multimodal Large Language Models (MLLMs). Unlike existing separate pipelines, we leverage the inherent duality between the two tasks to construct a self-evaluating reinforcement learning paradigm: "region $\to$ text $\to$ region''. Specifically, a single MLLM first acts as the actor to generate region captions, then immediately transitions to a critic to ground its generated text back in the spatial domain. Therefore, CycleGRPO requires only region inputs, e.g., masks or bounding boxes, entirely bypassing the need for textual ground truths. A quality-aware token-level cycle-consistency reward is employed to assess the semantic discriminability of text captions via their physical localization accuracy. Empirically, built upon SAMTok, our CycleGRPO framework successfully bootstraps both capabilities simultaneously. Without any task-specific fine-tuning, the framework yields consistent performance gains across a wide range of benchmarks, including region captioning, region VQA, grounded dialogue, and referring segmentation. Overall, CycleGRPO offers a straightforward and scalable way to advance pixel-level capabilities in MLLMs. Code and models are released at https://github.com/devinxzhang/CycleGRPO.
Authors: Chengze Ye, Linda-Sophie Schneider, Yipeng Sun, Andreas Maier
Abstract: This paper proposes a Gaussian-Based Shift-Variant filtered backprojection (FBP) neural network, which is designed for the efficient reconstruction of non-circular trajectory cone beam computed tomography. The traditional differentiable shift-variant FBP model consists of a filtering component and a backprojection process. The filtering component includes operations such as weightings, differentiations, a 2D Radon transform, and a 2D backprojection. The proposed methods build on this framework by introducing a trainable 2D Gaussian model to represent the trajectory-related part in the filtering process, achieving a substantial reduction in the number of trainable parameters. Experimental results demonstrate that the proposed model reduces the parameter count by 99%, while only sacrificing a slight amount of reconstruction quality. Furthermore, the training time for each trajectory is reduced to one-fourth of the original, significantly accelerating convergence. These enhancements demonstrate a considerable augmentation in the model's practicality and effectiveness, making it a valuable asset for real-world applications.
Authors: Muxin Liu, Xiaoyang Lyu, Tianhe Ren, Peng Dai, Xiaoshan Wu, Zhiyue Zhang, Jiaqi Zhang, Jiehong Lin, Shaoshuai Shi, Xiaojuan Qi
Abstract: We present FoundationGeo, a two-stage framework that explicitly bridges relative and metric prediction via spatial calibration and principled data design. Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3 and training on a curated 10.2M-sample multi-domain corpus with complementary local-detail supervision, yielding sharp boundaries and strong cross-domain generalization. Stage 2 moves beyond global scaling by introducing lightweight pixel-wise calibration fields for metric estimation: a scale field for spatially varying metric alignment and a ray-direction correction field that mitigates directional bias in point-map geometry, together producing metrically consistent 3D point maps. Beyond model design, we identify camera intrinsic coverage, especially focal length distribution mismatch between training and test data, as a key bottleneck for zero-shot metric generalization: performance drops sharply when test intrinsics fall outside the training distribution. To address this, we synthesize additional training data across diverse focal lengths using a Blender-based data engine, repairing under-covered focal regimes and improving robustness under intrinsic shift. Extensive zero-shot evaluations across seven benchmarks show that FoundationGeo significantly strengthens cross-domain robustness, staying near the top across diverse domains while avoiding the sharp cross-domain performance drops observed in other methods. This consistency translates into the best overall performance, surpassing heavier baselines by over 5.2% on average.
Authors: Anujaya Vijayakumar, Radu Timofte, Dmitry Ignatov
Abstract: Introduce a MinHash-based similarity scheduling framework that constructs a progressive curriculum over neural architecture code for LLM-based neural architecture search (NAS). Using 128-permutation MinHash signatures over normalised 7-gram source code shingles, we partition the reference pool into similarity bands and present them in increasing architectural heterogeneity, with the best LoRA adapter from each stage merged cumulatively into the backbone. We evaluate the framework on OlympicCoder-7B within the LEMUR benchmark on CIFAR-10 image classification, generating N =15 candidate architectures per epoch across six progressive fine-tuning steps. The curriculum achieves 60% peak success rate at the high-similarity level without post-processing repair. A 2*2 ablation at the most diverse level curriculum versus base model, with versus without partial interface repair reveals that without repair the base model (47% peak SR) substantially outperforms the curriculum model (7% SR), while adding partial repair brings both to 53% SR. This pattern is consistent with merge-level weight drift progressively erasing evaluator-interface priors, and suggests that interface repair and curriculum scheduling target distinct failure modes. We further report a cross-dataset transfer observation on SVHN, where direct base-model generation without curriculum warmup yields 27% peak SR at substantially lower accuracy (60.5%) than the CIFAR-10 equivalent, consistent with the increased synthesis difficulty of the unq-family anchor architecture.
Authors: Bingcai Wei
Abstract: Real-world paired image dehazing remains challenging because haze degradation is spatially non-uniform, illumination-dependent, and physically ambiguous even when haze-free references are available. Existing end-to-end restoration networks usually formulate dehazing as a deterministic mapping from a hazy observation to a clean target, leaving the uncertainty hidden in degraded features, haze priors, and cross-domain negative samples insufficiently explored. In this paper, we propose Backbone-Agnostic Perturbation-Induced Uncertainty Learning (BPUL), a plug-and-play uncertainty learning framework for end-to-end real-world image dehazing. BPUL first introduces a Learnable Perturbation-induced Uncertainty Modulator (LPUM) that estimates channel-wise and spatial-wise feature sensitivity through reparameterized stochastic perturbations. It then develops a Prior-informed Uncertainty-guided Reconstruction Module (PURM), which exploits transmission and atmospheric-light priors to reconstruct the hazy observation from the restored result and enforce degradation consistency. Furthermore, we propose a Dual-space Domain-diversified Distribution-aware Contrastive Loss ($D^3$CL) to regularize both clean restoration and hazy reconstruction spaces with real-world and synthetic negatives. Experiments on five real-world paired benchmarks show that BPUL consistently improves multiple representative backbones. Since only LPUM is retained during inference while PURM and $D^3$CL are used as training-time constraints, BPUL brings substantial restoration gains with only marginal additional inference overhead.
Authors: Ling-Hao Chen, Zixin Yin, Duomin Wang, Xianfang Zeng, Gang Yu
Abstract: This work explores the motion transfer from one video to another, which is crucial in animation for diverse characters. Previously, video motion transfer has been largely explored between human and human-like characters, enabling a lot of applications in digital creation. However, these approaches encounter a main limitation. Specifically, related technical pipelines heavily rely on a predefined human skeleton structure and accordingly require skeleton-conditional model training. On the one hand, these methods are difficult to generalize to diverse characters, such as animals from different species, while preserving their unique motion styles. On the other hand, labeled data in diverse skeletons is limited, which additionally restricts the large-scale training for the task. In this paper, we jump out of the skeleton-based motion transfer framework and propose a training-free motion transfer framework, named Motion4Motion. Motion4Motionmodels the motion flow of the character in a video instead of skeletons, which makes motion transfer across species easier. Extensive experimental results and novel applications show our methods outperform baselines impressively. Project page is available at https://lhchen.top/Motion4Motion.
Authors: Haidong Wang, Hengxing Cai, Wanlei Li, Xiaogang Xiong, Renxin Zhong
Abstract: Intelligent Transportation Systems deployed on highways predominantly rely on conventional RGB cameras for traffic perception and vehicle tracking. However, highway environments present unique challenges: the absence of artificial lighting infrastructure, combined with high vehicle velocities, results in severely degraded perception performance under low-light conditions. Specifically, nighttime scenarios suffer from motion blur, insufficient exposure, and poor signal-to-noise ratios, which catastrophically impair the reliability of RGB-based sensing systems. To address these limitations, we propose a novel Joint Event-RGB Adaptive Tracking (JEAT) framework. Unlike existing multi-sensor trackers constrained by rigid, hard-coded prioritization, JEAT merges asynchronous event streams and RGB frames into a unified joint data association optimization. By employing an Adaptive Extended Kalman Filter to continuously estimate measurement noise via NIS statistics, the framework dynamically weights and fuses both modalities, optimally harnessing event streams during dark or high-speed motion while leveraging RGB frames under bright or static conditions. Furthermore, given the absence of publicly available datasets tailored for event-based highway perception with diverse environmental conditions, we present SEHN, a large-scale synthetic dataset generated using the CARLA simulator. Our dataset encompasses diverse environmental conditions (daytime, nighttime, nighttime with out artificial lighting) and varying traffic densities, providing synchronized RGB imagery and event streams to facilitate multi-modal fusion research. Our code and datasets will be available at https://github.com/haidongwang96/SEHN.
Authors: Marina Dom\'inguez, N\'elida Mirabet-Herranz, Valery Naranjo
Abstract: Conditional diffusion models can generate anatomically plausible medical ultrasound (US) images, but anatomical plausibility alone does not ensure realistic B-mode appearance. Most US pipelines adapt standard generative architectures and condition them on anatomical masks, or use guidance mechanisms that reinforce the same anatomical signal. However, B-mode US images are shaped by acquisition-dependent properties such as speckle texture, tissue contrast, and attenuation. Using a frozen US foundation model, we show that standard conditional diffusion baselines remain separated from real images in representation space. In this work, we propose Feature-Space Candidate Guidance (FSCG), a training-free sampling strategy to reduce this gap. At sampling time, FSCG applies local k-NN feature correction and selects the best of multiple stochastic candidates according to their feature-space energy. In this way, the mask defines the anatomy, while FSCG steers samples toward the real US domain. Across three different datasets, FSCG reduces average FID64 by 56\%, FID192 by 57\%, and nearest-neighbour feature distance by 47\% over standard conditional diffusion sampling, outperforming alternative inference-time guidance baselines. The results suggest that domain-aware feature representations can reveal and reduce realism gaps in medical diffusion synthesis without retraining the generator. Our code is available at https://github.com/marinadominguez/FSCG.
Authors: Mingchao Sun, Luyang Tang, Yu Liu, Xu Yan, Zhan Li, Yunwei Zhang, Fei Yu, Zengye Ge, Yumin Liu, Jiacheng Zhang, Yongchang Zhang, Jiawei Zhang, Zhicheng Liu, Zhongxu Sun, Tianjian Ouyang, Wenzheng Chen, Shixing Yang, Nianfei Fan, Guodong Sun, Huan Li, Zheng Zhou, Yongze Li, Yingliang Peng, Mengmeng Du, Yuan Liu, Haozhe Shi, Chunnuo Gong, Chengzhen Yu, Chunxue Jia, Yang Liu, Shiying Zeng, Junnan Lai, Hang Zhang, Ning Guo, Baoquan Chen, Mu Xu, Hongyu Pan
Abstract: We present ABot-3DWorld 0, a universal multimodal 3D world model that turns text, image, and video inputs into high-fidelity, explorable 3D worlds. At the heart of our framework is a unified Spatial Generative Primitive (SGP), a compact tuple of a high-quality panorama and a spatial point cloud that delivers an efficient description of any 3D space. Multimodal inputs are first lifted into this primitive; a 3D-consistent panoramic video generator then explores the primitive along a planned trajectory; finally, our panoramic video reconstruction engine converts the generated video into a clean, photorealistic 3D Gaussian Splatting (3DGS) world. This pipeline covers two regimes: rich inputs (multi-view sets, casual video) are lifted into the SGP through a geometry-rigorous recovery that mirrors the observed scene, while a single image or sentence is completed generatively into a creative world. The result is one low-barrier engine for general 3D content creation that further anchors generated worlds to geographic points of interest, enabling map-native spatial exploration at consumer scale. Experiments show that ABot-3DWorld 0 sets the state of the art among open-source methods and demonstrates stronger scene fidelity than Marble under rich multimodal inputs.
Authors: Claudio Rota, Luca Cogo, Simone Bianco, Raimondo Schettini
Abstract: Color correction is a key component of camera image signal processing (ISP) pipelines, encompassing illuminant discounting and colorimetric mapping of device-dependent sensor responses to device-independent color spaces, such as CIE XYZ. Despite extensive research, accurate color correction remains challenging due to the non-linear relationship between camera sensor responses and CIE XYZ color space, as well as to the increasing presence of highly chromatic and spectrally complex LED illuminants. We propose a color correction framework based on illuminant-adaptive three-dimensional lookup tables (LUTs), which we call Color Correction LUT (C$^2$LUT). Our method combines a chromaticity-aware illuminant representation with a non-linear color transformation, enabling accurate correction under illuminants spanning a wide range of chromaticities and spectral complexities. We employ Tucker tensor decomposition to represent the LUTs, ensuring that computational requirements remain sufficiently low for deployment in camera ISPs. In addition, we introduce a large-scale illuminants dataset comprising 1,473 spectral power distributions, with different chromaticities and spectral profiles. Experiments across multiple cameras, illuminants, reflectance datasets, and real captured images demonstrate consistent improvements over existing methods for color correction, reducing CIE $\Delta E_{00}$ by up to 20% and angular error by up to 18% while remaining compatible with modern camera hardware constraints. Code and datasets are available at https://github.com/claudiom4sir/C2LUT.
Authors: Le-Kim Nguyen, Renato Martins, Pascal Vasseur, Cedric Demonceaux
Abstract: This paper addresses the problem of omnidirectional video interpolation, which plays an essential role in applications such as virtual reality and immersive video enhancement. Existing video interpolation methods are not well-suited for spherical videos, as they have difficulty handling severe distortions close to the poles. To address this issue, we propose SVI360, a dual-branch framework that combines the image frame and its rotated orthogonal view to deal with these distortions. The core methodological aspect of the approach is to reinforce equivariance of the flow displacements between the original and orthogonal views to improve intermediate frame prediction. Experiments show that our method outperforms state-of-the-art approaches in interpolation quality while maintaining accurate optical flow in four different public benchmarks. Code and pre-trained models are available at: https://icb-vision-ai.github.io/video360_interpolation/
URLs: https://icb-vision-ai.github.io/video360_interpolation/
Authors: Yilong Yang, Jianxin Tian, Shengchuan Zhang, Liujuan Cao
Abstract: Referring Camouflaged Object Detection (Ref-COD) requires segmenting hidden targets guided by reference cues. While supervised methods are annotation-heavy and training-free approaches via sparse point-prompting are sensitive to localization errors, we propose GFR-SAM, a robust three-stage training-free framework. GFR-SAM shifts the paradigm from fragile point-matching to a "Generate-Filter-Refine" pipeline. First, we introduce In-Context Exemplar-guided Segmentation, empowering SAM3 with cross-image inference to generate candidate masks via holistic visual exemplars, bypassing its native intra-image constraints. Second, a Region-Global Contrastive Filtering module ranks candidates through DINOv3-based prototypical alignment, effectively suppressing background distractors. Finally, a Geometric-Semantic Refinement module synergizes bounding box and text prompts to recover fine-grained boundaries and enhance instance recall. Evaluated on the R2C7K benchmark, GFR-SAM outperforms existing training-free methods by 8.7\% in weighted F-measure ($F_\beta^w$) and competes with supervised state-of-the-art counterparts. Ultimately, this work underscores the potential of unlocking SAM3's latent capability for cross-image In-Context prompting, establishing a robust, training-free paradigm that effectively bridges the gap between general-purpose foundation models and specialized, label-intensive perception tasks without the need for task-specific fine-tuning.
Authors: Jord\~ao Bragantini, Ilan Theodoro, Lo\"ic A. Royer
Abstract: Reconstructing lineages from live-imaging microscopy requires linking cell detections across time, including through cell divisions. A common approach is to construct a candidate graph and associate cell segmentations (nodes) across frames. However, these and other existing methods overlook two structural obstacles in candidate tracking graphs: (i) cell divisions entangle distinct lineage paths in the node embedding space, and (ii) edges sharing a node have near-random label agreement, so the candidate-graph topology carries no useful information for graph neural networks to aggregate. We propose the \textbf{Higher-Order Cell Tracking Transformer} (HOCT), an edge-centric architecture in which candidate cell links attend to one another under a 3D geometric prior, resolving both issues. Evaluated on the Cell Tracking Challenge and a bacteria division benchmark, HOCT achieves state-of-the-art results without deep pre-trained image encoders. Moreover, the proposed approach is easier to fine-tune, quickly reducing tracking errors by 59% with 400 annotations in a human-in-the-loop setting, outperforming LoRA fine-tuning of competing transformer baselines (6.75% improvement).
Authors: Seung Hyun Hahm, Minh T. Dinh, SouYoung Jin
Abstract: Long-form audio description (AD) requires more than describing visible actions: it must preserve characters, events, relationships, and story context across scenes so that blind and low-vision (BLV) audiences can follow a film. Modern video-language models (VLMs) are effective on short clips, but they often treat each moment independently, producing descriptions that miss who characters are, why events matter, and how the current scene connects to earlier narrative context. We propose StoryTeller, a training-free framework for story-aware long-form AD. Instead of relying only on local visual cues, StoryTeller maintains a verified narrative memory that carries forward story-relevant information across scenes, enabling later descriptions to remain coherent, grounded, and contextually informative. Given only raw video and a movie title, StoryTeller can optionally retrieve public movie metadata to resolve names and story context, while accepting only facts that are supported by the video through semantic filtering and VLM verification. The method requires no subtitles, scripts, AD transcripts, aligned captions, character banks, precomputed face identities, or task-specific fine-tuning. To evaluate whether generated AD preserves narrative information, we introduce StoryAD-QA, a question-answering benchmark that tests whether a language model can answer story-context questions using only the generated descriptions. Experiments on standard AD benchmarks and diverse long-form videos show that StoryTeller consistently improves narrative coherence, factual grounding, and story comprehension over strong baselines in automatic, QA-based, and human evaluations.
Authors: Kaixin Ma, Di Feng, Alexander Metz, Jiarui Lu, Eshan Verma, Afshin Dehghan
Abstract: We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents. The framework provides a stateful execution environment spanning 500+ tools across 16 application domains, supporting multi-image, multi-turn tasks where agents must ground progressively arriving visual inputs into executable tool calls while handling realistic conversational phenomena (goal revisions, error corrections, state mutations). An automated scenario generation pipeline produces diverse, visually grounded scenarios through information-flow-guided planning and multi-stage quality filtering, yielding 258 human-verified nominal scenarios and 50 variants targeting interactive UI applications. Evaluating 12 state-of-the-art models, from 4B open-weight to frontier proprietary systems, shows that current models still lack robust visual tool-calling capability: even the best model achieves below 50% success rate. Our failure analysis further reveals that visual precision, not only planning, is a primary bottleneck for capable models: 53% of failures stem from incorrect information extraction from images despite otherwise correct task workflows. A planning-to-precision crossover emerges with scale: smaller models fail at deciding what to do, while larger models fail at perceiving what they see, suggesting fundamentally different research directions for improving models at different capability levels. The framework and the benchmark are publicly available at https://github.com/apple/ml-mmtoolsandbox
Authors: Huy Che, Dinh-Duy Phan, Duc-Lung Vu
Abstract: License plate character detection is a crucial component of intelligent transportation systems, where high accuracy and computational efficiency are required for real-time deployment. Although recent deep learning-based methods have substantially improved detection performance, many high-accuracy models rely on large-scale architectures that incur substantial computational overhead, limiting their applicability to resource-constrained devices. In this paper, we propose MicroCharNet, an ultra-lightweight model specifically designed for license plate character detection. The proposed architecture employs a compact backbone composed of C2f blocks, integrated with CoordAtt module to enhance feature extraction while preserving spatial information. A lightweight C3k2-based neck fuses multi-level features, followed by a single-level anchor-free detection head that enables end-to-end prediction. Experiments conducted on the UFPR-ALPR dataset demonstrate that MicroCharNet achieves competitive detection accuracy with only 0.08M parameters and 0.096 GFLOPs, while outperforming several recent YOLO-based baselines. Hardware-level evaluations further confirm its efficiency for real-time deployment on edge devices. These results indicate that carefully designed ultra-lightweight architectures can effectively balance accuracy and efficiency in license plate character detection. The source code is available at https://github.com/chequanghuy/MicroCharNet.
Authors: Zihan Su, Teng Hu, Jiangning Zhang, Ruiyan Wang, Ran Yi, Lizhuang Ma, Dacheng Tao
Abstract: Autoregressive diffusion models have enabled high-quality video generation, yet their sequential nature inherently suffers from error accumulation. In long-horizon video synthesis, minor prediction deviations compound over time, inevitably leading to unconstrained generative drift, structural collapse, and severe visual degradation. To address this, we propose Cycle-World, a novel framework designed for stable and temporally consistent long-video generation. Our approach tackles error drift by enforcing strict temporal reversibility across both the training and inference phases. Theoretically, we demonstrate that forward generative drift can be strictly bottlenecked by a cycle-consistency objective. During training, we integrate an efficient reverse-prediction model to implicitly embed causal constraints into the forward generator, compelling it to produce reversible sequences that tightly adhere to the natural video manifold. At inference time, we repurpose this frozen reverse model as a runtime corrector. Through gradient-based cycle guidance, it iteratively refines the generated latent representations, actively suppressing accumulated errors before they are committed to the historical context. Extensive experiments on the VBench benchmark demonstrate that Cycle-World's dual-phase synergy significantly mitigates error drift, achieving state-of-the-art overall generation quality and long-horizon temporal consistency in 60-second synthesis.
Authors: Caleb Robinson, Anthony Ortiz, Simone Fobi Nsutezo, Cameron Birge, Meygha Machado, Marcelo Duarte, Joaquin Rivero Rodriguez, Anthony Cintron Roman, Kevin White, Inbal Becker-Reshef, Juan M. Lavista Ferres
Abstract: When a large disaster strikes, responders need a map of which buildings are damaged within hours. The models that do well on public benchmarks assume matched before-and-after imagery and a training set drawn from similar past events, and neither is usually available for a new disaster in its first day. We present HASTE (High-speed Assessment and Satellite Tracking for Emergencies), a no-code web platform that lets analysts who are not machine learning engineers produce per-building damage maps from post-disaster satellite imagery. HASTE implements two methods that share one interface. The first requires the user to label polygons over the post-disaster scene, trains a small semantic segmentation model on that single scene, runs it over the whole image, and joins the per-pixel output to existing building footprints. The second embeds every footprint with a pretrained vision model, requires the user to label a handful of buildings, and fits a logistic regression in the browser that scores the rest of the scene in seconds. We describe the platform, both methods, and the engineering that supports them. We also report preliminary experiments on xBD showing that foundation-model embeddings pooled over footprints separate damaged from intact buildings using post-disaster imagery alone, matching a fully supervised ResNet-50 baseline with a twentieth of its labels. HASTE and its predecessors have supported more than thirty real-world disaster responses since 2023, spanning earthquakes, hurricanes, cyclones, floods, wildfires, and tornadoes, delivering results to humanitarian partners within hours to days of imagery becoming available. We close with the directions we think are most promising, including vision-language assessment, active learning, and damage models for roads and other infrastructure. HASTE is open source at https://github.com/microsoft/haste.
Authors: Divya Mereddy, Jeevan Beedareddy
Abstract: This paper presents a cascaded Low-Rank Adaptation (LoRA)-based multimodal fusion framework for action and activity recognition in healthcare-oriented training environments. The proposed architecture combines parameter-efficient modality-specific adaptation with sequential fusion, enabling modalities to be integrated in stages without retraining previously learned components. Rather than assuming a fixed fusion structure, the framework first integrates more closely related modalities and then incorporates additional heterogeneous modalities, supporting scalable adaptation across datasets with different modality sets.We evaluate the framework on two healthcare-oriented training environment datasets: NurViD and the Nurse Training dataset. Across these datasets, preliminary results suggest that the proposed cascaded fusion strategy improves over individual modality models and provides competitive performance relative to previously reported dataset-specific baselines. Overall, these findings indicate that cascaded LoRA-based fusion is a promising parameter-efficient approach for integrating heterogeneous modalities in medical training action and activity recognition tasks. github: https://github.com/anonymous0-ai/LoRA-Based-Cascaded-Multimodal-Fusion-.git.
URLs: https://github.com/anonymous0-ai/LoRA-Based-Cascaded-Multimodal-Fusion-.git.
Authors: Kerui Chen, Jinglu Wang, Xiaoyi Zhang, Yan Lu
Abstract: Recent Multimodal Large Language Models (MLLMs) achieve strong performance on single-view video understanding benchmarks. However, sports videos involve dense occlusion, rapid motion, and complex interactions that are difficult to resolve from a single viewpoint. In practice, sports events are recorded from multiple camera angles, providing complementary evidence used by referees. Yet, no existing benchmark evaluates MLLMs on multi-view sports video understanding. To address this gap, we introduce SportMV-Bench, a comprehensive benchmark built from official match recordings, through a dedicated pipeline combining LLM-based generation, MLLM-based verification, and human filtering to ensure quality and consistency. SportMV-Bench containing 787 multi-view video bundles and 2592 question-answer pairs across three categories: Perception-Aware Recognition (PAR), Rule-aware Event Interpretation (REI), and Adjudicative Decision Reasoning(ADR). Our analysis shows that current MLLMs fail to effectively exploit multi-view information, with the bottlenecks lying in fine-grained visual perception and view selection rather than logical reasoning or domain knowledge. We propose SportMV-Agent, an agentic framework that orchestrates an iterative loop of active view selection, perception tool execution, and evidence-grounded reasoning, achieving a significant 14.46% relative improvement over the strongest MLLM baseline.
Authors: Shijie Wang, Honglu Zhou, Ziyang Wang, Ran Xu, Caiming Xiong, Silvio Savarese, Chen Sun, Juan Carlos Niebles
Abstract: Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding. Existing explainability efforts rely on textual rationales or sparse bounding boxes, which struggle to capture complex video dynamics such as occlusions and non-rigid deformations. We propose Evidence-Backed Video Question Answering (E-VQA), a novel task requiring models to jointly output a semantic answer and precise spatio-temporal evidence: temporal segments and dense, tracked object segmentation masklets. To support this, we introduce ST-Evidence, the first human-verified benchmark for both discriminative and generative pixel-level grounding. Evaluations of state-of-the-art models reveal a critical decoupling between QA accuracy and true visual perception that scaling alone fails to bridge. To address this, we develop scalable, automated generation pipelines to create ST-Evidence-Instruct, a 160k-scale dataset bridging high-level reasoning with fine-grained grounding. Fine-tuning grounded Video LLMs on this data yields substantial gains over the corresponding size-matched UniPixel baselines (e.g., +27.2 t-mean and +13.8 J&F on a 7B model), establishing a robust baseline for explainable, evidence-backed video understanding. Code and data are available at https://github.com/SalesforceAIResearch/EVQA.
Authors: Daniel Garibi, Ronen Kamenetsky, Hadar Averbuch-Elor, Daniel Cohen-Or, Or Patashnik
Abstract: Generating and editing a person's face demands high precision, as even minor modifications can significantly alter a subject's perceived identity. Current personalization and editing methods built on general-purpose text-to-image models, however, often lack the precision required for fine-grained facial edits. We present a method for fine-grained identity tuning in text-to-image personalization models. Unlike standard image editing, which operates on a given image, identity tuning modifies the latent representation of a specific identity, enabling the generation of diverse images that consistently depict the same edited identity. To enable fine-grained latent identity tuning, we explore the latent space of a pre-trained, frozen encoder for text-to-image personalization. Our approach requires no additional training. Instead, it leverages the existing architecture of a frozen encoder to uncover latent semantic directions. This space consists of a set of latent tokens that play distinct roles in capturing different aspects of an identity and often correspond to specific spatial or semantic facial regions. We show that meaningful directions can be identified within this space and within subspaces defined by selected tokens, enabling localized, fine-grained, and semantically coherent edits. We validate our approach through qualitative and quantitative experiments that demonstrate diverse localized facial edits while preserving cross-image identity consistency. Project page at: https://garibida.github.io/IdentityTuning/
Authors: Runhui Huang, Qihui Zhang, Zhe Liu, Yu Gao, Jie Wu, Hengshuang Zhao
Abstract: In this paper, we propose SpectraReward, a training-free reward function that turns pretrained MLLMs into off-the-shelf reward models for image-generation reinforcement learning. Instead of asking the MLLM to judge a generated image or answer decomposed verification questions, SpectraReward measures how well the original prompt can be recovered from the generated image through a single image-conditioned, teacher-forced forward pass. We use the average image-conditioned prompt log-likelihood as the reward, directly reusing the MLLM's pretrained image-text alignment ability without preference labels, reward-model fine-tuning. We further introduce Self-SpectraReward, a special case for unified multimodal models where the policy's own understanding branch serves as the reward model for its generation branch, forming a closed-loop self-improving framework without external reward models or external knowledge. Extensive experiments validate SpectraReward through a broad image-generation RL study covering two diffusion models, three RL algorithms, nine reward MLLM backbones from four MLLM families spanning 4B to 235B parameters, and five out-of-distribution text-to-image benchmarks. Results show that both SpectraReward and Self-SpectraReward significantly and consistently improve generation performance and outperform prior MLLM-derived reward training methods. Further analysis reveals that larger reward MLLMs are not always better, while Self-SpectraReward can match or surpass much larger external reward models, suggesting that reward-policy alignment is a key factor for effective image-generation RL. Project Page: https://huangrh99.github.io/SpectraReward/
Authors: Anca Marginean, Adrian Groza
Abstract: To provide a structured and interpretable assessment, we decompose the image-based diagnosis into components following the Toulmin model of argumentation. This model consists of a claim, grounds, warrant, qualifier, rebuttal, and backing. Consider a claim generated by a machine learning (ML) model for retinal diagnosis. Rather than accepting this claim at face value, one could either apply explainable AI (XAI) methods or adopt an argumentation-based approach. In our framework, a model specialized in biomarker extraction from images provides the grounds. The warrant-linking the grounds to the claim - is analyzed by an agent equipped with medical knowledge; in our architecture, this role is fulfilled by a MedGemma agent. The qualifier is determined based on the overall quantitative evaluation of both the warrant and grounds models. Finally, a rebuttal is constructed using image similarity measures computed with MedSigLip. All these components are presented to the human expert, enabling a more informed and critical assessment of the ML-generated diagnosis.
Authors: Joshua Kofi Asamoah, Blessing Agyei Kyem, Eugene Denteh, Armstrong Aboah
Abstract: Safe motion planning in advanced driver-assistance systems and autonomous vehicles requires an accurate understanding of how the surrounding traffic scene is likely to evolve. However, many existing lane-change prediction methods remain centered on a single target vehicle, while multi-agent forecasting approaches often describe scene evolution only through future positions and provide limited explicit information about the maneuver associated with each vehicle. This study proposes a dynamic scene graph attention framework that predicts the lane-change intention and future trajectory of every relevant vehicle within a local traffic scene. The scene is represented as a time-varying interaction graph in which vehicles are modeled as nodes and their spatial and kinematic relationships are encoded through explicit edge features. Temporal graph-attention message passing captures evolving inter-vehicle dependencies and pre-maneuver cues, while an intention-guided decoder links each predicted maneuver to its corresponding future motion. A scene-level consistency objective further encourages compatible multi-vehicle futures. Experiments on the NGSIM I-80, NGSIM US-101, and highD datasets demonstrate consistent improvements over competing baselines. DSiGAT achieves intention prediction accuracies of 90.12% and 90.97% on NGSIM I-80 and US-101, respectively, and reduces trajectory RMSE by up to 52.94% relative to the strongest baseline. It also produces lower inter-agent collision rates and joint displacement errors, indicating more coherent scene-level predictions. Ablation, sensitivity, robustness, and qualitative analyses further validate the contribution of the proposed components and the effectiveness of the scene-focused formulation.
Authors: Saahil Islam, Sebastian Piat, Venkatesh N. Murthy, Serkan Cimen, Puneet Sharma, Andreas Maier, Florin C. Ghesu
Abstract: Percutaneous Coronary Intervention (PCI) is a minimally invasive procedure used to restore coronary blood flow obstructed by atherosclerotic plaque. During PCI, repeated injections of iodine-based contrast agents are required to visualize the coronary arteries and guide interventional devices. However, frequent contrast injections increase radiation exposure and the risk of contrast-induced nephropathy, with acute kidney injury reported in up to 30% of patients with renal impairment. Dynamic Coronary Roadmapping (DRM) reduces these risks by overlaying a precomputed angiographic vessel map onto live fluoroscopy and continuously updating it throughout the procedure. Accurate DRM relies on precise cardiac phase matching between angiography and fluoroscopy, together with reliable catheter tip tracking for motion compensation. These tasks remain challenging in ECG-free settings and when only limited manual annotations are available. We present a unified DRM framework that simultaneously performs cardiac phase matching and catheter tip tracking for accurate real-time guidance. Our method employs a large-scale spatio-temporal encoder pretrained on 16 million X-ray frames to learn cardiac motion dynamics. To the best of our knowledge, this is the first application of large-scale spatio-temporal pretraining for motion compensation in DRM. We further introduce auxiliary tasks based on ECG R-peak detection and catheter tip tracking, improving optimization while eliminating the need for extensive catheter mask annotations. Finally, a majority-voting postprocessing strategy aggregates temporal predictions, improving robustness and providing a confidence score that correlates with phase-matching error. Comprehensive evaluation on clinical X-ray datasets demonstrates state-of-the-art performance, achieving low temporal misalignment and robust phase-matching accuracy suitable for real-time DRM.
Authors: Animesh Kumar
Abstract: Deep models for retinal optical coherence tomography (OCT) classification report high accuracy but rarely report whether their confidence can be trusted -- a gap that matters when a wrong-but-confident reading delays sight-saving treatment. We pair a hybrid convolutional-Transformer encoder with a gradient-boosting (XGBoost) classification head and a three-part clinical safety layer: confidence calibration, out-of-distribution (OOD) rejection, and per-prediction uncertainty flagging. On four-class OCT (84,495 scans) the model reaches 95.4% accuracy while cutting calibration error twelve-fold (expected calibration error, ECE = 0.0024), so the confidence it reports tracks its true accuracy. To our knowledge this is the first OCT classifier to validate all three safety mechanisms jointly, with public weights and reproducible multi-seed evaluation.
Authors: Jiaming Liang, Haolin Chen, Tingting Li, Bowen Yu, Qianyan Long, Tinghe Zhang, Xi Zhong, Xiaowei Hu, Xiaoqi Sheng, Hongmin Cai
Abstract: Microbial density is clinically important for tumor assessment and treatment decision-making, and recent advances in deep learning suggest that it can be non-invasively inferred from multimodal MRI. In this work, MRI-based Microbial Density Stratification (MRI-MDS) is first investigated as a patient-level representation learning task, and Center Heatmap-driven Macro-micro modeling Network (CHM-Net) is introduced for this task. CHM-Net first establishes the link between imaging phenotypes and microbial states through center heatmap-guided small-lesion response localization. Building upon this, it constructs patient-level macro-micro evidence from localized heatmap responses for microbial density prediction. Experiments on the novel GBNPC 2026 dataset constructed for MRI-MDS demonstrate the effectiveness of CHM-Net, achieving superior performance over representative baselines with a 12.06% absolute ACC gain over the strongest competing result. Additionally, auxiliary validation on two 3D medical image datasets further verifies its robustness across volumetric medical image classification scenarios. The project is available at https://anonymous.4open.science/r/CHM-Net-942E/.
Authors: Hongtao Liang, Xinyu Shao, Chenxu Wang, Yiyao Wan, Jiahuan Ji, Fangwei Ye, Fuhui Zhou, Qihui Wu
Abstract: Under Global Navigation Satellite System (GNSS) denial, a UAV controller still needs a distance and heading command it can execute, making accurate metric last-meter navigation essential. Dense pair-geometry foundation models transfer relative structure well, yet the distance scale of their raw metric outputs remains poorly calibrated. Under the relative error metric of PairUAV, correcting only the average scale can still leave costly, distance-dependent residuals near the goal. To address this scale mismatch, Range-Aware Scale Recovery (RASR) separates a transferable scale-recovery core from a protocol-specific calibration module in a per-pair system fixed at inference. The core compresses frozen Matching And Stereo 3D Reconstruction (MASt3R)-style geometry into a compact descriptor and uses global calibration to recover the dominant metric signal. Range-bucket residual correction and command-grid alignment stay inside the calibration module, so they match the command format and evaluation protocol of PairUAV. On the UAVs in Multimedia 2026 PairUAV online evaluation, RASR reaches a total score of 0.003189. Under the PairUAV protocol, frozen pair geometry thus yields stable per-pair distance and heading estimates, while every protocol-specific adjustment stays confined to a calibration module fixed before inference. Code and materials are available at https://github.com/lht-research/rasr-pairuav.
Authors: Shengzhuo Yang, Ronghao Yu, Chuanjie Lv, Linpeng Peng, Hang Yu, Jie Ren, Jiajun Lv, Yong Liu
Abstract: Vision-language-action (VLA) models aim to understand natural-language instructions and visual observations, and to generate and execute corresponding actions as embodied agents. Recently, autoregressive token-based action generation has driven the development of many representative VLA models. However, this paradigm often reduces action generation to next-token prediction, thereby lacking explicit modeling of the spatiotemporal structure of action sequences and the disentanglement between vision-language representations and actions, which can limit performance in long-horizon and complex scenarios. In this paper, we propose TS-Mask VLA, a vision-language-action framework for robot manipulation. TS-Mask VLA is built upon two key designs: (1) a Discrete Diffusion Action Expert equipped with a Bridge Attention conditioning bridge, which enables multi-layer conditioning from the VLM and facilitates more accurate and stable action generation; and (2) a temporal-spatial 2D masking strategy for discrete action tokens that strengthens the model's understanding of cross-time dependencies and inter-dimensional coupling, leading to more structurally consistent action sequences. We conduct extensive experiments on simulation benchmarks and real-world tasks. On LIBERO, TS-Mask VLA achieves a 95.7 percent average success rate with only 0.5B parameters, outperforming significantly larger models. On CALVIN, it attains the best average sequence length of 4.19 and strong long-horizon performance. Comprehensive analyses and ablations further validate the effectiveness of our design.
Authors: Sisipho Hamlomo, Marcellin Atemkeng
Abstract: Medical imaging generates high-resolution images posing significant storage, transmission, and computational challenges. While low-rank matrix approximation (LoRMA) techniques offer efficient compression by exploiting structural redundancy, global approaches often fail to preserve local details critical for diagnosis. This paper focuses on clustering techniques that exploit non-local self-similarity to identify structurally similar regions in medical images. These clusters can be used for post-processing tasks such as adaptive image compression. We evaluate five clustering techniques: k-means, mini-batch k-means, agglomerative hierarchical clustering, balanced iterative reducing and clustering using hierarchies (BIRCH), and bisecting k-means across MRI, ultrasound, and chest X-ray modalities. All clustering techniques were optimised using random search, and cluster quality was assessed using the Silhouette score, the Davies-Bouldin (DB) index, and the Calinski-Harabasz (CH) index. Results demonstrate that standard k-means and bisecting k-means generally achieve strong cluster cohesion and separation across modalities. However, they tend to form a small number of clusters with high intra-cluster variability, limiting their effectiveness for post-processing tasks such as adaptive compression. Agglomerative clustering outperformed other techniques for MRI and ultrasound in terms of intra-cluster homogeneity, making it more suitable for preserving fine diagnostic details. For chest X-rays, mini-batch k-means achieved the best balance between clustering quality and intra-cluster compactness. BIRCH consistently underperformed across all modalities.
Authors: Chengze Ye, Linda-Sophie Schneider, Yipeng Sun, Mareike Thies, Siyuan Mei, Paula Andrea P\'erez-Toro, Siming Bayer, Andreas Maier
Abstract: The differentiable shift-variant filtered backprojection (SV-FBP) framework enables data-driven estimation of redundancy weights for cone-beam CT reconstruction under general source trajectories, removing the need for analytically derived weighting schemes. In this work, we present a systematic study of the robustness and adaptability of differentiable SV-FBP under challenging acquisition settings. We show that the framework remains stable across highly irregular and discontinuous trajectories, indicating that reconstruction performance is largely insensitive to trajectory ordering or continuity. Instead, the spatial distribution of sampling points plays a more dominant role. Under sparse-view conditions, differentiable SV-FBP achieves competitive reconstruction quality while providing an order-of-magnitude reduction in computation time compared to iterative reconstruction methods at moderate sampling densities. However, we identify a clear transition regime under severe undersampling, where the absence of iterative data consistency leads to performance degradation. Furthermore, we demonstrate that the framework remains applicable to non-planar multi-isocenter geometries, such as Lissajous-saddle trajectories, without requiring architectural modifications. These findings provide new insights into the behavior and limitations of the differentiable SV-FBP model and highlight it as a flexible and efficient solution for non-standard and robotic CBCT acquisition scenarios.
Authors: Raphael Reme (IP Paris, BIA, IDS, IMAGES), Victor Piriou (BIA), Alison Hanson (IP Paris, IDS, IMAGES), Rafael Yuste (IP Paris, IDS, IMAGES), Alasdair Newson (IP Paris, IDS, IMAGES), Elsa Angelini (IP Paris, IDS, IMAGES), Jean-Christophe Olivo-Marin (BIA), Thibault Lagache (BIA)
Abstract: In time-lapse fluorescence imaging, single-particle-tracking is a powerful tool to monitor the dynamics of objects of interest, and extract information about biological processes. However, tracked particles can be subject to occlusion and intermittent detectability. When these phenomena persist over a few frames, tracking algorithms tend to produce multiple tracklets for the same particle. In this work, we introduce self-supervised learning of visual features to compare tracked particles, and we exploit both visual and positional distances to robustly stitch tracklets representing the same particle. We demonstrate the performance of our stitching framework on time-lapse fluorescence sequences of Hydra vulgaris neurons. Results show high stitching precision, and reduction of errors made by previous algorithms on the same data by a factor of two.
Authors: Mahsa Vali, Zhilong Weng, No\'emie Moreaua, Yuri Tolkach, Katarzyna Bozek
Abstract: Deep learning-based segmentation of histopathology whole-slide images (WSIs) requires large amounts of pixel-level annotations, which are costly and time-consuming to obtain. Active learning (AL) has been proposed to reduce this effort, but existing methods exhibit three key limitations. Uncertainty estimation is unreliable on partially annotated WSIs, patch-level acquisition is inconsistent with slide-level annotation workflows, and class imbalance in multi-class settings is not explicitly addressed. To address these challenges, we propose SHAL (Slide-level Hybrid Active Learning), a patient-level AL framework for annotation-efficient multi-class histopathology segmentation. SHAL integrates three complementary components: a foreground-aware strategy that suppresses bias from unlabeled background regions, a stage-adaptive mechanism that hybridizes predictive entropy and epistemic uncertainty across learning stages, and a class-aware strategy that prioritizes diagnostically relevant tissue classes. SHAL is evaluated on the TCGA colorectal cancer dataset. It achieves the highest Macro Dice at the full annotation budget (0.846) and reaches Dice greater than or equal to 0.80 using only 26 percent of the budget (50 of 190 slides), whereas competing methods reach this threshold only at 37 percent (70 slides). Across five independent external cohorts, SHAL attains the highest mean external Macro Dice (0.815) and the smallest internal-to-external generalization gap among all methods (0.025 at Round 3 and 0.026 at the full budget). The results indicate that patient-level hybrid uncertainty acquisition reduces annotation cost without sacrificing cross-domain generalization in computational pathology.
Authors: Juan Terven, Diana Margarita C\'ordova Esparza, Julio Alejandro Romero Gonzalez, Edgar Arturo Ch\'avez Urbiola, Francisco Javier Willars Rodriguez, Juan Bautista Hurtado Ramos, Alfonso Ramirez Pedraza
Abstract: Long-tailed recognition methods often modify losses, margins, or representations to reduce the dominance of frequent classes. We ask whether, after Balanced Softmax training, the remaining tail error can be reduced by retraining only the classifier. We evaluate BS-cRT, a two-stage procedure that trains a backbone and cosine classifier with Balanced Softmax, freezes the backbone, and updates only the classifier on balanced episodic batches. The second stage keeps the empirical-prior Balanced Softmax objective and uses raw cosine logits at inference. Across CIFAR-100-LT, CIFAR-10-LT, ImageNet-LT, and Places-LT, this classifier-only step consistently improves Few-shot accuracy over the matched Balanced Softmax checkpoint. At imbalance factor 100, Few-shot gains are +5.15 points on CIFAR-100-LT and +5.83 on CIFAR-10-LT; on ImageNet-LT and Places-LT, gains are +6.92 and +9.78 points, respectively, with a Top-1/Few-shot trade-off on ImageNet-LT. We also analyze Counterfactual Boundary Risk Minimization (CBRM), a boundary-probe extension using prototype-based features near decision boundaries. CBRM identifies two failure modes: scaled-logit cosine margins destabilize training, and corrected hardest-negative probes remain head-class anchored. The results support BS-cRT as a practical classifier-side baseline and indicate that boundary supervision must account for class frequency.
Authors: Rizwaan Malik, Ashna Khetan, Isabel Sieh, Samin Khan
Abstract: Mathematical diagrams play a crucial role in K 12 education, both as problem components and as scaffolding for student comprehension. However, current AI tools, including Large Language Models (LLMs), struggle to reliably generate accurate and pedagogically sound visual diagrams, even when provided with detailed descriptions. A significant gap therefore remains in the reliable generation of diagrams for middle school mathematics. To address this, we introduce an agentic workflow that enables LLM agents to evaluate the quality of generated visuals and use this feedback to iteratively improve their outputs. This self improvement loop aims to enhance the accuracy and educational appropriateness of AI generated diagrams. Our research investigates two questions. First, can LLMs accurately generate quality assurance questions for a visual aid given specific criteria for visual quality? Second, given valid quality assurance questions, can Vision Language Models effectively evaluate generated K 12 visual aids and use the resulting feedback to improve them iteratively? We conduct an exploratory evaluation of our agentic workflow and identify key areas for improvement, including stronger spatial reasoning and more comprehensive coverage of diagram features in the generated quality assurance questions. Our results provide preliminary evidence that this approach can improve the reliability and educational value of AI generated mathematical diagrams.
Authors: Tim White, Dingrui Tao, Camille Avestruz, Jeffrey Regier, the LSST Dark Energy Science Collaboration
Abstract: The prevailing approach to inferring weak gravitational lensing shear from images involves detecting galaxies, estimating their ellipticities, and calibrating these estimates to correct for image noise, selection bias, and model misspecification. Characterizing the statistical model and assumptions underlying this pipeline is challenging, which makes it difficult to propagate uncertainty through its various stages. As an alternative, we propose to infer shear using neural posterior estimation (NPE), a type of simulation-based inference. We train a deep neural network to map a simulated multiband image to a variational distribution over the underlying shear field, thereby folding galaxy detection, deblending, measurement, and calibration into a single implicit inference step. Once trained, the network accounts for all features present in the simulated images, including potential sources of bias. In experiments on simulated constant-shear images with increasingly complex observational effects, NPE produces accurate and well-calibrated posterior approximations for both shear components in the presence of blended galaxies, spatially varying point spread functions, stars, and detector artifacts. These results demonstrate that NPE can be a viable shear estimation method in settings where all anticipated features and artifacts can be simulated, a requirement that will become increasingly feasible as simulation fidelity improves in the coming decades.
Authors: Zhimin Li, Jake D. Balla, Joshua A. Levine
Abstract: Implicit neural representations (INRs) offer compact encoding of volumes, but as lossy approximators, inevitably have prediction errors. We consider INRs that can simultaneously encode relative error scales by predicting distributions using tools from uncertainty estimation. Typically, uncertainty estimation relies on computationally expensive approaches or on predefined parametric assumptions about the predictive distribution (e.g., Gaussian). In this study, we propose a lightweight method that reformulates regression-based INR training as a classification task by discretizing continuous targets into bins, enabling flexible distribution modeling to capture complex multimodal behaviors. We analyze the trade-off between regression and classification for INR training and demonstrate that the classification setting tends to achieve high reconstruction quality and competitive error awareness through uncertainty estimation, compared to regression-based approaches.
Authors: Wenyuan Wang, Lianyu Hu, Hao Wang, Yang Liu
Abstract: Video-language models (VLMs) have achieved remarkable performance on video understanding and visual question answering, yet they remain unreliable in reasoning about physical plausibility, where understanding object interactions, causal dynamics, and fundamental physical principles is essential. This limitation is particularly evident on challenging physical reasoning benchmarks, revealing a persistent gap in physical commonsense reasoning. To address this challenge, we propose PhysMRV, a training-free physical memory and verification framework for physical plausibility reasoning. Unlike retrieval-augmented VLMs that retrieve semantically similar videos as additional context, PhysMRV transforms training videos into a Hierarchical Memory Bank of structured physical knowledge comprising three complementary levels: scene descriptions capturing visual context, physical-event graphs modeling object interactions and causal structure, and physics-rule summaries distilling reusable physical principles and cues. During inference, PhysMRV retrieves physically relevant memories and leverages their structured physical evidence to guide a frozen VLM in verifying physical plausibility, requiring neither fine-tuning nor parameter updates. We evaluate PhysMRV on three challenging physical reasoning benchmarks, ImplausiBench, IntPhys2, and GRASP Level 2, across multiple state-of-the-art VLMs. Experimental results demonstrate consistent improvements over direct prompting across diverse VLMs and evaluation benchmarks, showing that structured physical memories provide an effective and scalable means of enhancing physical plausibility reasoning without additional training.
Authors: Kang Ding, Zhigui Lin, Hongsong Wang, Jie Gui, Qi Liu, Zhe Wang, Luqi Tang, Lei He
Abstract: This letter presents PrismAD, a decoupled end-to-end autonomous driving framework based on a Semantic Mixture-of-Planners. Existing planners usually aggregate heterogeneous scene tokens into a coupled representation space, forcing a single planning branch to jointly model agent interaction, road geometry, and driving intention. Such coupling may weaken factor-specific reasoning and obscure the contribution of different planning cues. To address this limitation, PrismAD partitions scene tokens into interaction, geometry, and intent groups, and assigns them to independent planning experts with the same architecture but separate parameters. Each expert learns a specialized motion-planning representation, while a semantics-aware router adaptively aggregates expert predictions with separate routing weights for motion prediction and ego planning. Sparse top-$K$ activation with noisy gating is further introduced to improve routing robustness and reduce unnecessary expert computation. Extensive experiments on the nuScenes open-loop dataset and NeuroNCAP closed-loop benchmark demonstrate that PrismAD exhibits competitive performance. Our code will be released soon.
Authors: Federico Rollo
Abstract: The transition of autonomous mobile robots from controlled industrial settings to dynamic, human-centric environments, such as manufacturing, logistics, and healthcare, has made their safe and autonomous operation a critical area of research. These sophisticated machines must be capable of perceiving, understanding, and interacting with their surroundings to navigate freely and perform complex tasks. A significant obstacle to achieving this is the lack of comprehensive contextual awareness, which requires a robot to recognize its spatial environment and identify the objects and actors within it. Without this perceptual knowledge, robots struggle to plan adaptive behaviors or engage in meaningful interaction with humans. This thesis presents novel solutions to this challenge by exploring two distinct but complementary research directions. The first direction involves human re-identification and tracking to improve Human-Robot Collaboration. Our developed approach enables a mobile robot to recognize a specific person, facilitating targeted collaboration while ignoring other individuals. The second direction focuses on enhancing the robot's overall perceptual capabilities to understand its environment geometrically and semantically. Geometric information is vital for motion planning and collision avoidance, while semantic knowledge provides the robot with a richer understanding for more advanced interaction. Both solutions are driven by the improvement of the semantical understanding of robots that enhance their knowledge of their surroundings, allowing a smoother and more natural interaction between robots, humans, and the environment. The contributions of this work in human re-identification and environmental understanding represent a significant step toward a future where robots are more contextually aware, enabling safer coexistence and more effective collaboration.
Authors: Qihan Xu, Ivan V. Baji\'c
Abstract: H.264 has been the most widely used video coding format for the past two decades due to its relative simplicity, efficiency, and wide availability of software and hardware implementations. However, optimizing codec parameters such as the quantization parameter (QP) for specific objectives (e.g., perceptual quality or machine vision tasks) is challenging due to the non-differentiable nature of standard video codecs. While differentiable proxies have recently been used to enable gradient-based optimization around standard codecs, their fidelity to the target codec is rarely explicitly characterized. In this paper, we propose a differentiable proxy learning method for H.264 intra codec to enable adaptive quantization control. Built upon a variable-rate learned compression model, the proposed proxy is made differentiable with respect to codec QP through a soft-indexing mechanism. It is then trained to approximate the rate-distortion behavior of H.264 under two quantization settings: global-QP, which uses one QP per image, and spatial-QP, which assigns QPs at the macroblock level. Using the frozen trained proxy, we develop a proxy-based adaptive quantization (AQ) framework for both perceptual optimization and machine vision tasks. Experimental results demonstrate that the proposed proxies closely approximate the rate-distortion behavior of H.264 intra codec. The resulting proxy-based AQ framework consistently improves rate-task trade-offs over fixed-QP H.264 baselines, achieving BD-rate reduction of up to 17.12% for semantic segmentation and 15.30% for MS-SSIM.
Authors: Yiluo Wei, Yupeng He, Qiming Ye, Gareth Tyson
Abstract: The open-sourcing of powerful image generation models has created a vibrant ecosystem where creators curate and combine a vast array of community-contributed models. This practice stands in sharp contrast to using closed-source tools like Midjourney. Yet, little is known about these emerging creative workflows. To bridge this gap, this paper presents the first large-scale empirical study of creator model usage behavior within this open-source image generation ecosystem. We construct a novel dataset of 6 million images with their embedded generation metadata -- a detailed recipe of the creation process, including the models used and the prompts. By linking the usage of 22.4K base models and 154K LoRA models to the images, our findings underscore the ecosystem's unique strengths and its inherent obstacles. This provides valuable insights for making this ecosystem more sustainable and innovative. Moreover, we make our dataset publicly available, providing creators with practical references for producing better artworks and researchers to facilitate further studies.
Authors: Lin Li, Chaochao Zhou, Benjamin Aubert, Junlin Guo, Junchao Zhu
Abstract: Accurate geometric calibration is essential for fluoroscopy-guided spinal imaging, digitally reconstructed radiograph (DRR) generation, and 2D--3D vertebral registration. Although calibration quality is typically evaluated using reconstruction-based metrics such as reprojection error, its influence on projection-domain consistency remains poorly understood. This study presents a synthetic framework for evaluating how intrinsic calibration perturbations affect vertebral fluoroscopic projections and downstream registration performance. CT-derived vertebral models and controlled cone-beam imaging geometry were used to generate DRRs with both ground-truth and perturbed intrinsic calibration parameters while maintaining identical anatomy and acquisition pose. Projection-domain changes were quantified using anatomical landmark displacement, contour distance, silhouette overlap, image similarity, and landmark-based 2D--3D registration accuracy in anterior--posterior (AP) and lateral (LAT) views. Results show that even small intrinsic calibration perturbations produce measurable changes in vertebral projection geometry, contour morphology, landmark localization, and DRR appearance. Sensitivity is strongly view dependent, with LAT projections exhibiting substantially greater deformation and anatomical displacement than AP projections. These projection inconsistencies also degrade downstream 2D--3D registration, particularly rotational alignment accuracy. The findings demonstrate that projection-domain consistency complements conventional reconstruction-based calibration metrics and provides a practical framework for assessing calibration robustness. This approach may improve the reliability of DRR generation and fluoroscopy-guided vertebral registration in image-guided spinal applications.
Authors: Shijin Wang, Zichong Chen, Yang Zhou, Hui Huang
Abstract: Mesh deformation, the process of altering the vertex positions of a 3D mesh while preserving its topological structure, is a cornerstone of computer graphics. Despite the recent emergence of numerous text-guided 3D mesh deformation methods, deforming an initial mesh into one that both adheres to text prompts and preserves its pose remains challenging. This paper proposes PoseAlign, which decomposes text-guided mesh deformation into two stages: global pose scaling and local detail sculpting. Specifically, in the first stage, we introduce the Laplacian as a differentiable mesh representation to enable more efficient yet smoother global deformation. Then, we propose a novel pose-aligned SDS loss by adapting score distillation sampling (SDS) with an attention-sharing mechanism, which sculptures fine-grained geometric details for the deformed mesh while preserving its original pose. PoseAlign significantly enhances the controllability of the overall deformation process, achieving a favorable balance between pose preservation and text alignment. Experiments demonstrate the competitive advantages of our method in text alignment and mesh quality. Code is available at: https://cousingrade6.github.io/PoseAlign
Authors: Hang Long, Tianhao Zhao, Junkai Lin, Youjia Zhang, Huipeng Guo, Rendong Liang, Jiale Xu, Jozef Hladk\'y, Matthias Nie{\ss}ner, Wei Yang
Abstract: Flow matching over carefully designed latent representations has recently emerged as a powerful paradigm for topology-aware mesh generation. Existing approaches, however, model vertices and connectivity jointly in a joint latent space, entangling continuous vertex geometry with discrete combinatorial structure; this complicates flow learning and manifests as drifting vertices and broken surfaces. We present LATO.2, a factorized flow matching framework that decomposes mesh generation into a vertex flow followed by a connectivity flow conditioned on the realized vertices, with both stages anchored to a shared coarse voxel scaffold. Dedicated VAEs underpin the two stages, recovering vertices at sub-voxel precision and embedding discrete connectivity into a continuous latent space. We demonstrate two advantages unique to this factorization: (i) part-wise generation, in which the scaffold is partitioned and each part synthesized at full latent capacity, yielding substantially higher-resolution meshes than a monolithic latent permits; and (ii) topology-adaptive editing, in which manipulating first-stage vertices induces the corresponding connectivity without re-optimization. Experiments show that LATO.2 surpasses state-of-the-art topology-aware mesh generators in geometric fidelity and connectivity quality.
Authors: Fabian Mager, Hiba Nassar, Lars Kai Hansen
Abstract: We study the modality gap in CLIP-style dual-encoder contrastive learning, where image and text embeddings remain misaligned despite being trained in a shared space. We argue that the gap is induced by a failure of the InfoNCE formulation with independent encoders. We conduct a uni-modal experiment with two independent encoders and identical initialization conditions and find that InfoNCE actively generates a gap at low temperatures. We provide a theoretical analysis of this phenomenon and show that the modality gap is indeed a mode-failure of InfoNCE, but only at low temperatures. We propose a simple modification called xNCE, which uses intermodal as well as intra-modality negative contrastive pairs. xNCE matches retrieval performance on MS-COCO while consistently reducing the gap even at low temperatures. Notably, xNCE improves zero-shot classification over the InfoNCE baseline across all benchmarks, whereas high-temperature InfoNCE and regularized InfoNCE both fail to do so, demonstrating that xNCE reduces the modality gap without sacrificing the discriminative geometry needed for transfer.
Authors: Haojie Huang, Zhang Ye, Linfeng Zhao, Boce Hu, Mingxi Jia, Yu Qi, Ahmed Agha, Dian Wang, Robert Platt, Robin Walters
Abstract: The action space poses a major challenge in robot learning, since it is often high-dimensional, can span long time horizons, and frequently admits multi-modal optimal solutions. A good choice of action representation and loss function can help to address these concerns, but there are often trade offs. We propose Action Map Policy (AMP), which casts 3D closed-loop manipulation policy learning as a classification problem in image space. While classification has been an effective formulation in generative language models, applying it to robot action learning is difficult because naively discretizing high-dimensional continuous actions explodes the token vocabulary. Our key idea is to project 3D actions onto the camera image planes and treat each pixel location as a discrete class, thus controlling dimensionality while retaining multi-modality. This method supports millimeter-level precision for high-dimensional actions without requiring a prohibitively large vocabulary, while preserving fine-grained pixel-wise visual signals. Furthermore, it can predict the entire action chunk in a single forward pass, avoiding complex noise scheduling and iterative denoising while achieving substantially faster inference than diffusion policies. Experiments on various manipulation tasks show that AMP outperforms strong baselines, achieving higher success rates, faster inference, and enhanced spatial reasoning.
Authors: Siyi H, Jared Strade, Hyungtae Lim, Luca Carlone
Abstract: Generating realistic 3D indoor scenes is an area of growing interest in computer vision and robotics. Existing methods, often motivated by applications such as interior design, generally focus on object layout generation within a single room. The generation of high-level scene structure, such as room-level layout and traversability, remains underexplored despite its importance for robotics applications. In this paper, we consider the case where a robot has explored part of an environment and needs to predict the unexplored parts to support downstream tasks such as exploration or object search. We propose a top-down framework for synthesizing hierarchical 3D scene graphs, including a room layer -- describing the floor plan and traversability -- and an object layer modeling object layouts within each room. For the room layer, we propose a novel mixed-domain graph diffusion model jointly predicting room categories, floor boundaries, and traversability between rooms. Via corruption and masking, this model supports partial constraints such as incomplete floor plans, avoiding the need for partially observed training data. For the object layer, we integrate an existing mixed discrete-continuous diffusion model for joint prediction of object categories, locations, sizes, and orientations within each room given the floor plan. We compare our method with state-of-the-art occupancy-based and LLM-based floor plan generation methods on a standard benchmark. Compared with an occupancy-based learning baseline, our method generalizes substantially better to out-of-distribution partial floor plans. We also demonstrate our integrated prediction pipeline on real-world scenes from robot-collected data, enabling prediction beyond explored areas.
Authors: Ali Ahmadi, Hamed Rahimi, Adrien Jacquet Cretides, Marie Samson, Mahdi Khoramshahi, Mohamed Chetouani
Abstract: As mobile robots become more integrated into everyday human environments, social robot navigation is becoming essential for ensuring human comfort, safety, and trust. While reinforcement learning (RL) navigation policies provide the fast inference and reactive behavior necessary for real-time deployment, they still lack flexible semantic reasoning capabilities and often fail to generalize to complex social scenarios. Recent approaches have increasingly turned to vision-language models (VLMs) in place of RL policies to improve semantic and social reasoning in robot navigation. Nevertheless, their high computational cost and slow inference remain major barriers to real-time deployment. To overcome these limitations, we introduce HUMA (Hybrid Understanding for Multi-modal social Navigation), a hybrid architecture that dynamically balances the computational efficiency of RL policies with the deep semantic understanding of VLMs. Our approach uses a reactive RL policy to handle low-density, routine navigation tasks, while conditioning it on a post-trained high-level VLM when a human enters sensitive situations, such as the robot's proximity zone. We evaluate HUMA on the Social-MP3D and Social-HM3D benchmarks, where it achieves task success improvements of 20% and 3%, respectively, while significantly reducing personal space violations and human collisions against state-of-the-art baselines. Extensive ablation studies validate each architectural component, and real-world deployment on the Miroka\"i mobile robot further demonstrates the practical viability of our approach.
Authors: Edward Beng Wai Tan, Siew-Kei Lam
Abstract: Recent progress in visual navigation has largely been driven by scale: end-to-end policies with hundreds of millions of parameters trained on billions of frames or large-scale simulated data. We ask how much of this scale a single task family actually requires, and what structure can substitute for it. We propose a decomposed navigation model in which operations with known closed-form structure, such as projective geometry, occupancy, and coordinate transforms, are computed analytically and serve as interfaces between three small learned modules: an egress predictor that grounds the episode goal as a local subgoal in the current view, a navigation predictor that estimates a goal-conditioned posterior over where trajectories travel, and an endpoint-pinned residual diffusion generator that samples trajectory shapes from this posterior. The system trains only 0.58M out of a total of 22.7M parameters, on 44k frames in under one GPU-hour, yet approaches the performance of state-of-the-art models on navigation tasks across 6060 point-goal episodes and 60 environments, while having 233x fewer trainable parameters, the lowest collision rate among all evaluated methods, and 50 Hz inference speed. The decomposition further transfers to no-goal exploration by retraining only the 123k-parameter egress head, and its failure modes under sensor corruption are transparent and analytically correctable.
Authors: Ting-Wei Ou, Huang-Ting Lin, Kuu-Young Young
Abstract: Reliable visual data association is fundamental to visual SLAM (V-SLAM), as it directly determines the quality of the camera pose estimation and map consistency. However, the handcrafted descriptors used by most mature real-time systems degrade under illumination and viewpoint changes, while learning-based front-ends that address this weakness typically require replacing the extraction-and-matching pipeline and introduce substantial computational overhead. Descriptor enhancement offers a compromise by refining existing descriptors within their original format, yet current methods rely on simplified attention mechanisms whose limited contextual modeling constrains the achievable matching quality. To resolve this trade-off between contextual expressiveness and efficiency, we propose Desc++, a lightweight enhancement module that jointly encodes descriptor representations and keypoint geometry and aggregates spatial context through a hybrid architecture that combines order-agnostic global attention with geometry-aware sequential modeling in linear time. The enhanced descriptors retain their original dimensionality and matching interface, enabling integration into deployed V-SLAM systems without modifying the pipeline. Experiments across descriptor matching, correspondence analysis, and system-level benchmarks with four different V-SLAM systems demonstrate that Desc++ improves matching accuracy over the state-of-the-art enhancement method, translates these gains into more accurate and stable trajectory estimation, and achieves a favorable balance between accuracy and efficiency for practical integration into existing real-time V-SLAM pipelines.
Authors: Raviteja Boddu, Guilherme Vieira Leite, Joed Lopes da Silva, \^Angelo Benetti, Isabela Barbieri, Nat\'alia de Melo Afonso, Thyago Santos, Helio Pedrini, Felipe Ven\^ancio Barbosa, Jos\'e Mario De Martino, Munir Georges, Alessandro Zimmer
Abstract: This paper addresses the challenges of using sign language within shared mobility services, such as taxis, carpools, or ride-sharing platforms. The use of sign language recognition (SLR) in real-world, confined environments, specifically vehicle interiors remains largely unexplored. To motivate research in this area, we present the In-Car Sign Language (ICSL) dataset for Brazilian Sign Language (Libras), with the long-term goal of improving public transport accessibility for the Deaf and Hard-of-Hearing community. The dataset consists of: (1) high-precision laboratory motion capture (MoCap) data to establish an idealized linguistic baseline and (2) real-world multi-modal in-car recordings captured using a 2D camera and 3D Time-of-Flight sensors. The dataset provides a basis for comparative analyses between synthesized signing avatar animations and recorded real signing interpreter videos, which enable future research into robust "in-the-wild" SLR models and domain adaptation. We describe in detail the use cases, the setup, the data collection protocol, and the metadata structure of the corpus. In total, we recorded a multimodal dataset exceeding 1.5 million frames, comprising the synchronized multimodal streams described above featuring Libras users across various in-car scenarios. The corpus is provided with gloss annotation of lexical signs and non-lexical sign language elements specially designed to support the training and evaluation of deep neural networks for constrained space recognition. In-vehicle signing offers a technically significant example of a constrained, occluded, and non-frontal environment. While recognizing the diverse communication strategies already employed by the Deaf community, identifying automotive-specific limitations provides a useful stepping stone for research into enhancing in-car accessibility and passenger quality of life.
Authors: Christos Kanakis, Mathias Perslev, Tim Schakel, Silvia Ingala, Akshay Pai, Dennis Klomp, Chantal M. W. Tax
Abstract: Diffusion-weighted imaging (DWI) is acquired as part of bi-parametric prostate MRI, but suffers from artifacts that degrade downstream quantitative and diagnostic performance. While DWI preprocessing is standard in brain imaging, its adoption in prostate imaging remains limited and lacks standardized pipelines. This study investigated the effect of different DWI preprocessing strategies on apparent diffusion coefficient (ADC) estimation and automatic Prostate Imaging Reporting and Data System (PI-RADS) classification. 268 cases were derived from the fastMRI prostate cohort by sequentially applying denoising, Gibbs-ringing correction, and diffeomorphic registration for susceptibility distortion correction. ADC maps were compared using linear least squares (LLS) and iteratively-weighted LLS (IWLLS). A 3-class DenseNet classifier was trained to predict PI-RADS scores from multi-channel MRI inputs. ADC analysis revealed statistically significant differences across preprocessing pipelines, with LLS and IWLLS producing numerically equivalent maps. Linear relationships between ADC values were preserved across most datasets (PCC ~0.99), while distortion correction realigned DWI to T2w anatomy and altered ADC values accordingly (PCC ~0.90). Classification showed the best AUROC and sensitivity for high-risk PI-RADS classes in the fully processed dataset. False-negative analysis revealed this dataset produced the least overconfident incorrect predictions on high-risk classes, which is a desirable property for clinical triage. DWI preprocessing, particularly distortion correction, enhances both ADC map quality and the predictive power of deep learning models for PI-RADS classification, supporting the need for optimized preprocessing pipelines in prostate MRI.
Authors: Thi Kim Trang Vo, Nghia Hieu Nguyen, Ha Minh Tan
Abstract: Translating Han-Nom manuscripts into modern Vietnamese is challenging because historical pages are often degraded, the script contains rare logographic characters, and parallel supervision is limited. We propose a multimodal RLHF preference-alignment framework that conditions Vietnamese generation on manuscript images and aligned Han-Nom source text. The model combines four streams: CLIP ViT-L/14@336 for visual features, bert-base-chinese for Han-Nom representations, vinai/phobert-base for Vietnamese representations, and T5-small encoder states. Modality-specific projections and a fusion block compress the resulting 2,048-dimensional concatenation into a shared 512-dimensional representation. Starting from the same supervised fine-tuned policy, we compare PPO, DPO, and KTO under matched work-level macro-averaged evaluation. DPO achieves the best BLEU-4, ROUGE-L, BERTScore, semantic similarity, CER, WER, and token accuracy, whereas PPO obtains the highest precision, recall, and F1. KTO remains competitive through its desirable-undesirable utility objective. All preference-aligned policies improve the BLEU-4 and semantic-similarity scores available for the SFT baseline. These results indicate that multimodal preference optimization complements supervised learning by improving lexical and semantic quality in low-resource historical translation.
Authors: Yijun Chen, Boyi Xiao, Yixian Zhao, Haoting Xia, Buqiang Xu, Jizhan Fang, Yanya Li, Yaqi Zheng, Xuehai Wang, Zirui Xue, Liuxin Zhang, Hui Li, Ningyu Zhang
Abstract: Personal AI assistants on mobile and wearable devices continuously perceive users' daily lives through visual and audio streams. However, answering queries about past experiences requires lightweight multimodal memory that can continuously accumulate, organize, and retrieve long-term experiences, which remains challenging. To address this challenge, we present LightMem-Ego, a lightweight streaming multimodal memory system for everyday-life assistance. The system continuously captures egocentric visual and audio streams, aligns them on a shared timeline, and organizes them into a hierarchical memory consisting of current, short-term, and long-term memory. Given a user query, LightMem-Ego dynamically routes retrieval to the appropriate memory level and generates answers grounded in multimodal evidence. The demonstration can be deployed on smartphones and AI glasses, supporting object finding, conversation recall, life summarization, routine discovery, and personalized assistance. Code is available at https://github.com/zjunlp/LightMem-Ego.
Authors: Abdulkader Helwan, Lina Abou-Abbas, Hussein El Amouri, Belkacem Chikhaoui, Khadidja Henni
Abstract: Deep learning for EEG-based seizure detection faces critical challenges: severe annotation scarcity and extreme class imbalance, where ictal events comprise less than 10\% of clinical recordings. We present DiffEEG, a 9.6M-parameter self-supervised foundation model that addresses both limitations through denoising diffusion pre-training and reinforcement learning (RL)-based fine-tuning. Pre-trained on 1.3M unlabeled segments from the Temple University Hospital Seizure Corpus (TUHSZ), DiffEEG learns generic neural representations via a 1D U-Net with multi-head self-attention. For downstream adaptation, a reinforced decision layer employs policy gradient optimization to directly maximize F1-score, prioritizing sensitivity to rare seizure events over overall accuracy. Under strict patient-wise evaluation (279 patients, Leave-One-Fold-Out), DiffEEG achieves 61\% accuracy and 59\% F1 for 4-class seizure subtyping, and 81\% accuracy with 85\% weighted F1 for binary detection, maintaining clinically viable seizure recall (59\%) despite extreme imbalance (6.7\% prevalence). Segment-level evaluation establishes an upper bound of 97.6\% accuracy, confirming strong architectural capacity. DiffEEG demonstrates that diffusion-based pre-training combined with metric-aware reinforcement learning enables clinically deployable seizure monitoring with minimal labeled data requirements.
Authors: Zhiyang Dou, John U. Onyemelukwe, Hangxing Zhang, Heng Zhang, Minghao Guo, Yunsheng Tian, Michal Piotr Lipiec, Joshua Jacob, Chao Liu, Peter Yichen Chen, Yuri Ivanov, Wojciech Matusik
Abstract: Differentiable simulators have advanced policy learning and model-based control, yet actuator dynamics remain an important source of sim-to-real error. This is particularly acute on low-cost platforms, where the linear current-to-torque relation $\tau = K_tI$ becomes unreliable during commanded-target tracking because of friction, hysteresis, backlash, and thermal effects. We present NeuralActuator, a neural actuator model that jointly predicts (i) a simulator-equivalent generalized-effort surrogate for trajectory propagation on low-cost servo platforms, (ii) external force with a contact-probability gate for sensorless force perception, and (iii) a motor-condition score for the supervised joint. We also introduce the Neural Actuation Dataset (NAD), collected with a twin-arm teleoperation system that records robot states and actuator telemetry together with external-force labels. The torque-surrogate head is trained through differentiable simulation from pose trajectories without direct generalized-effort labels, while the force, gate, and motor-condition heads receive direct supervision. A Transformer captures temporal dependencies while supporting real-time inference. We evaluate NeuralActuator on a 5-DoF OpenManipulator-X, a 6-DoF SO-101, and a 7-DoF Franka Emika Panda, spanning three actuator families and platforms costing approximately USD 500 to over USD 30,000. The low-cost platforms support dynamics and force evaluation, while the offline Franka experiment provides an additional payload-force-estimation benchmark. Experiments further demonstrate its application for motor condition estimation on OpenManipulator-X and improved behavior-cloning performance when NeuralActuator is used as a pretrained module.
Authors: Mohammad Reza Karimi Dastjerdi, Dominique Tanguay-Gaudreau, Fr\'ed\'eric Fortier-Chouinard, Yannick Hold-Geoffroy, Nima Kalantari, Jean-Fran\c{c}ois Lalonde
Abstract: Most novel view synthesis methods -- including Neural Radiance Fields (NeRF) -- struggle to capture the high dynamic range (HDR) radiance required for realistic image-based lighting (IBL). This limitation stems from a reliance on low dynamic range (LDR) imagery, which fails to capture the intensity of light sources found in indoor environments. While exposure bracketing can recover this range, it is often too slow for practical, large-scale acquisition. In this work, we introduce PanDORA: PANoramic Dual-Observer Radiance Acquisition, a system specifically designed for the fast and affordable capture of high-quality HDR radiance maps for IBL. Our approach utilizes two 360{\deg} cameras mounted on a portable monopod to simultaneously record videos at different exposures. These videos are processed by our proposed two-stage NeRF-based algorithm featuring a novel self-calibrating pipeline to estimate camera parameters. This pipeline produces non-saturated HDR radiance fields that accurately capture the radiance of a scene. When evaluated on a new dataset of real indoor environments featuring HDR ground truth lighting, PanDORA demonstrates superior fidelity in reconstructing the peak intensities necessary for downstream rendering tasks, providing a scalable and efficient solution for capturing real-world IBLs.
Authors: Martin Mayr, Marcel Dreier, Florian Kordon, Mathias Seuret, Jochen Z\"ollner, Fei Wu, Andreas Maier, Vincent Christlein
Abstract: The imitation of cursive handwriting is mainly limited to generating handwritten words or lines. Multiple synthetic outputs must be stitched together to create paragraphs or whole pages, whereby consistency and layout information are lost. To close this gap, we propose a method for imitating handwriting at the paragraph level that also works for unseen writing styles. Therefore, we introduce a modified latent diffusion model that enriches the encoder-decoder mechanism with specialized loss functions that explicitly preserve the style and content. We enhance the attention mechanism of the diffusion model with adaptive 2D positional encoding and the conditioning mechanism to work with two modalities simultaneously: a style image and the target text. This significantly improves the realism of the generated handwriting. We set a new benchmark in our comprehensive evaluation, achieving 61 % mAP and 56 % top-1 accuracy in style preservation, significantly outperforming the previous best method (37 % mAP, 30 % top-1). We are making our code publicly available for reproducibility, supporting research in this area and research into potential countermeasures: https://github.com/M4rt1nM4yr/paragraph_handwriting_imitation_ldm
URLs: https://github.com/M4rt1nM4yr/paragraph_handwriting_imitation_ldm
Authors: Rajat Modi, Vibhav Vineet, Yogesh Singh Rawat
Abstract: This paper explores the impact of occlusions in video action detection. We facilitate this study by introducing five new benchmark datasets namely O-UCF and O-JHMDB consisting of synthetically controlled static/dynamic occlusions, OVIS-UCF and OVIS-JHMDB consisting of occlusions with realistic motions and Real-OUCF for occlusions in realistic-world scenarios. We formally confirm an intuitive expectation: existing models suffer a lot as occlusion severity is increased and exhibit different behaviours when occluders are static vs when they are moving. We discover several intriguing phenomenon emerging in neural nets: 1) transformers can naturally outperform CNN models which might have even used occlusion as a form of data augmentation during training 2) incorporating symbolic-components like capsules to such backbones allows them to bind to occluders never even seen during training and 3) Islands of agreement can emerge in realistic images/videos without instance-level supervision, distillation or contrastive-based objectives2(eg. video-textual training). Such emergent properties allow us to derive simple yet effective training recipes which lead to robust occlusion models inductively satisfying the first two stages of the binding mechanism (grouping/segregation). Models leveraging these recipes outperform existing video action-detectors under occlusion by 32.3% on O-UCF, 32.7% on O-JHMDB & 2.6% on Real-OUCF in terms of the vMAP metric. The code for this work has been released at https://github.com/rajatmodi62/OccludedActionBenchmark.
URLs: https://github.com/rajatmodi62/OccludedActionBenchmark.
Authors: Rajat Modi, Yogesh Singh Rawat
Abstract: In this work, we propose Asynchronous Perception Machine (APM), a computationally-efficient architecture for test-time-training (TTT). APM can process patches of an image one at a time in any order asymmetrically and still encode semantic-awareness in the net. We demonstrate APM's ability to recognize out-of-distribution images without dataset-specific pre-training, augmentation or any-pretext task. APM offers competitive performance over existing TTT approaches. To perform TTT, APM just distills test sample's representation once. APM possesses a unique property: it can learn using just this single representation and starts predicting semantically-aware features. APM demostrates potential applications beyond test-time-training: APM can scale up to a dataset of 2D images and yield semantic-clusterings in a single forward pass. APM also provides first empirical evidence towards validating GLOM's insight, i.e. input percept is a field. Therefore, APM helps us converge towards an implementation which can do both interpolation and perception on a shared-connectionist hardware. Our code is publicly available at this link: https://rajatmodi62.github.io/apm_project_page/.
Authors: Xiangyong Lu, Masanori Suganuma, Takayuki Okatani
Abstract: In real-world applications of image recognition tasks, such as human pose estimation, cameras often capture objects, like human bodies, at low resolutions. This scenario poses a challenge in extracting and leveraging multi-scale features, which is often essential for precise inference. To address this challenge, we propose a new attention mechanism, named cascaded multi-scale attention (CMSA), tailored for use in CNN-ViT hybrid architectures, to handle low-resolution inputs effectively. The design of CMSA enables the extraction and seamless integration of features across various scales without necessitating the downsampling of the input image or feature maps. This is achieved through a novel combination of grouped multi-head self-attention mechanisms with window-based local attention and cascaded fusion of multi-scale features over different scales. This architecture allows for the effective handling of features across different scales, enhancing the model's ability to perform tasks such as human pose estimation, head pose estimation, and more with low-resolution images. Our experimental results show that the proposed method outperforms existing state-of-the-art methods in these areas with fewer parameters, showcasing its potential for broad application in real-world scenarios where capturing high-resolution images is not feasible. Code is available at https://github.com/xyongLu/CMSA.
Authors: Jun Hu, Zhang Chen, Zhong Li, Yi Xu, Juyong Zhang
Abstract: Recently, several studies have combined Gaussian Splatting to obtain scene representations with language embeddings for open-vocabulary 3D scene understanding. While these methods perform well, they essentially require very dense multi-view inputs, limiting their applicability in real-world scenarios. In this work, we propose SparseLGS to address the challenge of 3D scene understanding with pose-free and sparse view input images. Our method leverages a learning-based dense stereo model to handle pose-free and sparse inputs, and a three-step region matching approach to address the multi-view semantic inconsistency problem, which is especially important for sparse inputs. Different from directly learning high-dimensional CLIP features, we extract low-dimensional information and build bijections to avoid excessive learning and storage costs. We introduce a reconstruction loss during semantic training to improve Gaussian positions and shapes. To the best of our knowledge, we are the first to address the 3D semantic field problem with sparse pose-free inputs. Experimental results show that SparseLGS achieves comparable quality when reconstructing semantic fields with fewer inputs (3-4 views) compared to previous SOTA methods with dense input. Besides, when using the same sparse input, SparseLGS leads significantly in quality and heavily improves the computation speed (5$\times$speedup). Project page: https://ustc3dv.github.io/SparseLGS
Authors: Potito Aghilar, Vito Walter Anelli, Michelantonio Trizio, Eugenio Di Sciascio, Tommaso Di Noia
Abstract: Diffusion models have recently unlocked new possibilities in editing images of real-world objects. Yet, transforming objects in non-rigid ways, such as modifying poses or applying image-based conditioning, continues to present significant challenges. Retaining the unique identity of objects during these edits is a complex task, and current techniques often fall short of delivering the precision needed for industrial settings, where consistency is non-negotiable. Additionally, adapting diffusion models demands custom training data, which is often unavailable in real-world scenarios. To address these gaps, we present FashionRepose, a novel, training-free pipeline designed to handle non-rigid pose adjustments specifically for the fashion industry. This approach combines pretrained off-the-shelf models to modify the poses of long-sleeve garments while safeguarding their identity and branding characteristics. By adopting a zero-shot methodology, FashionRepose enables near real-time edits, entirely eliminating the requirement for specialized training data. FashionRepose has been deployed for a global fashion firm, OVS, handling more than 30,000 long-sleeve garments.
Authors: Parsa Hosseini, Sumit Nawathe, Mazda Moayeri, Sriram Balasubramanian, Soheil Feizi
Abstract: Unimodal vision models are known to rely on spurious correlations, but it remains unclear to what extent Multimodal Large Language Models (MLLMs) exhibit similar biases despite language supervision. In this paper, we investigate spurious bias in MLLMs and introduce SpurLens, a pipeline that leverages GPT-4 and open-set object detectors to automatically identify spurious visual cues without human supervision. Our findings reveal that spurious correlations cause two major failure modes in MLLMs: (1) over-reliance on spurious cues for object recognition, where removing these cues reduces accuracy, and (2) object hallucination, where spurious cues amplify the hallucination by over 10x. We validate our findings in various MLLMs and datasets. Beyond diagnosing these failures, we explore potential mitigation strategies, such as prompt ensembling and reasoning-based prompting, and conduct ablation studies to examine the root causes of spurious bias in MLLMs. By exposing the persistence of spurious correlations, our study calls for more rigorous evaluation methods and mitigation strategies to enhance the reliability of MLLMs.
Authors: Shenghui Chen, Po-han Li, Sandeep Chinchali, Ufuk Topcu
Abstract: Many decision-making tasks, where both accuracy and efficiency matter, still require human supervision. For example, tasks like traffic officers reviewing hour-long dashcam footage or researchers screening conference videos can benefit from concise summaries that reduce cognitive load and save time. Yet current vision-language models (VLMs) often produce verbose, redundant outputs that hinder task performance. Existing video caption evaluation depends on costly human annotations and overlooks the summaries' utility in downstream tasks. We address these gaps with Video-to-text Information Bottleneck Evaluation (VIBE), an annotation-free method that scores VLM outputs using two metrics: grounding (how well the summary aligns with visual content) and utility (how informative it is for the task). VIBE selects from randomly sampled VLM outputs by ranking them according to the two scores to support effective human decision-making. Human studies on LearningPaper24, SUTD-TrafficQA, and LongVideoBench show that summaries selected by VIBE consistently improve performance-boosting task accuracy by up to 61.23% and reducing response time by 75.77% compared to naive VLM summaries or raw video.
Authors: Ruize Yang, Ann Kennedy, R. James Cotton
Abstract: Advances in markerless motion capture are making high-quality biomechanical data increasingly accessible, creating a growing need for scalable downstream analytics. Building a bespoke pipeline for each analysis task is time-consuming, motivating models that can flexibly handle diverse clinical questions within a single framework. Recent work has shown that fine-tuning language models to accept tokenized motion as an additional modality enables descriptive captioning of movement, raising the question of whether these models are also capable of clinically relevant motion understanding, where diverse tasks and annotations provide a natural testbed. We investigate whether such a multimodal motion--language model can answer detailed, clinically meaningful questions about movement. We collected 71 hours of biomechanical data from 750 participants, many with movement impairments, performing tasks commonly used in clinical assessment. To further expand the training dataset, we designed a cross-format tokenizer that directly encodes motion data from heterogeneous formats into a shared latent space without paired data, allowing a second dataset to be incorporated and enabling pooling annotations across datasets. From these tokenized representations, we constructed a multimodal dataset of motion-related question--answer pairs and used it to train BiomechGPT, a multimodal biomechanics--language model. BiomechGPT achieves competitive performance across a range of clinically relevant tasks, with performance scaling with both dataset and model size. It offers a new way for clinicians and researchers to interact with biomechanical data and represents a promising direction for rehabilitation-focused movement analysis. Project page: https://intelligentsensingandrehabilitation.github.io/BiomechGPT/
URLs: https://intelligentsensingandrehabilitation.github.io/BiomechGPT/
Authors: Xinyu Wei, Jinrui Zhang, Zeqing Wang, Hongyang Wei, Zhen Guo, Bairui Li, Lei Zhang
Abstract: The rapid advancements of Text-to-Image (T2I) models have ushered in a new phase of AI-generated content, marked by their growing ability to interpret and follow user instructions. However, existing T2I model evaluation benchmarks fall short in limited prompt diversity and complexity, as well as coarse evaluation metrics, making it difficult to evaluate the fine-grained alignment performance between textual instructions and generated images. In this paper, we present TIIF-Bench Text-to-Image Instruction Following Benchmark), aiming to systematically assess T2I models' ability in interpreting and following intricate textual instructions. TIIF-Bench comprises 5,000 prompts organized along multiple dimensions and categorized into three levels of difficulty and complexity. To rigorously evaluate robustness to prompt length, each prompt is provided in both short and long versions with identical core semantics. We further propose a novel Global Normalized Edit Distance (GNED) metric for text rendering and provide aspect-ratio-diverse reference images for each prompt to assess style control. In addition, we collect 100 high-quality designer-level prompts covering diverse scenarios for comprehensive evaluation. To enable scalable and fine-grained evaluation, we explore the best paradigm for leveraging the world knowledge encoded in large Vision-Language Models (VLMs) as automated binary evaluators. Through extensive ablations, we develop a fully reproducible evaluator that provides interpretable reasoning and reliable verification, enabling our benchmark to discern subtle variations in T2I model outputs. Through comprehensive benchmarking of mainstream T2I models on TIIF-Bench, we analyze the strengths and weaknesses of current T2I systems and reveal the limitations of existing evaluation benchmarks. Project Page: https://a113n-w3i.github.io/TIIF_Bench/.
Authors: Yuan Zhang, Chun-Kai Fan, Sicheng Yu, Junwen Pan, Tao Huang, Ming Lu, Kuan Cheng, Qi She, Shanghang Zhang
Abstract: Inspired by text prompts in large language models, visual prompts have been explored to enhance the perceptual capabilities of large vision-language models (LVLMs). However, performance tends to saturate under single visual prompt designs, making further prompt engineering increasingly ineffective. To address this limitation, we shift from prompt engineering to prompt retrieval and propose AutoV, a lightweight framework for instance-adaptive visual prompt identification. Given an input image and a textual query, AutoV automatically locates the most suitable visual prompt from a diverse candidate pool. Training such a retrieval framework requires prompt-level supervision, yet prompt quality is inherently ambiguous and difficult to assess reliably, even for humans. To enable automatic supervision, we evaluate visual prompts using a pre-trained LVLM and label them according to their prediction losses. Using the loss-oriented ranking as a robust training signal, AutoV learns to retrieve the query-aware optimal prompt for each instance without manual annotation. Experiments indicate that AutoV enhances the performance of various LVLMs on image understanding, captioning, grounding, and classification tasks. For example, AutoV improves LLaVA-OV by $\textbf{10.2}\%$ on VizWiz and boosts Qwen2.5-VL by $\textbf{3.8}\%$ on MMMU, respectively.
Authors: Michal Heker, Sefy Kagarlitsky, David Tolpin
Abstract: We introduce a principled, data-driven approach for modeling a neural prior over human body poses using normalizing flows. Unlike heuristic or low-expressivity alternatives, our method leverages RealNVP to learn a flexible density over poses represented in the 6D rotation format. We address the challenge of modeling distributions on the manifold of valid 6D rotations by inverting the Gram-Schmidt process during training, enabling stable learning while preserving downstream compatibility with rotation-based frameworks. Our architecture and training pipeline are framework-agnostic and easily reproducible. We demonstrate the effectiveness of the learned prior through both qualitative and quantitative evaluations, and we analyze its impact via ablation studies. This work provides a sound probabilistic foundation for integrating pose priors into human motion capture and reconstruction pipelines.
Authors: Nisreen Albzour, Sarah S. Lam
Abstract: Cervical cancer remains a significant global health concern and a leading cause of cancer-related deaths among women. Early detection through Pap smear tests is essential to reduce mortality rates; however, the manual examination is time consuming and prone to human error. This study proposes a deep learning framework that integrates U-Net for segmentation and a classification model to enhance diagnostic performance. The Herlev Pap Smear Dataset, a publicly available cervical cell dataset, was utilized for training and evaluation. The impact of segmentation on classification performance was evaluated by comparing the model trained on segmented images and another trained on non-segmented images. Experimental results showed that the use of segmented images marginally improved the model performance on precision (about 0.41 percent higher) and F1-score (about 1.30 percent higher), which suggests a slightly more balanced classification performance. While segmentation helps in feature extraction, the results showed that its impact on classification performance appears to be limited. The proposed framework offers a supplemental tool for clinical applications, which may aid pathologists in early diagnosis.
Authors: Yihong Chen, Jiancheng Yang, Deniz Sayin Mercadier, Hieu Le, Juerg Schwitter, Pascal Fua
Abstract: Reconstructing cardiac motion from CMR sequences is critical for diagnosis, prognosis, and intervention. Existing methods rely on complete CMR stacks to infer full heart motion, limiting their applicability during intervention when only sparse observations are available. We present TetHeart, the first end-to-end framework for unified 4D heart mesh recovery from both offline full-stack and intra-procedural sparse-slice observations. Our method leverages deformable tetrahedra to capture shape and motion in a coherent space shared across cardiac structures. Before a procedure, it initializes detailed, patient-specific heart meshes from high-quality full stacks, which can then be updated using whatever slices can be obtained in real-time, down to a single one during the procedure. TetHeart incorporates several key innovations: (i) an attentive slice-adaptive 2D-3D feature assembly mechanism that integrates information from arbitrary numbers of slices at any position; (ii) a distillation strategy to ensure accurate reconstruction under extreme sparsity; and (iii) a weakly supervised motion learning scheme requiring annotations only at keyframes, such as the end-diastolic and end-systolic phases. Trained and validated on three large public datasets and evaluated zero-shot on additional private interventional and public datasets without retraining, TetHeart achieves state-of-the-art accuracy and strong generalization in both pre- and intra-procedural settings. Code and dataset is available at https://github.com/Scalsol/TetHeart.
Authors: Adam Romlein, Benjamin X. Hou, Yuval Boss, Cynthia L. Christman, Stacie Koslovsky, Erin E. Moreland, Jason Parham, Anthony Hoogs
Abstract: We introduce KAMERA: a comprehensive system for multi-camera, multi-spectral synchronization and real-time detection of seals and polar bears. Utilized in aerial surveys for ice-associated seals in the Bering, Chukchi, and Beaufort seas around Alaska, KAMERA provides up to an 80% reduction in dataset processing time over previous methods. Our rigorous calibration and hardware synchronization enable using multiple spectra for object detection. All collected data are annotated with metadata so they can be easily referenced later. All imagery and animal detections from a survey are mapped onto a world plane for accurate surveyed area estimates and quick assessment of survey results. We hope KAMERA will inspire other mapping and detection efforts in the scientific community, with all software, models, and schematics fully open-sourced.
Authors: Yu Zhao, Ying Zhang, Xuhui Sui, Baohang Zhou, Xinying Qian, Li Shen, Dacheng Tao
Abstract: Knowledge-based Visual Question Answering (KBVQA) necessitates external knowledge incorporation beyond cross-modal understanding. Existing KBVQA methods either utilize implicit knowledge in multimodal large language models via in-context learning or explicit knowledge via retrieval augmented generation. However, their reasoning processes remain implicit, without explicit multi-step trajectories. To address this gap, we propose a Self-Encouraged Hindsight Distillation Reasoning (HinD) framework, aiming at eliciting reasoning ability inside the MLLM by constructing a Hindsight Teacher with privileged information to teach the Foresight Student. First, we construct the Hindsight Teacher by prompting the MLLM with the reasoning target as privileged information to complete the reasoning process, obtaining Hindsight-Zero training data. Then, the Foresight Student, without knowing the answer, learns the golden trajectories from Hindsight in two ways: (1) Hindsight Distillation Fine-Tuning to self-distill the Hindsight-Zero into a modularized Chain-of-Thought Generator and a Knowledge Generator for sequential steps and discrete facts generation, respectively; (2) Knowledge Encouragement Preference Optimization to encourage the under-confident but relevant knowledge inside the MLLM and suppress the over-confident but irrelevant one. Experiments on OK-VQA and A-OKVQA validate the effectiveness of HinD, showing that HinD with 7-8B MLLM achieves superior performance without commercial model APIs or retrieved knowledge.
Authors: Xinliang Wang, Yijie Kang, Zhenyu Wu, Yifeng Shi
Abstract: 3D urban generation from satellite imagery is an important task for scalable digital twins and real-world simulation environments. Existing approaches primarily rely on scene-level generation paradigms, which often require large-scale 3D city assets and struggle with controllability, geographic alignment, and realistic appearance grounding in real-world urban environments. To address these limitations, we present Sat2RealCity, a grounded urban generation framework that leverages object-level 3D generative priors for scalable city synthesis from satellite imagery. Our framework decomposes cities into geographically grounded building entities, enabling the reuse of pretrained object-level 3D generative priors while preserving real-world spatial structures. Supported by our constructed BuildVerse3D dataset, (1) we introduce an OpenStreetMap (OSM)-guided spatial grounding strategy to inject geospatial constraints into the 3D generation process; (2) we design an appearance-guided controllable generation mechanism for realistic architectural appearance and regional style consistency; and (3) we construct an MLLM-powered semantic pipeline for regional appearance understanding and semantic-aware appearance synthesis. Extensive experiments demonstrate that Sat2RealCity achieves strong geographic alignment, regional stylistic consistency, and plausible urban asset synthesis compared with existing urban generation and 3D asset generation approaches.
Authors: Yuhao Wan, Lijuan Liu, Jingzhi Zhou, Zihan Zhou, Xuying Zhang, Dongbo Zhang, Shaohui Jiao, Qibin Hou, Ming-Ming Cheng
Abstract: Previous works that leverage video models for image-to-3D scene generation often suffer from geometric distortions and blurry content. Using video generation models to implicitly maintain geometric consistency according to a single-frame input is ineffective. In this paper, we present a two-stage method, named $\textbf{GeoWorld}$, that renovates the image-to-3D scene generation pipeline by providing full-frame geometry features. The first-stage video generation model, followed by a multi-view geometry model, produces $\textbf{full-frame}$ geometry features, which are then used as a mental draft of geometric conditions to aid the second-stage video-generation model. A geometric loss is proposed to impose real-world geometric constraints, and a geometry adaptation module is introduced to ensure the effective utilization of geometry features. Thanks to full-frame geometric modeling, the two smaller video models in our two-stage method can generate higher-fidelity 3D scenes than SOTA methods, while being even faster, e.g. 7.5$\times$ faster than Hunyuan-Voyager. Project page: https://peaes.github.io/GeoWorld.
Authors: Qiming Li, Xiaocheng Feng, Yixuan Ma, Zekai Ye, Ruihan Chen, Xiachong Feng, Bing Qin
Abstract: Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) demonstrate strong reasoning capabilities, yet their performance in English significantly outperforms that in low-resource languages, raising fairness concerns in multilingual applications. Existing approaches either rely on costly multilingual training or employ prompting with external translation tools, both of which are resource-intensive and sensitive to translation quality. To address these limitations, we propose a training-free inference-time method to enhance Multilingual Reasoning capabilities via Representation Engineering (MRRE) without using any additional training data or tools. MRRE sequentially injects two precomputed vectors at specific layers during inference processing: cross-lingual reasoning enhancement vectors, which steer non-English reasoning representations toward English space to unlock multilingual reasoning, and target-language output anchoring vectors, which restore the distribution of the target language to preserve input-output language consistency. Comprehensive experiments across six advanced LLMs and LVLMs on four reasoning benchmarks demonstrate that MRRE consistently enhances non-English reasoning by an average gain of 5.48% and up to 7.54% in low-resource languages (Thai and Swahili), while improving input-output language consistency by 3.78%.
Authors: Peizheng Li, Zhenghao Zhang, David Holtz, Hang Yu, Yutong Yang, Yuzhi Lai, Rui Song, Andreas Geiger, Andreas Zell
Abstract: End-to-end autonomous driving methods built on vision language models (VLMs) have undergone rapid development driven by their universal visual understanding and strong reasoning capabilities obtained from the large-scale pretraining. However, we find that current VLMs struggle to understand fine-grained 3D spatial relationships which is a fundamental requirement for systems interacting with the physical world. To address this issue, we propose SpaceDrive, a spatial-aware VLM-based driving framework that treats spatial information as explicit positional encodings (PEs) instead of textual digit tokens, enabling joint reasoning over semantic and spatial representations. SpaceDrive employs a universal positional encoder to all 3D coordinates derived from multi-view depth estimation, historical ego-states, and text prompts. These 3D PEs are first superimposed to augment the corresponding 2D visual tokens. Meanwhile, they serve as a task-agnostic coordinate representation, replacing the digit-wise numerical tokens as both inputs and outputs for the VLM. This mechanism enables the model to better index specific visual semantics in spatial reasoning and directly regress trajectory coordinates rather than generating digit-by-digit, thereby enhancing planning accuracy. Extensive experiments validate that SpaceDrive achieves state-of-the-art open-loop performance on the nuScenes dataset and the second-best Driving Score of 78.02 on the Bench2Drive closed-loop benchmark over existing VLM-based methods. Code is available at: https://github.com/zhenghao2519/SpaceDrive.
Authors: Yannan He, Garvita Tiwari, Xiaohan Zhang, Pankaj Bora, Tolga Birdal, Jan Eric Lenssen, Gerard Pons-Moll
Abstract: We introduce MoLingo, a text-to-motion (T2M) model that generates realistic, lifelike human motion by denoising in a continuous latent space. Recent works perform latent space diffusion, either on the whole latent at once or auto-regressively over multiple latents. In this paper, we study how to make diffusion on continuous motion latents work best. We focus on two questions: (1) how to build a semantically aligned latent space so diffusion becomes more effective, and (2) how to best inject text conditioning so the motion follows the description closely. We propose a semantic-aligned motion encoder trained with frame-level text labels so that latents with similar text meaning stay close, which makes the latent space more diffusion-friendly. We also compare single-token conditioning with a multi-token cross-attention scheme and find that cross-attention gives better motion realism and text-motion alignment. With semantically aligned latents, auto-regressive generation, and cross-attention text conditioning, our model sets a new state of the art in human motion generation on standard metrics and in a user study. We will release our code and models for further research and downstream usage.
Authors: Kotaro Funakoshi, Yaoxiong Zhu
Abstract: Recognition of signers' emotions suffers from one theoretical challenge and one practical challenge, namely, the overlap between grammatical and affective facial expressions and the scarcity of data for model training. This paper addresses these two challenges in a cross-lingual setting using our eJSL dataset, a new benchmark dataset for emotion recognition in Japanese Sign Language signers, and BOBSL, a large British Sign Language dataset with subtitles. In eJSL, two signers expressed 78 distinct utterances with each of seven different emotional states, resulting in 1,092 video clips. We empirically demonstrate that 1) textual emotion recognition in spoken language mitigates data scarcity in sign language, 2) temporal segment selection has a significant impact, and 3) incorporating hand motion enhances emotion recognition in signers. Finally we establish a stronger baseline than spoken language LLMs.
Authors: Hui Li, Fu-Yun Wang, Haoyuan Xia, Jiayue Lyu, Kaihui Cheng, Siyu Zhu, Jingdong Wang
Abstract: This paper studies the training-testing discrepancy (a.k.a. exposure bias) problem for improving the diffusion models. During training, the input of a prediction network at one training timestep is the corresponding ground-truth noisy data that is an interpolation of the noise and the data, and during testing, the input is the generated noisy data. We present a novel training approach, named MixFlow, for improving the performance. Our approach is motivated by the Slow Flow phenomenon: the ground-truth interpolation that is the nearest to the generated noisy data at a given sampling timestep is observed to correspond to a higher-noise timestep (termed slowed timestep), i.e., the corresponding ground-truth timestep is slower than the sampling timestep. MixFlow leverages the interpolations at the slowed timesteps, named slowed interpolation mixture, for post-training the prediction network for each training timestep. Experiments over class-conditional image generation (including SiT, REPA, and RAE) and text-to-image generation validate the effectiveness of our approach. Our approach MixFlow over the RAE models achieve strong generation results on ImageNet: 1.43 FID (without guidance) and 1.10 (with guidance) at 256 x 256, and 1.55 FID (without guidance) and 1.10 (with guidance) at 512 x 512.
Authors: Yongkun Du, Zhineng Chen, Yazhen Xie, Weikang Bai, Hao Feng, Wei Shi, Yuchen Su, Can Huang, Yu-Gang Jiang
Abstract: Text and formulas constitute the core informational components of many documents. Accurately and efficiently recognizing both is crucial for developing robust and generalizable document parsing systems. Recently, vision-language models (VLMs) have achieved impressive unified recognition of text and formulas. However, they are large-sized and computationally demanding, restricting their usage in many applications. In this paper, we propose UniRec-0.1B, a unified recognition model with only 0.1B parameters. It is capable of performing text and formula recognition at multiple levels, including characters, words, lines, paragraphs, and documents. To implement this task, we first establish UniRec40M, a large-scale dataset comprises 40 million text, formula and mixed samples, enabling the training of a powerful yet lightweight model. Secondly, we identify two challenges when building such a lightweight but unified expert model. They are: structural variability across levels and semantic entanglement between textual and formulaic content. To tackle these, we introduce a hierarchical supervision training that explicitly guides structural comprehension, and a semantic-decoupled tokenizer that separates text and formula representations. Finally, we develop a comprehensive evaluation benchmark covering Chinese and English documents from multiple domains and with multiple levels. Experimental results on this and public benchmarks demonstrate that UniRec-0.1B outperforms both general-purpose VLMs and leading document parsing expert models, while achieving 2-9x speedup, validating its effectiveness and efficiency. Codebase and Dataset: https://github.com/Topdu/OpenOCR.
Authors: Habiba Kausar, Saeed Anwar, Omar Jamal Hammad, Ibrahim Radwan, Abdul Bais
Abstract: Face super-resolution aims to recover high-quality facial images from severely degraded low-resolution inputs, but remains challenging due to the loss of fine structural details and identity-specific features. This work introduces SwinIFS, a landmark-guided super-resolution framework that integrates structural priors with hierarchical attention mechanisms to achieve identity-preserving reconstruction at both moderate and extreme upscaling factors. The method incorporates dense Gaussian heatmaps of key facial landmarks into the input representation, enabling the network to focus on semantically important facial regions from the earliest stages of processing. A compact Swin Transformer backbone is employed to capture long-range contextual information while preserving local geometry, allowing the model to restore subtle facial textures and maintain global structural consistency. Extensive experiments on the CelebA benchmark demonstrate that SwinIFS achieves superior perceptual quality, sharper reconstructions, and improved identity retention; it consistently produces more photorealistic results and exhibits strong performance even under $8\times$ magnification, where most methods fail to recover meaningful structure. SwinIFS also provides an advantageous balance between reconstruction accuracy and computational efficiency, making it suitable for real-world applications in facial enhancement, surveillance, and digital restoration. Our code, model weights, and results are available at https://github.com/Habiba123-stack/SwinIFS.
Authors: Kim Yu-Ji, Dahye Lee, Kim Jun-Seong, Nam Hyeon-Woo, GeonU Kim, Yongjin Kwon, Yu-Chiang Frank Wang, Jaesung Choe, Tae-Hyun Oh
Abstract: Vision-Language Models (VLMs) have demonstrated strong reasoning capabilities over images and videos, yet their application to embodied scene understanding often constrained by the fixed viewpoints stored in episodic RGB-D memories. These observations may fail to capture query-relevant evidence due to occlusions, object truncation, restricted fields of view, or suboptimal view composition. We present SplatReasoner, a framework that introduces novel view synthesis into the VLM reasoning process by leveraging 3D Gaussian Splatting (3DGS). Given a user query about a 3D scene, SplatReasoner retrieves relevant observations and synthesizes query-conditioned viewpoints that reveal the visual evidence needed to answer the query and ground the referred entities in 3D. Experiments show that query-conditioned novel view synthesis improves both embodied reasoning and 3D grounding over fixed-view memory and language-embedded 3DGS baselines.
Authors: Haoyu Cao, Kun Yin, Yunfei Wu, Bing Liu, Zhongpeng Cai, Xiaotian Li, Huang Chen, Xin Li, Yinsong Liu, Deqiang Jiang, Xing Sun, Yunsheng Wu, Qianyu Li, Antai Guo, Yanzhen Liao, Yanqiu Qu, Haodong Lin, Chengxu He, Shuangyin Liu
Abstract: This paper presents Youtu-Parsing, an efficient and versatile document parsing model designed for high-performance content extraction. The architecture employs a native Vision Transformer (ViT) featuring a dynamic-resolution visual encoder to extract shared document features, coupled with a prompt-guided Youtu-LLM-2B language model for layout analysis and region-prompted decoding. Leveraging this decoupled and feature-reusable framework, we introduce a high-parallelism decoding strategy comprising two core components: token parallelism and query parallelism. The token parallelism strategy concurrently generates up to 64 candidate tokens per inference step, which are subsequently validated through a verification mechanism. This approach yields a 5--11x speedup over traditional autoregressive decoding and is particularly well-suited for highly structured scenarios, such as table recognition. To further exploit the advantages of region-prompted decoding, the query parallelism strategy enables simultaneous content prediction for multiple bounding boxes (up to five), providing an additional 2x acceleration while maintaining output quality equivalent to standard decoding. Youtu-Parsing encompasses a diverse range of document elements, including text, formulas, tables, charts, seals, and hierarchical structures. Furthermore, the model exhibits strong robustness when handling rare characters, multilingual text, and handwritten content. Extensive evaluations demonstrate that Youtu-Parsing achieves state-of-the-art (SOTA) performance on both the OmniDocBench and olmOCR-bench benchmarks. Overall, Youtu-Parsing demonstrates significant experimental value and practical utility for large-scale document intelligence applications.
Authors: Mahmoud Z. A. Wahba, Francesco Barbato, Sara Baldoni, Federica Battisti
Abstract: Saliency estimation has received growing attention in recent years due to its importance in a wide range of applications. In the context of 360-degree video, it has been particularly valuable for tasks such as viewport prediction and immersive content optimization. In this paper, we propose SalFormer360, a novel saliency estimation model for 360-degree videos built on a transformer-based architecture. Our approach is based on the combination of an existing encoder architecture, SegFormer, and a custom decoder. The SegFormer model was originally developed for 2D segmentation tasks, and it has been fine-tuned to adapt it to 360-degree content. To further enhance prediction accuracy in our model, we incorporated Viewing Center Bias to reflect user attention in 360-degree environments. Extensive experiments on the three largest benchmark datasets for saliency estimation demonstrate that SalFormer360 outperforms existing state-of-the-art methods. In terms of Pearson Correlation Coefficient, our model achieves 8.4% higher performance on Sport360, 2.5% on PVS-HM, and 18.6% on VR-EyeTracking compared to previous state-of-the-art.
Authors: Julia Werner, Julius Oexle, Oliver Bause, Maxime Le Floch, Franz Brinkmann, Hannah Tolle, Jochen Hampe, Oliver Bringmann
Abstract: The classification performance of deep neural networks relies strongly on access to large, accurately annotated datasets. In medical imaging, however, obtaining such datasets is particularly challenging since annotations must be provided by specialized physicians, which severely limits the pool of annotators. Furthermore, class boundaries can often be ambiguous or difficult to define which further complicates machine learning-based classification. In this paper, we want to address this problem and introduce a framework for mislabel detection in medical datasets. This is validated on the two largest, publicly available datasets for Video Capsule Endoscopy, an important imaging procedure for examining the gastrointestinal tract based on a video stream of lowresolution images. In addition, potentially mislabeled samples identified by our pipeline were reviewed and re-annotated by three experienced gastroenterologists. Our results show that the proposed framework successfully detects incorrectly labeled data and results in an improved anomaly detection performance after cleaning the datasets compared to current baselines.
Authors: Pengcheng Pan, Yonekura Shogo, Yasuo Kuniyosh
Abstract: Human eye movements in visual recognition reflect a balance between foveal sampling and peripheral context. Task-driven hard-attention models for vision are often evaluated by how well their scanpaths match human gaze. However, common scanpath metrics can be strongly confounded by dataset-specific center bias, especially on object-centric datasets. Using Gaze-CIFAR-10, we show that a trivial center-fixation baseline achieves surprisingly strong scanpath scores, approaching many learned policies. This makes standard metrics optimistic and blurs the distinction between genuine behavioral alignment and mere central tendency. We then analyze a hard-attention classifier under constrained vision by sweeping foveal patch size and peripheral context, revealing a peripheral sweet spot: only a narrow range of sensory constraints yields scanpaths that are simultaneously (i) above the center baseline after debiasing and (ii) temporally human-like in movement statistics. To address center bias, we propose GCS (Gaze Consistency Score), a center-debiased composite metric augmented with movement similarity. GCS uncovers a robust sweet spot at medium patch size with both foveal and peripheral vision, that is not obvious from raw scanpath metrics or accuracy alone, and also highlights a "shortcut regime" when the field-of-view becomes too large. We discuss implications for evaluating active perception on object-centric datasets and for designing gaze benchmarks that better separate behavioral alignment from center bias.
Authors: Akashah Shabbir, Muhammad Umer Sheikh, Muhammad Akhtar Munir, Hiyam Debary, Mustansar Fiaz, Muhammad Zaigham Zaheer, Paolo Fraccaro, Fahad Shahbaz Khan, Muhammad Haris Khan, Xiao Xiang Zhu, Salman Khan
Abstract: Recent progress in multimodal reasoning has enabled agents that interpret imagery, connect it with language, and execute structured analytical tasks. Extending these capabilities to remote sensing remains challenging, as models must reason over spatial scale, geographic structures, and multispectral indices while maintaining coherent multi-step logic. To address this gap, we introduce \textit{OpenEarthAgent}, a unified framework for tool-augmented geospatial reasoning trained on satellite imagery, natural-language queries, and structured reasoning traces. Beyond serving as a benchmark, OpenEarthAgent establishes a cohesive agentic architecture built around a unified executable tool registry and trajectory-based policy learning. The framework standardizes heterogeneous visual, spectral, GIS, and georeferenced raster operations under a consistent callable schema, enabling modular orchestration and deterministic execution. Training is performed via supervised fine-tuning on structured reasoning trajectories with deterministic replay validation to ensure executability and spatial correctness. The accompanying corpus comprises 14,538 training and 1,169 evaluation instances with over 107K reasoning steps, spanning urban, environmental, disaster, and infrastructure domains and incorporating GIS operations alongside index analyses such as NDVI, NBR, and NDBI. Grounded in explicit reasoning traces, the learned agent demonstrates structured reasoning, stable spatial understanding, and interpretable tool-driven behaviour across diverse EO scenarios. We report consistent improvements over a strong baseline and competitive performance against recent open and closed-source models. Our code, data and trained models are publicly available: https://github.com/mbzuai-oryx/OpenEarthAgent
Authors: Xiaoru Dong, Ruiqin Li, Xiao Han, Zhenxuan Wu, Jiamin Wang, Jian Chen, Qi Jiang, SM Yiu, Xinge Zhu, Yuexin Ma
Abstract: Human driving behavior is inherently diverse, yet most end-to-end autonomous driving (E2E-AD) systems learn a single average driving style, neglecting individual differences. Achieving personalized E2E-AD faces challenges across three levels: limited real-world datasets with individual-level annotations, a lack of quantitative metrics for evaluating personal driving styles, and the absence of algorithms that can learn stylized representations from users' trajectories. To address these gaps, we propose Person2Drive, a comprehensive personalized E2E-AD platform and benchmark. It includes an open-source, flexible data collection system that simulates realistic scenarios to generate scalable, diverse personalized driving datasets; style vector-based evaluation metrics with Maximum Mean Discrepancy and KL divergence to comprehensively quantify individual driving behaviors; and a personalized E2E-AD framework with a style reward model that efficiently adapts E2E models for safe and individualized driving. Crucially, our framework enables plug-and-play personalization by fine-tuning only the trajectory prediction head, preserving the pretrained base model and ensuring safety. Extensive experiments demonstrate that Person2Drive enables fine-grained analysis and effective personalization, while preserving driving performance and success rate even in challenging scenarios.
Authors: Qinfeng Zhu, Yunxi Jiang, Lei Fan
Abstract: Panoramic dense-prediction models, spanning semantic segmentation and depth estimation, are typically trained under a strict gravity-aligned assumption. Real-world captures, however, routinely violate it: handheld devices jitter and aerial platforms change attitude, so the camera is rarely upright. Under such 3D reorientation, standard spherical Transformers overfit global latitude cues and collapse. We introduce SO3UFormer, an architecture that learns intrinsic spherical features largely decoupled from the underlying coordinate frame, through three geometric components: (1) removing absolute latitude encoding, which breaks the dependence on the gravity axis; (2) quadrature-consistent spherical attention, which corrects for non-uniform sampling density; and (3) a gauge-aware relative positional bias built from local tangent-plane angles rather than global axes. A logit-space \emph{SO(3)}-consistency regularizer, used only during training, further suppresses residual discretization effects. To benchmark robustness, we introduce Pose35, a variant of Stanford2D3D perturbed by random rotations within $\pm 35^\circ$, and evaluate under a full, arbitrary \emph{SO(3)} stress test. There, the baseline SphereUFormer collapses from 67.53 \emph{mIoU} on Pose35 to 25.26 under the full \emph{SO(3)} test, whereas SO3UFormer reaches 72.03 on Pose35 and retains 70.67 under the same test. Similarly, on a second real-world dataset (Matterport3D) for segmentation and on panoramic depth estimation, SO3UFormer remains essentially rotation-invariant while the gravity-anchored baseline again loses most of its accuracy. Code and models are available at https://github.com/zhuqinfeng1999/SO3UFormer.
Authors: Wenxin Li, Kunyu Peng, Di Wen, Junwei Zheng, Jiale Wei, Mengfei Duan, Yuheng Zhang, Rui Fan, Kailun Yang
Abstract: 3D semantic occupancy prediction is a cornerstone of robotic perception, yet real-world voxel annotations are inherently corrupted by structural artifacts and dynamic trailing effects. This raises a critical but underexplored question: can autonomous systems safely rely on such unreliable occupancy supervision? To systematically investigate this issue, we establish OccNL, the first benchmark dedicated to 3D occupancy under occupancy-asymmetric and dynamic trailing noise. Our analysis reveals a fundamental domain gap: state-of-the-art 2D label noise learning strategies collapse catastrophically in sparse 3D voxel spaces, exposing a critical vulnerability in existing paradigms. To address this challenge, we propose DPR-Occ, a principled label-noise-robust framework that constructs reliable supervision through dual-source partial label reasoning. By synergizing temporal model memory with representation-level structural affinity, DPR-Occ dynamically expands and prunes candidate label sets to preserve true semantics while suppressing noise propagation. Extensive experiments on SemanticKITTI demonstrate that DPR-Occ prevents geometric and semantic collapse under extreme corruption. Notably, even at 90% label noise, our method achieves significant performance gains (up to 2.57% mIoU and 13.91% IoU) over existing label noise learning baselines adapted to the 3D occupancy prediction task. By bridging label noise learning and 3D perception, OccNL and DPR-Occ provide a reliable foundation for safety-critical robotic perception in dynamic environments. The benchmark and source code will be made publicly available at https://github.com/mylwx/OccNL.
Authors: Shuai Guo, Ao Guo, Junchao Zhao, Qi Chen, Yuxiang Qi, Zechuan Li, Dong Chen, Mingliang Xu
Abstract: Object-level 3D reconstruction play important roles across domains such as cultural heritage digitization, industrial manufacturing, and virtual reality. However, existing Gaussian Splatting-based approaches generally rely on full-scene reconstruction, in which substantial redundant background information is introduced, leading to increased computational and storage overhead. To address this limitation, we propose an efficient single-object 3D reconstruction method based on 2D Gaussian Splatting. By directly integrating foreground-background probability cues into Gaussian primitives and dynamically pruning low-probability Gaussians during training, the proposed method fundamentally focuses on an object of interest and improves the memory and computational efficiency. Our pipeline leverages probability masks generated by YOLO and SAM to supervise probabilistic Gaussian attributes, replacing binary masks with continuous probability values to mitigate boundary ambiguity. Additionally, we propose a dual-stage filtering strategy for training's startup to suppress background Gaussians. And, during training, rendered probability masks are conversely employed to refine supervision and enhance boundary consistency across views. Experiments conducted on the MIP-360, T&T, and NVOS datasets demonstrate that our method exhibits strong self-correction capability in the presence of mask errors and achieves reconstruction quality comparable to standard 3DGS approaches, while requiring only approximately 1/10 of their Gaussian amount. These results validate the efficiency and robustness of our method for single-object reconstruction and highlight its potential for applications requiring both high fidelity and computational efficiency.
Authors: Vansh Sharma, Venkat Raman
Abstract: This study presents a novel algorithm based on graph theory for the precise segmentation and measurement of detonation cells from 3D pressure traces, termed detonation lattices, addressing the limitations of manual and primitive 2D edge detection methods prevalent in the field. Using a segmentation model, the proposed training-free algorithm is designed to accurately extract cellular patterns, a longstanding challenge in detonations research. First, the efficacy of segmentation phase on two synthetic datasets is evaluated with an error of 2%. Next, 3D simulation data is used to establish performance of the graph-based workflow. The results of statistics and joint probability densities show oblong cells aligned with the wave propagation axis with 17% deviation, whereas larger dispersion in volume reflects cubic amplification of linear variability. Although the framework is robust, it remains challenging to reliably segment and quantify highly complex cellular patterns. However, the graph-based formulation generalizes across diverse cellular geometries, positioning it as a practical tool for detonation analysis and a strong foundation for future extensions in triple-point collision studies.
Authors: Jindong Li, Dario Zanca, Vincent Christlein, Tim Hamann, Jens Barth, Peter K\"ampf, Bj\"orn Eskofier
Abstract: Inertial measurement unit-based online handwriting recognition enables the recognition of input signals collected across different writing surfaces but remains challenged by uneven character distributions and inter-writer variability. In this work, we systematically investigate two strategies to address these issues: subword tokenization and concatenation-based data augmentation. Our experiments on the OnHW-Words500 dataset reveal a clear dichotomy between handling inter-writer and intra-writer variance. On the writer-independent split, structural abstraction via Bigram tokenization significantly improves generalization to unseen writing styles, reducing the word error rate (WER) from 15.40% to 12.99%. In contrast, on the writer-dependent split, tokenization degrades performance due to vocabulary distribution shifts between the training and validation sets. Instead, our proposed concatenation-based data augmentation acts as a powerful regularizer, reducing the character error rate by 34.5% and the WER by 25.4%. Further analysis shows that short, low-level tokens benefit model performance and that the performance gains from concatenation-based data augmentation surpass those achieved by proportionally extended training. These findings reveal a clear variance-dependent effect: subword tokenization primarily mitigates inter-writer stylistic variability, whereas concatenation-based data augmentation effectively compensates for intra-writer distributional sparsity.
Authors: Chenyang Zhu, Maorong Wang, Jun Liu, Ching-Chun Chang, Isao Echizen
Abstract: The rapid proliferation of AI-Generated Images (AIGIs) poses severe misinformation risks, making AIGI detection critical yet challenging. Traditional detection paradigms mainly rely on low-level features, whereas recent research increasingly focuses on leveraging the general understanding ability of Multimodal Large Language Models (MLLMs) to achieve better generalization, yet it still suffers from limited extensibility and expensive data annotations. Instead of building yet another detector, we recast AIGI detection as learned, reasoning-based evidence synthesis over a pool of heterogeneous off-the-shelf detectors, realized through EvoGuard, a novel agentic framework. A capability-aware selection mechanism profiles each detector and gathers complementary evidence per sample; a dynamic orchestration mechanism then reasons over heterogeneous outputs across multiple rounds, cross-validating conflicting or low-confidence signals before concluding. This design exploits the complementary strengths among heterogeneous detectors, transcending the limits of any single model. Furthermore, optimized by a GRPO-based Agentic Reinforcement Learning algorithm using only low-cost binary labels, it eliminates the reliance on fine-grained annotations. Extensive experiments demonstrate that this learned reasoning paradigm outperforms single-detector and static ensembling, achieving SOTA accuracy while mitigating the bias between positive and negative samples. More importantly, it allows the plug-and-play integration of new detectors to boost overall performance in a train-free manner, offering a highly practical, long-term solution to ever-evolving AIGI threats. Source code will be publicly available upon acceptance.
Authors: Kaiqiang Li, Gang Li, Mingle Zhou, Min Li, Delong Han, Jin Wan
Abstract: Zero-shot (ZS) 3D anomaly detection is crucial for reliable industrial inspection, as it enables detecting and localizing defects without requiring any target-category training data. Existing approaches render 3D point clouds into 2D images and leverage pre-trained Vision-Language Models (VLMs) for anomaly detection. However, such strategies inevitably discard geometric details and exhibit limited sensitivity to local anomalies. In this paper, we revisit intrinsic 3D representations and explore the potential of pre-trained Point-Language Models (PLMs) for ZS 3D anomaly detection. We propose BTP (Back To Point), a novel framework that effectively aligns 3D point cloud and textual embeddings. Specifically, BTP aligns multi-granularity patch features with textual representations for localized anomaly detection, while incorporating geometric descriptors to enhance sensitivity to structural anomalies. Furthermore, we introduce a joint representation learning strategy that leverages auxiliary point cloud data to improve robustness and enrich anomaly semantics. Extensive experiments on Real3D-AD and Anomaly-ShapeNet demonstrate that BTP achieves superior performance in ZS 3D anomaly detection. Code will be available at \href{https://github.com/wistful-8029/BTP-3DAD}{https://github.com/wistful-8029/BTP-3DAD}.
URLs: https://github.com/wistful-8029/BTP-3DAD, https://github.com/wistful-8029/BTP-3DAD
Authors: Bingxuan Zhao, Qing Zhou, Chuang Yang, Qi Wang
Abstract: Text-to-image generation powered by Diffusion Transformers (DiTs) has made remarkable strides, yet remote sensing (RS) synthesis lags behind due to two barriers: the absence of a domain-specialized DiT prior and the prohibitive cost of training at the large resolutions that RS applications demand. Training-free resolution promotion via Rotary Position Embedding (RoPE) rescaling offers a practical remedy, but every existing method applies a static positional scaling rule throughout the denoising process. This uniform compression is particularly harmful for RS imagery, whose substantially denser medium- and high-frequency energy encodes the fine structures critical for aerial-scene realism, such as vehicles, building contours, and road markings. Addressing both challenges requires a domain-specialized generative prior coupled with a denoising-aware positional adaptation strategy. To this end, we fine-tune FLUX on over 100,000 curated RS images to build a strong domain prior (RS-FLUX), and propose Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion (SHARP), a training-free method that introduces a rational fractional time schedule k_rs(t) into RoPE. SHARP applies strong positional promotion during the early layout-formation stage and progressively relaxes it during detail recovery, aligning extrapolation strength with the frequency-progressive nature of diffusion denoising. Its resolution-agnostic formulation further enables robust multi-scale generation from a single set of hyperparameters. Extensive experiments across six square and rectangular resolutions show that SHARP consistently outperforms all training-free baselines on CLIP Score, Aesthetic Score, and HPSv2, with widening margins at more aggressive extrapolation factors and negligible computational overhead. Code and weights are available at https://github.com/bxuanz/SHARP.
Authors: Hayeon Kim, Ji Ha Jang, Junghun James Kim, Se Young Chun
Abstract: While Vision-Language Models (VLMs) have achieved remarkable performance, their Euclidean embeddings remain limited in capturing hierarchical relationships such as part-to-whole or parent-child structures, and often face challenges in multi-object compositional scenarios. Hyperbolic VLMs mitigate this issue by better preserving hierarchical structures and modeling part-whole relations (i.e., whole scene and its part images) through entailment. However, existing approaches do not model that each part has a different level of semantic representativeness to the whole. We propose UNcertainty-guided Compositional Hyperbolic Alignment (UNCHA) for enhancing hyperbolic VLMs. UNCHA models part-to-whole semantic representativeness with hyperbolic uncertainty, by assigning lower uncertainty to more representative parts and higher uncertainty to less representative ones for the whole scene. This representativeness is then incorporated into the contrastive objective with uncertainty-guided weights. Finally, the uncertainty is further calibrated with an entailment loss regularized by entropy-based term. With the proposed losses, UNCHA learns hyperbolic embeddings with more accurate part-whole ordering, capturing the underlying compositional structure in an image and improving its understanding of complex multi-object scenes. UNCHA achieves state-of-the-art performance on zero-shot classification, retrieval, and multi-label classification benchmarks. Our code and models are available at: https://github.com/jeeit17/UNCHA.git.
Authors: Zhaochong An, Orest Kupyn, Th\'eo Uscidda, Andrea Colaco, Karan Ahuja, Serge Belongie, Mar Gonzalez-Franco, Marta Tintore Gazulla
Abstract: Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying geometry-aware alignment. However, architectural modifications can compromise the generalization of internet-scale pretrained models, while existing alignment methods are limited to static scenes and rely on RGB-space rewards that require repeated VAE decoding, incurring substantial compute overhead and failing to generalize to highly dynamic real-world scenes. To preserve the pretrained capacity while improving geometric consistency, we propose VGGRPO (Visual Geometry GRPO), a latent geometry-guided framework for geometry-aware video post-training. VGGRPO introduces a Latent Geometry Model (LGM) that stitches video diffusion latents to geometry foundation models, enabling direct decoding of scene geometry from the latent space. By constructing LGM from a geometry model with 4D reconstruction capability, VGGRPO naturally extends to dynamic scenes, overcoming the static-scene limitations of prior methods. Building on this, we perform latent-space Group Relative Policy Optimization with two complementary rewards: a camera motion smoothness reward that penalizes jittery trajectories, and a geometry reprojection consistency reward that enforces cross-view geometric coherence. Experiments on both static and dynamic benchmarks show that VGGRPO improves camera stability, geometry consistency, and overall quality while eliminating costly VAE decoding, making latent-space geometry-guided reinforcement an efficient and flexible approach to world-consistent video generation.
Authors: Huiyao Zhang, Jin Bai, Rui Guo, JianWen Tan, HongFei Wang, Ye Li
Abstract: Prompt-conditioned foundation segmenters have emerged as a dominant paradigm for image segmentation, where explicit spatial prompts(e.g., points, boxes, masks) guide mask decoding. However, many real-world deployments require fully automatic segmentation, creating a structural mismatch: the decoder expects prompts that are unavailable at inference. Existing adaptations typically modify intermediate features, inadvertently bypassing the model's native prompt interface and weakening prompt-conditioned decoding. We propose IP-SAM, which revisits adaptation from a prompt-space perspective through prompt-space conditioning. Specifically, a Self-Prompt Generator (SPG) distills image context into complementary intrinsic prompts that serve as coarse regional anchors. These cues are projected through SAM2's frozen prompt encoder, restoring prompt-guided decoding without external intervention. To suppress background-induced false positives, Prompt-Space Gating (PSG) leverages the intrinsic background prompt as an asymmetric suppressive constraint prior to decoding. Under a deterministic no-external-prompt protocol, IP-SAM achieves state-of-the-art performance across four camouflaged object detection benchmarks with only 21.26M trainable parameters. Furthermore, the proposed conditioning strategy generalizes beyond COD to medical polyp segmentation.
Authors: Tao Liu, Yingzhi Zhang, Kan Ren, Xiaoqi Zhao
Abstract: Drone-view geo-localization (DVGL) aims to determine the location of drones in GPS-denied environments by retrieving the corresponding geotagged satellite tile from a reference gallery given UAV observations of a location. In many existing formulations, these observations are represented by a single oblique UAV image. In contrast, our satellite-free setting is designed for multi-view UAV sequences, which are used to construct a geometry-normalized UAV-side location representation before cross-view retrieval. Existing approaches rely on satellite imagery during training, either through paired supervision or unsupervised alignment, which limits practical deployment when satellite data are unavailable or restricted. In this paper, we propose a satellite-free training (SFT) framework that converts drone imagery into cross-view compatible representations through three main stages: drone-side 3D scene reconstruction, geometry-based pseudo-orthophoto generation, and satellite-free feature aggregation for retrieval. Specifically, we first reconstruct dense 3D scenes from multi-view drone images using 3D Gaussian splatting and project the reconstructed geometry into pseudo-orthophotos via PCA-guided orthographic projection. This rendering stage operates directly on reconstructed scene geometry without requiring camera parameters at rendering time. Next, we refine these orthophotos with lightweight geometry-guided inpainting to obtain texture-complete drone-side views. Finally, we extract DINOv3 patch features from the generated orthophotos, learn a Fisher vector aggregation model solely from drone data, and reuse it at test time to encode satellite tiles for cross-view retrieval. Experimental results on University-1652 and SUES-200 show that our SFT framework substantially outperforms satellite-free generalization baselines and narrows the gap to methods trained with satellite imagery.
Authors: Jason Qiu, Zachary Meurer, Xavier Thomas, Deepti Ghadiyaram
Abstract: This work investigates the fundamental fragility of state-of-the-art Vision-Language Models (VLMs) under basic geometric transformations. While modern VLMs excel at semantic tasks such as recognizing objects in canonical orientations and describing complex scenes, they exhibit systematic failures at a more fundamental level: lack of robust spatial invariance and equivariance required to reliably determine object identity under simple rotations, scaling, and identity transformations. We demonstrate this limitation through a systematic evaluation across diverse visual domains, including symbolic sketches, natural photographs, and abstract art. Performance drops sharply as semantic content becomes sparse, and this behavior is observed across architectures, model capacities, and prompting strategies. Overall, our results reveal a systematic gap between semantic understanding and spatial reasoning in current VLMs, highlighting the need for stronger geometric grounding in future multimodal systems.
Authors: Nicolae Cudlenco, Mihai Masala, Marius Leordeanu
Abstract: Game engines hold what video models struggle to learn: a complete, explicit world state behind every frame. We turn one into a data instrument. GEST-Engine, our production-grade open-source system, deterministically executes Graphs of Events in Space and Time (GESTs), whether procedurally generated or derived from text, into videos of synchronized multi-actor scenarios, recording ground truth as it renders: 3D entity and camera state, pairwise spatial relations, event-to-frame mappings, instance segmentation, and long descriptions, at zero marginal annotation cost. With it we release GTASA, a 938-video sample of what the system can generate at arbitrary scale, carrying, to our knowledge, the densest spatial-relation coverage of any video dataset: a complete entity-pair relation graph at every frame, ~84x denser than the state of the art, frame-for-frame. We validate GTASA both qualitatively, through human evaluation of physical validity and semantic alignment where frontier neural generators, given the same prompts, largely fail, and quantitatively, with GTASA pretraining improving VLM video captioning. Probing six frozen video encoders across 11 spatio-temporal tasks enabled by GTASA's exact 3D ground truth, a previously untestable inter-entity relational probe of frozen video features, reveals that who-is-near-whom barely rises above chance for all of them. We release the engine, the corpus, and the benchmark, making this gap a measurable, trainable target.
Authors: Tianhao Fu, Austin Wang, Charles Chen, Roby Aldave-Garza, Yucheng Chen
Abstract: Reliable uncertainty estimation is critical for medical image segmentation, where automated contours feed downstream quantification and clinical decision support. Many strong uncertainty methods require repeated inference, while efficient single-forward-pass alternatives often provide weaker failure ranking or rely on restrictive feature-space assumptions. We present $\textbf{SegWithU}$, a post-hoc framework that augments a frozen pretrained segmentation backbone with a lightweight uncertainty head. SegWithU taps intermediate backbone features and models uncertainty as perturbation energy in a compact probe space using rank-1 posterior probes. It produces two voxel-wise uncertainty maps: a calibration-oriented map for probability tempering and a ranking-oriented map for error detection and selective prediction. Across ACDC, BraTS2024, and LiTS, SegWithU is the strongest and most consistent single-forward-pass baseline, achieving AUROC/AURC of $0.9838/2.4885$, $0.9946/0.2660$, and $0.9925/0.8193$, respectively, while preserving segmentation quality. These results suggest that perturbation-based uncertainty modeling is an effective and practical route to reliability-aware medical segmentation. Source code is available at https://github.com/ProjectNeura/SegWithU.
Authors: Baoyou Chen, Hanchen Xia, Peng Tu, Haojun Shi, Liwei Zhang, Yuxuan Yao, Weihao Yuan, Siyu Zhu
Abstract: Autoregressive vision-language models (VLMs) deliver strong multimodal capability, but their token-by-token decoding imposes a fundamental inference bottleneck. Diffusion VLMs offer a more parallel decoding paradigm, yet directly converting a pretrained autoregressive VLM into a large-block diffusion VLM (dVLM) often leads to substantial quality degradation. In this work, we present BARD, a simple and effective bridging framework that converts a pretrained autoregressive VLM into a same-architecture, decoding-efficient dVLM. Our approach combines progressive supervised block merging, which gradually enlarges the decoding block size, with stage-wise intra-dVLM distillation from a fixed small-block diffusion anchor to recover performance lost at larger blocks. We further incorporate a mixed noise scheduler to improve robustness and token revision during denoising, and memory-friendly training to enable efficient training on long multimodal sequences. A key empirical finding is that direct autoregressive-to-diffusion distillation is poorly aligned and can even hurt performance, whereas distillation within the diffusion regime is consistently effective. Experimental results show that, with $\leq$ 4.4M data, BARD-VL transfers strong multimodal capability from Qwen3-VL to a large-block dVLM. Remarkably, BARD-VL establishes a new SOTA among comparable-scale open dVLMs on our evaluation suite at both 4B and 8B scales. At the same time, BARD-VL achieves up to 3$\times$ decoding throughput speedup compared to the source model. Code is available at https://github.com/fudan-generative-vision/Bard-VL.
Authors: Junxiao Xue, Quan Deng, Tingqi Hu, Meicong Si, Xinyi Yin, Yunyun Shi, Xuecheng Wu
Abstract: Despite recent progress in multimodal large language models (MLLMs), reliable visual question answering in aerial scenes remains challenging. In such scenes, task-critical evidence is often carried by small objects, explicit quantities, coarse locations, and inter-object relations, whereas conventional dense visual-token representations are not well aligned with these structured semantics. To address this interface mismatch, we propose AeroRAG, a scene-graph-guided multimodal retrieval-augmented generation framework for visual question answering. The framework first converts an input image into structured visual knowledge, including object categories, quantities, spatial locations, and semantic relations, and then retrieves query-relevant semantic chunks to construct compact prompts for a text-based large language model. Rather than relying on direct reasoning over dense visual tokens, our method introduces a more explicit intermediate interface between perception and language reasoning. Experiments on the AUG aerial dataset and the general-domain VG-150 benchmark show consistent improvements over six strong MLLM baselines, with the largest gains observed in dense aerial scenes and relation-sensitive reasoning. We further evaluate the framework on VQAv2 to verify that the proposed interface remains compatible with standard visual reasoning settings. These results suggest that structured retrieval is a practical design direction for deployment-oriented and grounded visual reasoning systems.
Authors: Yihong Chen, Pascal Fua
Abstract: Accurate cardiac anatomy modeling requires the model to be able to handle intricate interrelations among structures. In this paper, we propose VecHeart, a unified framework for holistic reconstruction and generation of four-chamber cardiac structures. To overcome the limitations of current feed-forward implicit methods, specifically their restriction to single-object modeling and their neglect of inter-part correlations, we introduce Hybrid Part Transformer, which leverages part-specific learnable queries and interleaved attention to capture complex inter-chamber dependencies. Furthermore, we propose Anatomical Completion Masking and Modality Alignment strategies, enabling the model to infer complete four-chamber structures from partial, sparse, or noisy observations, even when certain anatomical parts are entirely missing. VecHeart also seamlessly extends to 3D+t dynamic mesh sequence generation, demonstrating exceptional versatility. Experiments show that our method achieves state-of-the-art performance, maintaining high-fidelity reconstruction across diverse challenging scenarios. Code is available at https://github.com/Scalsol/VecHeart.
Authors: Siyu Cao, Lu Zhang, Ruizhe Zeng, Zhi-yong Liu
Abstract: Sports videos are a challenging domain for multimodal understanding because they involve complex and dynamic human activities. Despite rapid progress in Multimodal Large Language Models (MLLMs), long-horizon reasoning in sports videos remains difficult, as answering questions requires both locating temporally sparse evidence and integrating it into reasoning. We attribute this limitation to two closely coupled factors: insufficient supervision over temporally dispersed evidence, and the lack of methods that require models to identify, localize, and justify temporal evidence. To address these gaps, we introduce SportsTime, a large-scale benchmark for long-form sports video understanding, comprising 14K+ open-ended QA pairs and 50K+ step-wise temporal evidence annotations. Building on SportsTime, we propose Chain-of-Time Reasoning (CoTR), which treats reasoning as a process of temporally grounded evidence composition. Specifically, during training, CoTR introduces a temporal-reward GRPO to encourage temporally grounded reasoning. During inference, it employs an anchor-observe-infer evidence-seeking loop to iteratively localize, verify, and compose temporal evidence before producing the final answer. Experiments demonstrate the usefulness of SportsTime as a benchmark and the effectiveness of CoTR, which consistently improves temporal compositional reasoning and step-wise grounding quality over strong MLLM baselines.
Authors: Zibo Shao, Baochen Xiong, Xiaoshan Yang, Yaguang Song, Qimeng Zhang, Haifeng Chen, Changsheng Xu
Abstract: Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities. Model merging provides a cost-effective mechanism for integrating multiple expert MLLMs with complementary strengths into a unified model. However, existing model merging research mainly focuses on post-finetuning scenarios, leaving the pre-training stage largely unexplored. We argue that the core of MLLM pre-training lies in establishing effective cross-modal alignment, which bridges visual and textual representations into a unified semantic space. Motivated by this insight, we introduce the post-alignment merging task, which aims to integrate cross-modal alignment capabilities learned from heterogeneous multimodal pre-training. This setting introduces two key challenges: cross-domain parameter interference, where parameter updates learned from different data distributions conflict during merging, and layer-wise alignment contribution disparity, where different layers and projectors contribute unevenly to cross-modal alignment. To address them, we propose \textbf{PivotMerge}, a post-alignment merging framework for cross-modal projectors. PivotMerge incorporates two key components: Shared-space Decomposition and Filtering, which disentangles shared alignment patterns from domain-specific variations and suppresses conflicting directions, and Alignment-guided Layer-wise Merging, which assigns layer-specific merging weights based on differing alignment contributions. We construct systematic CC12M-based post-alignment merging scenarios for evaluation. Extensive experiments on multiple multimodal benchmarks show that PivotMerge consistently outperforms existing baselines, demonstrating its effectiveness and generalization ability.
Authors: Sharayu Nilesh Deshmukh, Kailash A. Hambarde, Joana C. Costa, Hugo Proen\c{c}a, Tiago Roxo
Abstract: Current DeepFake detection scenarios are mostly binary, yet data manipulation can vary across audio, video, or both, whose variability is not captured in binary settings. Four-class audio-visual formulations address this by discriminating manipulation type, but introduce an unresolved problem: models may rely solely on data source integrity to detect DeepFakes without evaluating their semantic consistency. If the DeepFake origin is not in the data source but in its content, can semantic mismatch be assessed by the state-of-the-art? This paper proposes a new evaluation setup, extending the four-class formulation by explicitly modeling semantic-level inconsistency between authentic modalities with the introduction of a new class: Real Audio-Real Video with Semantic Mismatch RARV-SMM. We assess the robustness of state-of-the-art models in this new realistic DeepFake setting, using the FakeAVCeleb dataset, highlighting the limitations of existing approaches when faced with semantic mismatch data. We further introduce three RARV-SMM variants that expose distinct architectural vulnerabilities as audio-visual divergence increases. We also propose a semantic reinforcement strategy that incorporates the semantic mismatch class and ImageBind embeddings to probe whether an explicit semantic coherence signal improves detection across architectures with different detection strategies, on FakeAVCeleb and LAV-DF, contributing toward more realistic DeepFake detectors. The source code available at https://github.com/sharayu-20/deepfake-semantic-mismatch.
URLs: https://github.com/sharayu-20/deepfake-semantic-mismatch.
Authors: Thong Nguyen, Khoi M. Le, Cong-Duy Nguyen, Luu Anh Tuan, See-Kiong Ng, Chunyan Miao
Abstract: Recent advancements in image animation have utilized diffusion models to breathe life into static images. However, existing controllable frameworks typically rely on Lagrangian motion guidance, where optical flow is estimated relative to the initial frame. This paper revisits the same optical-flow primitive through a more local supervision design: we use adjacent-frame Eulerian motion fields to guide generation, where the motion signal always describes a short temporal hop. This shift enables parallelized training and provides bounded-error supervision throughout the generation process. To mitigate the drift artifacts common in adjacent frame generation, we introduce a Bidirectional Geometric Consistency mechanism, which computes a forward-backward cycle check to mathematically identify and mask occluded regions, preventing the model from learning incorrect warping objectives. Extensive experiments demonstrate that our approach accelerates training, preserves temporal coherence, and reduces dynamic artifacts compared to reference-based baselines. The code, model, and data have been made available at https://nguyentthong.github.io/eulerian/
Authors: Zhekai Fan, Wanze Li, Jinxin Wang, Yunpeng Shi
Abstract: Translation averaging aims to recover camera locations from pairwise relative translation directions and is a fundamental component of global Structure-from-Motion pipelines. The problem is challenging because direction measurements contain no distance information, making the estimation problem highly ill-conditioned and highly sensitive to corrupted observations. In this paper, we propose TriP, a triangle-based framework for robust translation averaging. TriP first infers local relative edge scales from triangle geometry, and then synchronizes the scales of overlapping triangles in the logarithmic domain to recover globally consistent edge lengths and camera locations. By leveraging higher-order consistency across triangles, the proposed method is robust to adversarial, cycle-consistent, and other structured corruptions. In addition, TriP avoids the collapse issue without requiring any extra anti-collapse constraints, since log-scale synchronization excludes the degenerate zero-scale solution by construction. These structural advantages enable a particularly strong theory for exact location recovery. On the practical side, TriP is fully parallelizable, computationally efficient, and naturally scalable to graphs with millions of cameras. Moreover, it outperforms all previous translation averaging methods by a large margin on both synthetic and real datasets.
Authors: Xiaotian Hu, Mingxuan Liu, Hongjia Yang, Tongxi Song, Yijin Li, Yifei Chen, Haoxiang Li, Zihan Li, Yingqi Hao, Ziyu Li, 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. Code: https://github.com/hu2274898/INFANiTE
Authors: Wenjie Yang, Hang Yu, Yuyu Guo, Peng Di
Abstract: In this work, we address the critical yet underexplored challenge of symmetric multimodal-to-multimodal (MM2MM) retrieval, where queries and contexts are interchangeable. Existing universal multimodal retrieval works struggle with this task, as they are constrained by the labeled asymmetric datasets used. We produce SOLAR (Self-supervised jOint LeArning for symmetric multimodal Retrieval), a novel two-stage self-supervised framework that leverages readily available unlabeled web-scale image-text pairs. Based on the observation that both semantic alignment and discrepancies exist between two modalities, in the first stage, we learn the intersection mask of image-text pair, allowing us to align intersection while preserving semantic of difference. In the second stage, the learned mask is further utilized to construct positive and hardnegative samples via masking different parts of image/text, which enable us to conduct self-supervised multimodal embedding learning. Complementing this framework, we present a new benchmark featuring high-quality human-verified positive and hard-negative pairs to evaluate symmetric MM2MM retrieval under realistic conditions, as well as the corresponding pipeline. Extensive experiments against ten SOTA methods show SOLAR surpasses the strongest supervised VLM by 7.08 points on this benchmark, with over 50x fewer model parameters and a 5x smaller embedding dimension. Code, model and benchmark are available at https://github.com/codefuse-ai/SOLAR.
Authors: Shangwen Zhu, Qianyu Peng, Zhao Pu, Zhilei Shu, Xiangrui Ke, Zhaohu Xing, Zizhao Tong, Zeqing Wang, Xinyu Cui, Zian Zheng, Huangji Wang, Jian Zhao, Yeying Jin, Fan Cheng, Ruili Feng
Abstract: Modern interactive video world models have achieved impressive visual fidelity, yet lack fine-grained multi-entity control and cross-entity, cross-world generalization. We trace this gap to the action interface: standard control protocols (e.g. animation IDs, device inputs, scene-level captions) bind action semantics to specific entities or engines at design time. We propose natural language as the interface to unlock expressiveness that no prior interface can achieve, and we present Incantation, the first interactive video world model with per-latent-frame (0.25 s) natural-language conditioning that supports simultaneous multi-entity control and concept-level cross-entity transfer beyond any fixed rendering pipeline. We pair a pretrained bidirectional video backbone with frame-local text cross-attention, and enable real-time long-horizon streaming through ODE-initialized Self-Forcing distillation with a RoPE-decoupled sliding KV-cache. We surpass the Action-Index baseline on cross-entity transfer (89% vs. 43%) and out-of-vocabulary prompts (90% vs. 0%), and our 2-step student sustains 19.7 FPS at 480p with stable FVD over 2-hour rollouts. We further apply the same architecture and training recipe to The King of Fighters, changing only the per-entity action vocabulary slots. We have released a preview subset of the Incantation dataset at https://huggingface.co/datasets/zhush/incantation-elden-ring-scenes, containing manually collected Elden Ring player-boss combat clips with structured action-oriented metadata. Larger-scale Elden Ring and KOF data will be released with the full project.
URLs: https://huggingface.co/datasets/zhush/incantation-elden-ring-scenes,
Authors: Yitong Chen, Shiduo Zhang, Jingjing Gong, Xipeng Qiu
Abstract: Generating diverse images from sparse text is hard; generating compact actions from rich observations is easier. From the condition-target view, Vision-Language-Action (VLA) thus aligns with image-to-text, not text-to-image. We formalize this view through the irreducible velocity loss $R_v(t,c)$ of standard flow matching and validate it with a controlled 8-mode toy experiment and image-to-text MNIST task. We then show that high-noise training boosts one-step VLA decoding on standard LIBERO, achieving 95.6% on LIBERO-Long, and remains competitive across LIBERO-Plus, LIBERO-Pro, and real-world robot tasks, while ablations that weaken the condition or expand the horizon predictably erase the one-step gain. These results suggest that whether one-step action generation works in VLA depends not on specialized training, but on the condition-target structure.
Authors: Yousef Radwan
Abstract: Different vision neural networks -- trained to classify, contrast, reconstruct, or match images to text -- should have correspondingly different internal representations. We report that they do not. After training, the top sixteen principal directions of variation inside thirteen modern vision encoders converge to the same sixteen-dimensional geometric object. We call this the cross-architecture substrate and study it with PCA, centred kernel alignment (CKA), and Pang 2026 calibration. The substrate transports across four visual domains (natural photographs, medical CT, satellite, microscopy) at median Procrustes-CKA 0.679, and across eight domains (adding sketches, depth, thermal infrared, astronomy) at 0.604, every pair >0.40. It survives Pang calibration globally (7.4x disc-vs-MAE separation, n=13,394) and locally (4.82-5.30, p<10^{-44}). It is not pixel statistics (0.263), not Gabor features (0.31), not a random projection (0.041), and emerges in the first 10% of training while accuracy keeps climbing. We deliver four applications: a label-free transferability filter beating LogME (3x faster, +0.15 Kendall-tau); a four-way domain detector (99.6% accuracy); a frozen low-shot probe (16 dims beat 768-dim DINOv2 by 3.78pp at N=50 labels per class); and a teacher-free distillation auxiliary matching trained-teacher KD on 33 pairs (7.56pp peak gain at 10% label fraction). The substrate does not cross modalities, does not help cross-paradigm distillation, and does not predict transfer quality (rho=0.08 against transfer accuracy).
Authors: Xiang Gao, Yunpeng Jia
Abstract: Visual anagram is an intriguing form of art creation wherein a single image presents different conceptual interpretations under transformations such as flipping or rotation. Recent work has achieved visual anagram synthesis by leveraging pretrained text-to-image (T2I) diffusion models, yet still suffers from several key limitations including computational inefficiency, suboptimal aesthetic quality, and weak semantic fidelity and expressiveness. This work focuses on generating visual anagrams with substantially improved visual quality at minimal computational cost, thereby advancing intelligent creation of illusionary digital art. To increase image resolution while reducing time overhead, we adapt the cutting-edge parallel denoising algorithm from pixel-based T2I model to the adversarially distilled latent-based one, and accordingly propose a structure-semantic co-optimization (S2CO) framework to counteract the consequent visual degradation. As the core of our approach, S2CO framework comprises three key innovations: (\romannumeral1) null-text structure alignment optimization; (\romannumeral2) semantic enhancement optimization; (\romannumeral3) attention-guided noise fusion. Building upon these components, our method dubbed \textbf{S2CO-Anagram} is able to generate higher-resolution anagram images with noticeably superior visual harmony and semantic faithfulness than related SOTA approaches, all while achieving substantially faster inference speed. Code will be publicly available.
Authors: Zhenhua Wu, Yun Pang, Mingkun Chang, Yuwei Ning, Liangzhi Wang, Yi Xiao, Guanbin Li
Abstract: Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect and reproduce at scale. Editable 3D Gaussian Splatting (3DGS) simulation offers a promising alternative by reconstructing real driving scenes and supporting controllable scene editing. However, edited 3DGS-rendered videos still suffer from a significant Sim-to-Real gap, including rendering artifacts, degraded foreground assets, inconsistent illumination, and temporal flickering. Existing restoration and video generation methods are insufficient for this task, as they often fail to jointly repair 3DGS-specific artifacts, improve visual realism, and ensure temporal consistency. To fill this gap, we propose RealityBridge, a structure-preserving and asset-aware Sim-to-Real framework for edited 3DGS driving videos. RealityBridge uses multimodal controls, including rendered videos, foreground masks, edge maps, and semantic masks, together with a lightweight GateNet for adaptive condition allocation across backbone layers. We further construct targeted training data and introduce autoregressive long-video training with reward-guided post-training to improve restoration quality, temporal stability, and hallucination suppression. Extensive experiments on internal and public driving datasets show that RealityBridge outperforms existing methods in artifact removal, illumination harmonization, and long-sequence temporal consistency.
Authors: Hongzhu Yi, Zhongtian Luo, Tong Li, Yiyan Fan, Jungang Xu
Abstract: One-step diffusion editors are fast because they avoid inversion and iterative optimization, but a single transport update must be aggressive enough to realize the target prompt and conservative enough to preserve the source image--and no fixed update strength satisfies both demands across edit types. We treat this tension as a post-hoc candidate-selection problem on top of energy-field transport rather than as a new editing model. Our proposed method, Riemannian Residual Line Search, first builds a stronger edit by estimating the local time curvature of the prompt-delta field and projecting the corrected direction back onto the update norm of the original first-order energy-field transport estimation. It then forms a small residual path from the source image to this strong edit, retains the original first-order output as one candidate, and picks the final image by maximizing target-prompt CLIP alignment. On a 700-sample PIE-Bench++ evaluation across 10 edit type IDs, our method achieves state-of-the-art (SOTA) performance among current one-step update algorithms.
Authors: Rajat Modi, Sebastian Noel, Xin Liang, Yogesh Singh Rawat
Abstract: Test Time Training (TTT) is a mechanism in which a model adapts to an incoming test-sample by performing some self-supervised (SSL) task and updating its weights even during inference. This procedure does not require labels at test-time. This paper focuses on TTT for long-videos. A major concern with existing approaches is: 1) they perform TTT updates using a sliding window containing frames in the past, whose compute increases linearly with the size of window. This becomes computationally intractable when the videos are hours long. 2) TTT is performed even when temporally close frames look similar, thereby consuming a lot of compute. We present the Frame Forgetting Network (FFN) that: 1) operates on only three frames within the sliding window, namely the frame that exits, the current frame and the frame after that. The model still manages to retain temporal context and work for hours long-videos; 2) mathematically define a surprise metric: how much new information the incoming frame contains with respect to the past seen frame. This facilitates determining how to modify the effective window size during TTT and constitutes the core mechanism of an adaptive windowing algorithm. Additionally, we curate a dataset EpicTours containing up to 3 hour long videos of walking city-tours, whereas earlier datasets on this problem were only 5 min long. We demonstrate FFNs empirical effectiveness on dense-segmentation, video classification tasks, generalization to depth-estimation, and multi-hour long videos.
Authors: Xinyu Wang, Chongbo Zhao, Fangneng Zhan, Yue Ma
Abstract: Streaming video editing has made rapid progress, yet practical deployment is still limited by two core issues: maintaining stable backgrounds and non-edited regions over time, and achieving the low latency required for real-time interactive scenarios. Meanwhile, recent streaming video generation methods are mostly developed for synthesis and cannot be directly applied to editing due to the strict preservation requirement and region-specific control. In this work, we present a novel streaming video editing framework that performs causal, frame-by-frame editing with strong content preservation and real-time responsiveness. Our key design is a three-stage distillation pipeline that progressively transfers editing capability from a powerful bidirectional foundation model to an efficient unidirectional streaming editor, enabling stable long-horizon edits without sacrificing visual fidelity. To further support real-time deployment, we introduce an AR-oriented mask cache that reuses region-related computation across frames, substantially reducing redundant processing and accelerating inference. Finally, we establish a dedicated benchmark for streaming video editing. Extensive evaluations demonstrate that our method achieves state-of-the-art visual quality among streaming baselines while drastically boosting inference speed to 12.66 FPS, making it suitable for interactive and augmented reality applications.
Authors: Zheqi Lv, Zhibo Zhu, Jinke Wang, Qi Tian, Shengyu Zhang, Zhengyu Chen, Chengxi Zang, Zhou Zhao, Fei Wu
Abstract: Video Diffusion Models (VDMs) is constrained by immense computational costs. While offline calibration-based acceleration suffers from calibration data dependency, prohibitive calibration duration, and susceptibility to distribution shifts, offline calibration-free methods eliminate these hurdles. However, since they rely on instantaneous zero-order approximations where the mapping between input and output differences varies in real-time, they are susceptible to observational noise and ignore the intrinsic momentum within the diffusion trajectory. In this paper, we propose NaviCache, a plug-and-play test-time self-calibration method re-conceptualizing feature evolution as an Inertial Navigation System (INS) problem. NaviCache bridges the fundamental domain gap and the non-stationary nature of diffusion by modeling the relative coupling between input and output variations. We introduce a dual-state estimation architecture that adaptively tracks the feature change ratio and its latent drift, initialized via a specialized Initial Alignment phase. By integrating a time-dependent noise schedule with an uncertainty-aware Measurement Update mechanism, NaviCache provides a theoretically grounded mechanism for error-bounded computation skipping. Extensive experiments on the HunyuanVideo, Wan, and Open-Sora series demonstrate that NaviCache exhibits more accurate error judgment for computation skipping and achieves outstanding comprehensive performance.
Authors: Haoyu Chen, Kaichen Zhou, Hang Hua, Kaile Zhang, Jingwen Qian, Wufei Ma, Haonan Chen, Chunjiang Liu, Yizhou Zhao, Xiaoyuan Wang, Weiyue Li, Alan Yuille, Paul Pu Liang, Yilun Du
Abstract: Video generation models aspire to simulate dynamic environments, and several benchmarks now evaluate memory consistency across frames. However, most assess consistency only while the target remains in view, and the few that force objects out of view evaluate static scenes where nothing changes during occlusion. To bridge this gap, we introduce MemoBench, a diagnostic benchmark built around the disappear-and-reappear paradigm in dynamically changing environments: a target object undergoes a physical process, disappears from view, and must be correctly recovered in its updated state upon reappearance. We curate 360 ground-truth clips spanning synthetic and real-world scenes, and design an evaluation suite combining automated metrics with VQA-based assessment across four diagnostic pillars. Evaluation of eight state-of-the-art models reveals key insights and open challenges regarding memory consistency under the disappear-and-reappear paradigm.
Authors: David Charatan, Daniel Xu, Richard Szeliski, George Kopanas, Vincent Sitzmann
Abstract: Differentiable rendering has emerged as a powerful approach for 3D reconstruction and novel view synthesis. State-of-the-art differentiable rendering methods combine a variety of custom representations of 3D geometry and appearance with specialized renderers. However, most downstream tasks in computer graphics rely on 3D meshes. While prior work has attempted differentiable rendering with mesh representations, these approaches are limited to object-centric scenes and fail to reconstruct large-scale, unbounded scenes. In this work, we introduce Meshtryoshka, a novel mesh differentiable rendering framework that combines an off-the-shelf triangle rasterizer with a 3D representation that consists of nested mesh shells which resemble a matryoshka doll. In every forward pass, the mesh shells are extracted anew from a 3D signed distance function via iso-surface extraction, and the opacities for each vertex are computed as a function of signed distance. Each mesh shell is then rasterized independently, and the final image is created via alpha compositing. Crucially, mesh vertex positions are updated only indirectly via gradients that flow through the opacity values into the signed distance function, and hence, our method is compatible with off-the-shelf mesh renderers that need not be differentiable with respect to vertex positions. On object-centric scenes, our method performs competitively with surface-based differentiable rendering techniques. Our differentiable mesh rendering method scales to unbounded, real-world 3D scenes, where it yields high-quality novel view synthesis results approaching those of state-of-the-art, non-mesh methods. Our method suggests that it may be possible to solve the differentiable rendering problem without relying on specialized renderers, only using conventional tools from the computer graphics toolbox.
Authors: Kaiqi Liu, Yunyao Mao, Ziqi Cai, Zheng Geng, Jing Wang, Qiulin Wang, Xintao Wang, Pengfei Wan, Kun Gai, Shuchen Weng, Boxin Shi
Abstract: While recent generative models produce high-fidelity videos, they struggle with the complex narrative control required for coherent multi-shot audio-visual generation. Existing methods suffer from temporal misalignment, limited controllability, and incomplete scripting. In this paper, we propose MAVIN, the first framework for multi-shot audio-visual generation with customized narrative control. To resolve temporal misalignment, we propose boundary-aware attention, which leverages hierarchical captions and boundary-aware token routing to render audio-visual elements within their respective temporal boundaries. To improve the controllability for multi-subject scenarios, we propose ID-aware propagation, utilizing identity embeddings and an identity-aware mask to bind specific identities to consistent visual appearances and vocal timbres. To provide comprehensive audio-visual narratives, we present a multi-agent scripting pipeline to transform free-form user inputs into hierarchical captions. Furthermore, we construct MAVINSet, a multi-shot audio-visual dataset for robust training and evaluation. Extensive experiments demonstrate that MAVIN achieves state-of-the-art performance, opening up a new avenue for integrating generative models into professional filmmaking workflows.
Authors: Yaofu Liu, Wanli Lan, Jinxi Li, Binhang Yuan, Harry Yang
Abstract: In $\textbf{DiT-based video generation models equipped with 3D Rotary Position Embeddings (3D RoPE)}$, the attention mechanism remains a primary computational bottleneck due to its quadratic complexity with respect to sequence length. While quantized $\textbf{FlashAttention}$ offers a promising path toward hardware acceleration, existing low-bit quantization methods overlook two critical challenges in this setting: $\textbf{1)}$ applying online rotation matrices -- a widely used technique for mitigating outliers in Queries ($Q$) and Keys ($K$) -- is difficult to reconcile with $\textbf{RoPE}$; and $\textbf{2)}$ the non-negative attention matrix $P = \exp(QK - \max(QK))$ makes symmetric quantization waste half of the 4-bit dynamic range. In this work, we observe that the outlier distributions of $Q$ and $K$ are strongly affected by the dimensional partitioning of $\textbf{3D RoPE}$. Based on this finding, we propose $\textbf{RotateAttention}$, an efficient $\textbf{mixed-precision INT4 FlashAttention}$ framework tailored for $\textbf{DiT-based video generation models with 3D RoPE}$, using selective $\textbf{FP16 fallback}$ for accuracy-sensitive attention blocks and denoising steps. RotateAttention introduces two core techniques: $\textbf{1) RoPE-aware Rotation}$, which employs either mergeable rotation matrices that can be fused into RoPE or negligible-overhead matrices to mitigate RoPE-induced outliers in $Q$ and $K$; and $\textbf{2) Range-optimized $P$ Quantization}$, which uses fixed scales and zero-points to fully exploit the $\textbf{INT4 numerical range}$ with minimal computational overhead. Experiments show that $\textbf{RotateAttention}$ preserves video generation quality nearly identical to full-precision baselines while achieving up to 1.68$\times$ end-to-end speedup and 2.2$\times$ kernel-level acceleration.
Authors: Nisreen Albzour
Abstract: Multimodal CT-MRI registration is central to image-guided radiotherapy, surgical navigation, and diagnostic workflows, but most pipelines report only aggregate quality metrics without per-case reliability signals. We propose a reliability-aware framework that converts registration quality into Green/Yellow/Red risk categories using data-learned thresholds. CT images were registered to T1-weighted MRI using rigid and affine transformations on 90 paired slices from 18 patients across brain, abdominal, and neck anatomies. Reliability was assessed using Delta NMI, Delta SSIM, Dice overlap, registration stability, and inverse consistency error, combined into a single score R. Thresholds learned from training patients were applied unchanged to held-out test patients. Affine registration outperformed rigid registration on NMI and SSIM, yielding 44% Green classifications versus 33% for rigid. Reliability-filtered registrations improved the average alignment profile compared with unfiltered methods. Per-anatomy analysis showed substantial variation, with stronger reliability for abdominal registrations than brain registrations. Weight sensitivity analysis identified Dice overlap as the dominant reliability component. The proposed framework provides an interpretable quality-control layer for multimodal registration, while risk thresholds reflect statistical rather than clinical validation.
Authors: Jaeyoung Kim, Eunseok Kim, Dongsuk Jang
Abstract: Whether a hyperbolic representation model uses its geometry cannot be inferred from curvature alone: what matters is the dimensionless operating point $\sqrt{c}\rho$ and whether the radial and cone mechanisms are operational there. We develop necessary-condition diagnostics and audit three published hyperbolic vision-language families -- MERU, HyCoCLIP, and PHyCLIP -- across released checkpoints and matched interventions. All converged checkpoints remain near-Euclidean ($H(u)\approx1$; none reaches $\sqrt{c}\rho>1$), and releasing the curvature floor changes $c$ and norms without leaving this regime or substantially degrading downstream performance. Entailment cones are inactive or saturated, and graded traversal fails under controlled readouts, including the models' native distance metrics. External parent-child ordering shows no shuffle-controlled pair-specific radial signal at quantified sensitivity; the only surviving pair-specific signal, a statistically detectable but small residual on the GRIT box-to-full-caption relation, remains non-operative under the evaluated readouts. Taxonomy correlations show no detectable norm contribution beyond cosine, and coarse-retrieval gains co-vary with box/compositional supervision without establishing an active radial mechanism. Gradient diagnostics expose a low-curvature, wide-cone shortcut in the entailment objective. A closed-form aperture identity places the saturation edge at $\sqrt{c}\rho\le2K$: with the floor released, all trained relation-level parent means lie at or below this edge, leaving the parent cones fully or nearly saturated. Entailment-off runs pass the edge and continue contracting. The shortcut is the dominant accelerator of collapse, not its sole cause. These audited formulations do not show an operative radial/cone mechanism under our diagnostics. We distill the audit into a five-number geometry report for hierarchy claims.
Authors: Zhiwei Yang, Yuanchen Wu, Nan Zhang, Yucong Meng, Ke Yan, Shouhong Ding
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong perception and reasoning capabilities. However, most existing models focus on isolated objects and neglect structured relationships for efficient target navigation, limiting their performance on visually intensive tasks. To address this challenge, we introduce Scene Graph Thinking (SaGe), a novel paradigm that enables fine-grained and structured visual reasoning through explicit scene-graph representations. Specifically, we first introduce an automated data engine that converts flat image-text corpora into structured scene graphs, where hierarchical entities constitute the nodes and diverse visual relations define the edges. Building upon this, we construct 120K high-quality training data by sampling reasoning traces from scene graphs. Then, two-stage graph-aligned post-training paradigms are introduced, where supervised fine-tuning internalizes MLLMs with structured reasoning, and subsequent reinforcement fine-tuning proposes node-as-proxy graph rewards to consolidate efficient graph exploration. With curated data and graph-aligned training, our approach achieves significant improvements across eight multimodal benchmarks, demonstrating strong effectiveness on fine-grained perception and reasoning tasks. Code is available at https://github.com/zwyang6/SaGe.
Authors: He Liang, Chenyang Ma, Yiming Zhang, Sangyun Shin, Andrew Markham, Niki Trigoni, Yuhang He
Abstract: Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions grounded in simplified single-room 3D scenes, lacking the ability to reason over real-world household environments containing multiple interconnected rooms and diverse object categories. We introduce CAIRN, a topology-aware 3D-LLM for multi-room 3D scene understanding. CAIRN aligns transformer attention with scene hierarchy, giving the model explicit awareness of object-level relations and room-level connectivity. It enriches object tokens with room-local relational context via a graph neural network, introduces learned room tokens for room-level abstraction, and applies a hierarchical attention mask with geometric bias to route information according to scene topology. CAIRN is developed on CAIRN-MR, a benchmark we introduce on HM3D for multi-room 3D scene understanding, covering grounding, captioning, and four question-answering tasks that progressively evaluate from intra-room perception to cross-room reasoning. Experiments show that CAIRN outperforms prior 3D-LLMs by a large margin across all CAIRN-MR tasks while remaining competitive on five single-room benchmarks.
Authors: Kyuan Oh, Bumsoo Kim
Abstract: Large vision-language models incur substantial inference costs because high-resolution inputs introduce thousands of visual tokens, many of which are redundant for a given query. Existing pruning methods often combine query relevance and token diversity, yet these objectives can conflict under aggressive compression: relevance-driven selection may overconcentrate the budget on correlated local evidence, while diversity-driven selection may suppress indispensable tokens or retain distinct but uninformative regions. We introduce AnchorPrune, a training-free framework that first constructs a protected relevance anchor and then expands it with complementary visual context. AnchorPrune adaptively determines the anchor size from the novelty profile of relevance-ranked tokens, preserving a compact set of query-critical evidence, and allocates the remaining budget through importance-weighted novelty to recover informative, non-redundant context relative to the anchor. This ordered design prevents contextual expansion from displacing indispensable query cues while improving overall visual coverage. AnchorPrune is lightweight, architecture-aware, and requires neither retraining nor model modification. Across image and video vision-language models and benchmarks, it consistently improves the accuracy-efficiency trade-off over training-free baselines, particularly under severe compression. On LLaVA-NeXT-7B, AnchorPrune preserves 97.6% of full-token performance using only 160 of 2,880 visual tokens. These results establish relevance-anchored contextual expansion as an effective principle for efficient multimodal inference. Code is available at https://github.com/MULTI-cau/AnchorPrune.
Authors: Fatimah Zohra, Chen Zhao, Shuming Liu, Bernard Ghanem
Abstract: Contrastive Language-Image Pre-training (CLIP) relies on softmax-based self-attention, a strictly positive distribution that assigns probability mass to every pair of tokens-even semantically irrelevant ones. While these dense softmax weights are effective for gathering broad context during pre-training, they spread attention across many low-salience tokens, producing noise that obscures the fine-grained, spatially localized cues required for dense, open-vocabulary prediction. We study an inference-time substitution of the row-wise softmax in the final visual self-attention layers with the $\alpha$-entmax transform, applied across both the standard query-key attention and self-correlation variants. Because entmax applies a data-dependent threshold that maps low scores exactly to zero, it acts as an implicit denoiser, zeroing contextually irrelevant dependencies while redistributing mass onto the most relevant tokens. We evaluate on open-vocabulary tasks-dense semantic segmentation (Pascal VOC, Pascal Context, ADE20K) and fine-grained retrieval (FG-OVD)-and find the gain from attention sparsification is proportional to how much the baseline attention spreads off the target class.
Authors: Sarthak Kumar Maharana, Shambhavi Mishra, Yunbei Zhang, Shuaicheng Niu, Taki Hasan Rafi, Jihun Hamm, Marco Pedersoli, Jose Dolz, Yunhui Guo
Abstract: Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failure modes: catastrophic forgetting of source knowledge and error accumulation from noisy pseudo-labels over extended time horizons. In this comprehensive survey, we formally define the CTTA problem, analyze the diverse continual domain shift patterns that characterize different evaluation protocols, and propose a hierarchical taxonomy that categorizes existing methods into three families: optimization-based strategies (entropy minimization, pseudo-labeling, parameter restoration), parameter-efficient methods (normalization layer adaptation, adaptive parameter selection), and architecture-based approaches (teacher-student frameworks, adapters, visual prompting, masked modeling). We systematically review representative methods within each category and present comparative benchmarks and experimental results across standard evaluation settings. Finally, we discuss the limitations of current approaches and highlight emerging research directions, including the adaptation of foundation models and black-box systems, thereby providing a roadmap for future research in robust continual test-time adaptation.
Authors: In-Hwan Jin, Hyeongju Mun, Joonsoo Kim, Kugjin Yun, Kyeongbo Kong
Abstract: Dynamic scene reconstruction remains challenging due to the heterogeneous and spatially varying nature of real-world motion. Although recent 3D Gaussian Splatting methods have introduced diverse deformation formulations for dynamic novel view synthesis, each method typically relies on a single deformation model within its representation, which limits robustness across diverse dynamic scenarios. In this work, we study a fundamental problem-multi-deformation modeling for dynamic 3D Gaussian representations-under two distinct integration constraints that differ in when and how multiple deformation experts interact during training. From a Mixture-of-Experts (MoE) perspective, we view multi-deformation modeling as the problem of combining multiple specialized deformation models within a unified 3D representation. We first introduce Mixture of Deformation Experts (MoDE), which integrates multiple deformation experts directly into the deformable Gaussian Splatting pipeline through joint optimization. In MoDE, experts operate on a shared canonical Gaussian representation, enabling multi-deformation modeling without introducing additional training stages or modifying the original optimization schedule. In contrast, we further present Mixture of Experts for Dynamic Gaussian Splatting (MoE-GS) under a different integration constraint, where deformation experts are optimized independently and combined through a separate routing stage. As a result, expert interaction occurs over non-canonical Gaussian representations after individual optimization. Together, these two approaches provide alternative strategies for multi-deformation modeling, clarifying how integration constraints shape the design and behavior of deformation experts in dynamic 3D Gaussian representations. Our code is available at: https://github.com/cvsp-lab/MoE-GS-studio.
Authors: Haoran Feng, Ruiyang Zhang, Longyi Zhang, Dizhe Zhang, Lu Qi
Abstract: In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream task-specific fine-tuning. To address the lack of large-scale, high-quality training data tailored to in-context panoramic tasks, we propose Canvas360Dataset, a collection of 1M high-quality paired panoramic samples for style transfer, inpainting, outpainting, and editing, enabling effective supervision across diverse in-context generation scenarios. On the modeling side, Canvas360 enhances text-to-panorama generation through parallel depth generation, velocity circular padding, and similarity loss regularization, enabling the model to learn geometry-aware representations, capture object distortion details, and improve geometric consistency and global coherence. Furthermore, empowered by strong panoramic priors, Canvas360 enables a unified in-context panoramic generation framework that supports diverse downstream tasks via token-level concatenation, surpassing prior methods in both task coverage and modeling flexibility. Extensive experiments show that Canvas360 improves panoramic image fidelity, achieving particularly strong performance on the panorama-specific FAED metric and competitive or leading results across the reported quantitative evaluations. More information can be found on our project page: https://zry000.github.io/Canvas360/
Authors: Jaesun Baek, Chanwook Lee, Eun-Kyu Lee
Abstract: Event-based vision and spiking neural networks (SNNs) are increasingly adopted for edge intelligence under strict latency and energy constraints. However, the vulnerability of event-based SNN object detection models to availability backdoor attacks remains insufficiently studied. This paper presents Event Burst Trigger (EBT), an availability backdoor attack targeting SNN-based object detection models. EBT injects carefully crafted event-based triggers into the training data, which induce temporally concentrated event streams during inference. These burst-like activations increase the number of phantom (i.e., spurious) object candidates, and consequently inflate the computational cost of the post-processing stage, particularly Non-Maximum Suppression (NMS). We evaluate EBT on SpikeYOLO, the state-of-the-art SNN-based object detector, under a poison-only threat model that does not require modifications to the model architecture, loss function, or inference pipeline. Experimental results show that while detection accuracy remains largely preserved, with mAP@0.5 decreasing by less than 0.099, the latency of the NMS stage increases by up to 38%. This indicates that NMS can become a dominant availability bottleneck in event-based SNN object detection. Experiments on an edge platform further show that the proposed attack elevates baseline resource utilization and reduces scheduling slack without inducing conspicuous peaks in resource usage. In addition, STRIP-based backdoor detection fails to reliably distinguish the proposed attack from benign inputs. These results characterize a previously underexplored availability backdoor threat in event-based SNN object detection systems.
Authors: Mingyang Huang, Peng Zhang, Li Hu, Guangyuan Wang, Bang Zhang
Abstract: Generating long-duration, high-definition, and rhythmically synchronized dance videos directly from music remains a significant challenge, primarily due to the temporal constraints of current diffusion models, which typically fail beyond 20 seconds. Existing approaches, whether they rely on intermediate 3D skeletons or on end-to-end video synthesis, suffer from temporal drift, identity inconsistency, and repetitive motion patterns when extended to longer horizons. To address these limitations, we propose a novel hierarchical framework for minute-scale coherent music-to-dance generation. Our method decouples the process into global keyframe planning and local temporal refinement, leveraging full-track musical context to ensure long-range coherence. Key innovations include dynamic frame rate adaptation via time-mapped RoPE embeddings for precise alignment, an optical-flow-based loss function to enhance motion continuity, and motion-speed control to preserve high-fidelity details during rapid movements. Extensive experiments demonstrate that our framework surpasses the conventional duration barrier, generating stable, 720p/30fps videos exceeding one minute with superior temporal stability. Furthermore, the model exhibits robust versatility across five distinct dance genres, conditioned on both audio and textual prompts, establishing a new state-of-the-art in coherent, long-form dance video synthesis.
Authors: Xiaokai Bai, Lianqing Zheng, Runwei Guan, Songkai Wang, Siyuan Cao, Hui-liang Shen
Abstract: Reliable autonomous driving requires full-scene perception that couples foreground objects with dense semantic layout. Recently, 4D millimeter-wave radar has emerged as a robust and affordable sensor, yet its sparse returns make radar-camera fusion necessary for comprehensive scene understanding. Existing radar-camera methods mainly optimize detection, while dual-task systems usually decode boxes and occupancy with limited interaction. To address this gap and advance radar-based multi-task learning, we propose \method, a 4D radar-camera framework for 360$^\circ$ full-scene perception, which models semantic occupancy as a persistent scene state rather than a terminal output. \method{} follows a cross-modal state reasoning paradigm, where the occupancy state is modeled and propagated through stages for coarse-to-fine feature aggregation. Specifically, State-guided BEV Enhancement (SBE) strengthens intra-frame BEV representation, while Doppler-guided Temporal Fusion (DTF) preserves state evidence over longer temporal horizons. Beyond the model, we further extend ManTruckScenes with satellite-map-based generated occupancy labels and pair it with OmniHD-Scenes in a unified cross-dataset detection-and-occupancy protocol. The resulting experiments cover accuracy, robustness, ablation, and efficiency under one radar-camera multi-task evaluation framework. Code and labels will be released upon acceptance.
Authors: Abdul-mojeed Olabisi Ilyas, Adeleke Maradesa, Jamal Banzi, Jianpan Huang, Henry K. F. Mak, Kannie W. Y. Chan
Abstract: Medical imaging plays a vital role in clinical diagnosis, yet AI-driven imaging methods remain challenged by patient variability, image artifacts, and limited robustness across acquisition conditions. Although deep learning has advanced medical image analysis, 3D image translation remains hindered by limited training data and variability arising from scanner differences, imaging protocols, and patient motion. Conventional data augmentation typically relies on a single transformation pipeline, overlooking augmentation-specific characteristics and limiting representation learning. To address these challenges, we propose Multi-Encoder Augmentation-Aware Learning (MEAL), which processes multiple augmentation variants through dedicated encoder pathways. Three feature integration strategies are investigated: encoder concatenation (MEAL-CC), fusion layer (MEAL-FL), and an adaptive controller block (MEAL-BD). By dynamically weighting augmentation-specific features before decoding, MEAL-BD preserves complementary representations and improves robustness to clinically relevant variability. We evaluate MEAL using CT-to-T1-weighted MRI translation, a clinically relevant task when MRI is unavailable, contraindicated, or delayed. Across predefined and unseen test datasets, MEAL-BD consistently outperformed competing approaches under both geometric perturbations and standard imaging conditions, achieving higher peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). By prioritizing structural fidelity over perceptual realism, MEAL supports clinical interpretation and downstream image analysis rather than replacing diagnostic MRI, demonstrating that augmentation-aware representation learning improves the robustness and clinical applicability of medical image translation.
Authors: Xiaolong Qian, Qi Jiang, Yao Gao, Lei Sun, Kailun Yang, Xian Wang, Zhonghua Yi, Wenyong Li, Ming-Hsuan Yang, Luc Van Gool, Kaiwei Wang
Abstract: Emerging deep-learning-based lens library pre-training (LensLib-PT) pipeline offers a new avenue for blind lens aberration correction by training a universal neural network, demonstrating strong capability in handling diverse unknown optical degradations. This work proposes FoundCAC, a universal foundational framework that resolves two challenges hindering the generalization of existing pipelines: the difficulty of scaling training data and the absence of prior guidance characterizing optical degradation. To improve data scalability, we expand the design specifications to increase degradation diversity and construct AODLibpro, a large-scale lens library using stratified sampling over spatial-variation patterns and degradation severity. In terms of model design, to leverage Point Spread Functions (PSFs) as guidance while maintaining the blind paradigm, we propose a multi-stage vector-quantized representation learning scheme. This paradigm is specifically designed to construct a Latent PSF Representation (LPR), explicitly encoding complex continuous PSFs into a discrete degradation prior to regularize the highly ill-posed restoration process. Through a simple yet effective codebook-freezing strategy, our framework leverages the discrete prior to elevate full-shot restoration performance and unlock highly efficient few-shot adaptation for unseen lenses. Experiments on synthetic LensLib, real-design simulations, and real-captured lenses show that our framework achieves state-of-the-art zero-shot performance under complementary evaluation protocols, while enabling highly efficient few-shot adaptation for specific lenses. The source code and datasets will be made publicly available at https://github.com/zju-jiangqi/FoundCAC.
Authors: Mohammed Talha Alam, Nada Saadi, Fahad Shamshad, Nils Lukas, Karthik Nandakumar, Fahkri Karray, Samuele Poppi
Abstract: Text-to-image diffusion models can emit copyrighted, unsafe, or private content. Safety alignment aims to suppress specific concepts, yet evaluations seldom test whether safety persists under benign downstream fine-tuning routinely applied after deployment (e.g., LoRA personalization, style/domain adapters). We study the stability of current safety methods under benign fine-tuning and observe frequent breakdowns. As true safety alignment must withstand even benign post-deployment adaptations, we introduce the SPQR benchmark (Safety, Prompt adherence, Quality, and Robustness). SPQR is a single-scored metric that provides a unified, reproducible framework to evaluate how well safety-aligned diffusion models preserve safety, utility, and robustness under benign fine-tuning, by reporting a single leaderboard score to facilitate comparisons. We conduct multilingual, domain-specific, and out-of-distribution analyses, along with category-wise breakdowns, to identify when safety alignment fails after benign fine-tuning, ultimately showcasing SPQR as a concise yet comprehensive benchmark for T2I safety alignment techniques for T2I models.
Authors: Xi Peng
Abstract: To develop a deep-learning method for achieving fast high-resolution MR elastography from highly undersampled data without the need of high-quality training dataset. We first framed the deep neural network representation as a nonlinear extension of the linear subspace model, then used it to represent and reconstruct MRE image repetitions from undersampled k-space data. The network weights were learned using a multi-level k-space consistent loss. To further enhance reconstruction quality, phase-contrast specific magnitude and phase priors were incorporated, including the similarity of anatomical structures and smoothness of wave-induced harmonic displacement. Experiments were conducted using both 3D gradient-echo spiral and multi-slice spin-echo spiral MRE datasets. Compared to the conventional linear subspace-based approaches, the nonlinear network representation method was able to produce superior image reconstruction with suppressed noise and artifacts from a single in-plane spiral arm per MRE repetition (e.g., 2mm isotropic resolution in 1 min with a total R=10), yielding comparable stiffness estimation to the fully sampled data. This work demonstrated the feasibility of using deep network representations to model and reconstruct MRE images from highly-undersampled data, a nonlinear extension of the subspace-based approaches.
Authors: Jaewon Lee, Jaeseok Heo, Gunmin Lee, Howoong Jun, Jeongwoo Oh, Songhwai Oh
Abstract: Safe visual navigation is critical for indoor mobile robots operating in cluttered environments. Existing benchmarks, however, often neglect collisions or are designed for outdoor scenarios, making them unsuitable for indoor visual navigation. To address this limitation, we introduce the reactive visual navigation benchmark (RVN-Bench), a collision-aware benchmark for indoor mobile robots. In RVN-Bench, an agent must reach sequential goal positions in previously unseen environments using only visual observations and no prior map, while avoiding collisions. Built on the Habitat 2.0 simulator and leveraging high-fidelity HM3D scenes, RVN-Bench provides large-scale, diverse indoor environments, defines a collision-aware navigation task and evaluation metrics, and offers tools for standardized training and benchmarking. RVN-Bench supports both online and offline learning by offering an environment for online reinforcement learning, a trajectory image dataset generator, and tools for producing negative trajectory image datasets that capture collision events. Evaluations demonstrate that policies trained on RVN-Bench generalize effectively across unseen simulated environments. Furthermore, initial physical experiments using a Jackal UGV indicate promising sim-to-real transfer. Code and additional materials are available at: https://sequor-robotics-research.github.io/projects/RVN-Bench/.
URLs: https://sequor-robotics-research.github.io/projects/RVN-Bench/.
Authors: Ming Ye, Kui Cai, Cunhua Pan, Zhen Mei, Wanting Yang, Chunguo Li
Abstract: Depthwise separable convolutional (DSConv) layers have been successfully applied to deep learning (DL)-based joint source-channel coding (JSCC) schemes to reduce computational complexity. However, a systematic investigation of the layerwise and ratio-wise replacement of standard convolutional (Conv) layers with DSConv layers in JSCC systems for wireless image transmission remains largely unexplored. In this letter, we propose a configurable lightweight JSCC framework that incorporates a selective replacement strategy, enabling flexible Conv-to-DSConv replacement at different replacement ratios and positions. By varying the replacement ratio, we obtain models with different computational complexities and analyze their impact on reconstruction performance. Furthermore, we investigate how replacements at different encoder and decoder depths influence reconstruction quality under a fixed replacement ratio. Our results show that Conv-to-DSConv replacement at the intermediate layers of the encoder and decoder achieves a favorable complexity-performance trade-off, revealing layer-wise redundancy in DL-based JSCC systems. Extensive experiments further demonstrate that the proposed framework achieves substantial parameter reduction with only slight performance degradation, enabling flexible complexity-performance trade-offs for resource-constrained edge devices.
Authors: Nihanth W. Cherukuru, Matt Rehme, Kirsten J. Mayer, David John Gagne, John Schreck, John Clyne, Charlie Becker
Abstract: Earth system science is producing increasingly large, high-dimensional datasets from both physics-based and AI-driven models. While embedding-based representations make these data searchable and serve as foundational building blocks for AI-driven discovery engines, nearest neighbors in latent spaces are not automatically scientifically meaningful. They may reflect real meteorological structures, or simply artifacts of preprocessing, geography, or model bias. Researchers therefore need visual tools to inspect latent space organization, trace search results back to physical evidence, and evaluate candidate representations against one another. We present an open source visual analytics workbench designed to support this provenance-aware scientific retrieval workflow. The system links distinct embedding experiments to shared source data, metadata, spatial contexts, and model configurations. It enables interactive retrieval strategy design by allowing users to issue image-level and localized patch-level queries, apply multi-constraint filters, and inspect analogs through familiar meteorological views. This facilitates a discovery loop where scientists characterize a phenomenon in a well-understood dataset and use its latent signature to probe larger archives. While we demonstrate the workbench through a tropical cyclone retrieval scenario using a vision foundation model (DINOv3) on ERA5 data, the framework is model-agnostic and designed to integrate with other embedding architectures in the future. Finally, we evaluate its out-of-core retrieval backend, demonstrating that interactive visual search over tens of millions of embeddings is highly scalable on commodity hardware.
Authors: Shijie Lian, Bin Yu, Xiaopeng Lin, Zhaolong Shen, Laurence Tianruo Yang, Yurun Jin, Haishan Liu, Changti Wu, Hang Yuan, Cong Huang, Kai Chen
Abstract: Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context. Existing frame-conditioned VLA policies infer each chunk from the current observation and instruction alone, so under partial observability they may resample different intents across adjacent replanning steps, leading to inter-chunk conflict and unstable execution. We introduce IntentVLA, a history-conditioned VLA framework that encodes recent visual observations into a compact short-horizon intent representation and uses it to condition chunk generation. We further introduce AliasBench, a 12-task ambiguity-aware benchmark on RoboTwin2 with matched training data and evaluation environments that isolate short-horizon observation aliasing. Across AliasBench, SimplerEnv, LIBERO, and RoboCasa, IntentVLA improves rollout stability and outperforms strong VLA baselines
Authors: Xinggang Hu, Chenyangguang Zhang, Alexandros Delitzas, Xiangkui Zhang, Marc Pollefeys, Francis Engelmann, Xiangyang Ji
Abstract: Functional 3D scene graphs offer a versatile and flexible representation for 3D scene understanding and robotic manipulation, defined by object nodes, interactive elements, and functional relationship edges. However, their potential remains underexplored due to the limited coverage of existing benchmarks and the overly straightforward design of previous pipelines, which primarily focus on large-scale furniture but lack of hierarchical structures. Therefore, in this work, we extend the benchmark coverage by introducing dense tabletop objects and explicit multi-level functional relationships. This expansion introduces critical challenges involving small-scale, dense, and similar instances, with lack of visual anchoring in relational reasoning, instance confusion during cross-frame fusion, and attribution uncertainty under dynamic viewpoints. To address these issues, we propose an open-vocabulary pipeline based on 2D visual grounding and 3D graph optimization. Specifically, we anchor fine-grained functional edges from 2D visual evidence, and associate nodes across frames in 3D using multiple cues. Furthermore, edge association is formulated as temporal graph optimization, integrating evidence accumulation, entropy regularization, and temporal smoothing to robustly determine the functional connections of each node. Finally, global hierarchy shaping is performed to recover the hierarchical graph structure. Extensive experiments demonstrate that the proposed method can reliably infer functional 3D scene graphs in challenging real-world scenes, thereby further unlocking their potential for practical applications.
Authors: Yu Zhang, Yidi Shao, Wenqi Ouyang, Yushi Lan, Zhexin Liang, Chengrui Wu, Xudong Xu, Xingang Pan
Abstract: Unified and scalable Transformers have recently achieved remarkable success in modeling diverse phenomena traditionally associated with computer graphics, such as 3D visual effects, rendering processes, and motion in videos. In this work, we take a step further by investigating whether modern Transformer techniques can tackle the challenging task of cloth simulation. To this end, we present ClothTransformer, a framework that reformulates cloth simulation as autoregressive sequence modeling in a learned latent space. Existing neural cloth simulators are largely specialized to single scenarios, intrinsically coupled to the mesh discretization, and lack robust collision handling. Our approach addresses these limitations through three contributions: (1) a unified Transformer architecture that handles diverse scenarios -- body-driven garments, robotic manipulation, and free-fall collisions -- under a single model and achieves approximately $4$--$9{\times}$ lower error than prior state-of-the-art methods across all scenarios; (2) a scalable latent-space formulation that compresses arbitrary-resolution meshes into a fixed-size set of latent tokens, making temporal dynamics computation independent of mesh resolution; and (3) a diverse-scenario high-fidelity penetration-free dataset of ${\sim}$493.4k frames spanning all three settings, which enables a differentiable Continuous Collision Detection (CCD) module to suppress penetration artifacts. Project Page: https://yucrazing.github.io/clothtransformer/
Authors: Umut Onur Yasar
Abstract: We investigate how teacher-student capacity relationships modulate knowledge distillation (KD) effectiveness in ResNet-based image classification on CIFAR-10. Across four teacher-student pairs (R50->R18, R34->R18, R50->R34, and R101->R34) we compare Logit-KD and Feature-KD under a strict evaluation protocol: hyperparameters and checkpoints are selected on a held-out validation split, selected configurations are re-run with five seeds, and the test set is used exclusively for final reporting. Beyond accuracy, we measure distillation fidelity directly via teacher-student agreement and KL divergence. We report four findings. First, the student-capacity pattern survives the corrected protocol at reduced magnitude: the only statistically significant gains occur for R34 students under Feature-KD (+0.19 and +0.21 pp, p<0.05), in two pairs whose teachers differ two-fold in parameters but not in accuracy, localizing the moderating variable on the student side, while no KD gain for R18 students is distinguishable from zero. Second, Feature-KD matches or outperforms Logit-KD in all four pairs, and its students land closer to the teacher's output distribution (KL at T=1) than Logit-KD students despite never observing teacher logits. Third, top-1 teacher-student agreement is flat across all pairs, decoupling fidelity from accuracy gains. Fourth, architecture dominates KD: correcting the ResNet stem for 32x32 inputs is worth +5.5 to +7.2 pp, more than 25x the largest KD gain. We also retract an attribution made in v1: a controlled re-run shows the reported gradient-clipping bug had no measurable effect, and v1's larger gains are explained by test-set selection. Code and results: github.com/umutonuryasar/kd-capacity-gap (tag v2.0).
Authors: Nadav Benedek, Tomer Koren, Ohad Fried
Abstract: AdamW is a default optimizer for modern deep learning, but its first and second moment states add roughly two parameter-sized buffers to training memory, increasing the already substantial cost of large-scale pretraining. We propose Gefen, a memory-efficient optimizer that automatically shares second-moment estimates across parameter blocks and quantizes the first moment using a learned codebook, thereby reducing AdamW's memory footprint by ~8x while maintaining the same performance, corresponding to a reduction of 6.5 GiB per billion parameters. The method is motivated by a theoretical result showing that large mixed Hessian entries constrain the ratio of squared gradients toward one, suggesting that Hessian-aligned parameters are natural candidates for sharing second-moment statistics. Since computing Hessians is impractical at scale, Gefen infers block structure from the initial squared gradients, requiring no architecture-specific metadata or hyperparameters beyond AdamW defaults. Gefen learns an exact histogram-based dynamic-programming quantization codebook and reuses the same blocks for first-moment scaling. Across diverse pretraining experiments, Gefen achieves the lowest peak optimizer memory among the compared AdamW-like methods while maintaining AdamW-level performance. In single-machine or distributed training, the reduced memory footprint enables larger microbatches and improves throughput significantly over AdamW, providing a practical drop-in replacement with lower memory usage that can increase throughput and enable training larger models or using larger global batch sizes. We provide the complete Python implementation, including fused CUDA kernels at https://github.com/ndvbd/Gefen
Authors: Kai Wang, Zhaopeng Gu, Yixiang Chen, Yuan Xu, Qisen Ma, Jiabing Yang, Zhaowen Li, Yan Huang, Liang Wang, Peng Su
Abstract: World-action models have shown promising robot-manipulation performance by jointly predicting future visual states and actions. However, existing methods mainly rely on short-term history and short-horizon future prediction, which is insufficient for long-horizon tasks whose correct execution depends on earlier observations and task progress. Such temporally dependent tasks require effective use of complementary temporal information, including recent local context, cross-stage historical events, immediate future dynamics, and global task progress. To address long-term forgetting and poor awareness of the global task state, we introduce DiM-WAM, a memory-augmented world-action model that integrates multi-scale historical context, local future dynamics, and global task progress. The memory extracts compact visual event information from real observations, updates multiple memory banks through independent similarity-based merging, and then reads the bank-identity- and time-embedded long-term context to condition video and action denoising. A progress-supervision objective further encourages memory tokens to encode not only completed historical events but also the current task stage and its implications for the remaining task. On RMBench, DiM-WAM raises average success from 28.4% with LingBot-VA to 69.8%, exceeding the explicit-memory Mem-0 baseline at 42.0%. On four real-world Franka tasks, it improves average stage success from 70.7% to 91.5% and full-task success from 52.5% to 80.0%. Project page: https://wangkai-casia.github.io/dim-wam.
Authors: Hamidreza Mazandarani, Masoud Shokrnezhad, Tarik Taleb, Onur G\"unl\"u
Abstract: Emerging uplink-dominant 6G use cases, such as cooperative vehicular streaming, require efficient transmission of high-volume visual data over limited wireless resources. While semantic communications can reduce traffic by prioritizing task-relevant content, most existing approaches treat users independently and therefore overlook spatial redundancy among nearby devices' observations. This paper proposes a semantic-aware multiple access scheme that exploits overlapping fields of view among vehicular users to reduce redundant uplink transmissions. We formulate a joint perception and transmission control problem in which users decide which image patches to transmit, when to transmit them, and over which channel, subject to communication constraints. To address the resulting complexity, we introduce a practical two-phase approach. First, nearby vehicles share selected observation patches over Vehicle-to-Vehicle (V2V) links to calculate inter-user spatial redundancy. Second, users transmit only semantically important, non-redundant patches to the base station, where observations can be reconstructed using the received patches and complementary views from neighboring vehicles. Simulation results in a dense urban vehicular scenario demonstrate that our approach improves the proportion of users who achieve high-fidelity reconstruction, highlighting the potential of semantic-aware multiple access for sustainable and resource-efficient 6G uplink systems.
Authors: Suhyeong Park, Junha Jung, Jungwoo Park, Jaewoo Kang
Abstract: Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interaction, but dense image-side tokens make storage and scoring expensive. Existing token compression methods reduce this cost, yet they can remove or collapse object- and region-level evidence that future query tokens may need to select. We propose SaMer, an object-aware token merging framework that compresses image-side post-projector tokens into $K$ representative centroids while preserving the original late-interaction interface. SaMer uses object annotations only during training as a merge prior to discourage cross-instance mixing, requires no ground-truth bounding boxes or detectors at inference time, and adapts only the shared projection layer with frozen vision and language backbones. With $K=64$, SaMer removes more than 93% of image-side tokens and reduces ColPali storage by $16.09\times$, while improving R@1 on Flickr30K and MSCOCO. These gains arise because object-aware merging preserves query-selectable object evidence that pruning or feature-only pooling can remove or collapse. SaMer also outperforms compression baselines and shows stronger phrase-level grounding, suggesting that efficient multi-vector retrieval depends not only on reducing token count, but on preserving the evidence future query tokens need to select.
Authors: Wongyun Yu, Youngwoon Kim, Minsu Cho
Abstract: Retargeting human object interaction demonstrations to physics based simulation requires reproducing not only body motion but also the object motion and contacts that make manipulation succeed. However, position only hand trajectories do not specify the contact forces needed to manipulate objects, and directly tracking them can overconstrain contact rich finger behavior. We introduce WristMimic, a wrist guided whole body control framework that explicitly separates contact free body motion from contact rich hand manipulation. The contact free body and wrist are guided by kinematic pose targets, whereas the fingers are not directly supervised by human hand pose. Instead, they learn grasping and manipulation behaviors from object tracking and contact outcomes. Our key insight is that the wrist is the natural gate between these two regimes. It is largely free from contact and can be tracked kinematically, yet it determines the global hand configuration and places the fingers within reachable grasp affordances. To ensure reliable wrist placement during interaction, we introduce wrist specific reset constraints and reward prioritization. Experiments show that WristMimic matches or surpasses methods using full finger pose supervision while enabling finger agnostic retargeting across diverse hand embodiments.
Authors: Xinjie Wang, Liu Liu, Taojun Ding, Andrew Choi, Chaodong Huang, Mengao Zhao, Ziang Li, Jackson Jiang, Chunlei Yu, Shengxiang Liu, Wei Xu, Zhizhong Su
Abstract: We present EmbodiedGen V2, a generative 3D world engine for building executable policy-ready environments for embodied intelligence. Sim-ready 3D asset generation has advanced rapidly, yet assembling such assets into policy-ready task environments remains largely manual, limiting scalable closed-loop learning. EmbodiedGen V2 addresses this gap through a unified sim-ready representation that connects cross-simulator assets, interaction affordances, task-driven worlds, large-scale multi-room scenes, and stateful Vibe Coding into a generative, editable, and reusable simulation pipeline. The generated environments support manipulation, navigation, mobile manipulation, cross-simulator deployment, and embodied policy training. In evaluation, the asset pipeline achieves 96.5% human acceptance and 98.6% collision success, and 83.3% of task-driven worlds are directly usable for downstream simulation without manual modification. Online reinforcement learning with generated environments further improves simulation success from 9.7% to 79.8%, and transfers to real robots with task success increasing from 21.7% to 75.0%. These results establish EmbodiedGen V2 as scalable simulation infrastructure for training, evaluating, and deploying embodied policies.