Authors: Chenyu Ge
Abstract: Neural Radiance Fields (NeRF) have achieved photorealistic novel view synthesis but suffer from computational inefficiency due to dense ray sampling during volume rendering. We propose SAC-NeRF, a reinforcement learning framework that learns adaptive sampling policies using Soft Actor-Critic (SAC). Our method formulates sampling as a Markov Decision Process where an RL agent learns to allocate samples based on scene characteristics. We introduce three technical components: (1) a Gaussian mixture distribution color model providing uncertainty estimates, (2) a multi-component reward function balancing quality, efficiency, and consistency, and (3) a two-stage training strategy addressing environment non-stationarity. Experiments on Synthetic-NeRF and LLFF datasets show that SAC-NeRF reduces sampling points by 35-48\% while maintaining rendering quality within 0.3-0.8 dB PSNR of dense sampling baselines. While the learned policy is scene-specific and the RL framework adds complexity compared to simpler heuristics, our work demonstrates that data-driven sampling strategies can discover effective patterns that would be difficult to hand-design.
Authors: Yu Li, Yuchen Zheng, Giles Hamilton-Fletcher, Marco Mezzavilla, Yao Wang, Sundeep Rangan, Maurizio Porfiri, Zhou Yu, John-Ross Rizzo
Abstract: This paper investigates the potential of vision-language models (VLMs) to assist people with blindness and low vision (pBLV) in navigation tasks. We evaluate state-of-the-art closed-source models, including GPT-4V, GPT-4o, Gemini-1.5-Pro, and Claude-3.5-Sonnet, alongside open-source models, such as Llava-v1.6-mistral and Llava-onevision-qwen, to analyze their capabilities in foundational visual skills: counting ambient obstacles, relative spatial reasoning, and common-sense wayfinding-pertinent scene understanding. We further assess their performance in navigation scenarios, using pBLV-specific prompts designed to simulate real-world assistance tasks. Our findings reveal notable performance disparities between these models: GPT-4o consistently outperforms others across all tasks, particularly in spatial reasoning and scene understanding. In contrast, open-source models struggle with nuanced reasoning and adaptability in complex environments. Common challenges include difficulties in accurately counting objects in cluttered settings, biases in spatial reasoning, and a tendency to prioritize object details over spatial feedback, limiting their usability for pBLV in navigation tasks. Despite these limitations, VLMs show promise for wayfinding assistance when better aligned with human feedback and equipped with improved spatial reasoning. This research provides actionable insights into the strengths and limitations of current VLMs, guiding developers on effectively integrating VLMs into assistive technologies while addressing key limitations for enhanced usability.
Authors: Arbish Akram, Nazar Khan, Arif Mahmood
Abstract: Facial expression synthesis aims to generate realistic facial expressions while preserving identity. Existing conditional generative adversarial networks (GANs) achieve excellent image-to-image translation results, but their performance often degrades when test images differ from the training dataset. We present Regression GAN (RegGAN), a model that learns an intermediate representation to improve generalization beyond the training distribution. RegGAN consists of two components: a regression layer with local receptive fields that learns expression details by minimizing the reconstruction error through a ridge regression loss, and a refinement network trained adversarially to enhance the realism of generated images. We train RegGAN on the CFEE dataset and evaluate its generalization performance both on CFEE and challenging out-of-distribution images, including celebrity photos, portraits, statues, and avatar renderings. For evaluation, we employ four widely used metrics: Expression Classification Score (ECS) for expression quality, Face Similarity Score (FSS) for identity preservation, QualiCLIP for perceptual realism, and Fr\'echet Inception Distance (FID) for assessing both expression quality and realism. RegGAN outperforms six state-of-the-art models in ECS, FID, and QualiCLIP, while ranking second in FSS. Human evaluations indicate that RegGAN surpasses the best competing model by 25% in expression quality, 26% in identity preservation, and 30% in realism.
Authors: Lansiaux Edouard, Leman Margaux
Abstract: We present OrthoAI v2, the second iteration of our open-source pipeline for AI-assisted orthodontic treatment planning with clear aligners, substantially extending the single-agent framework previously introduced. The first version established a proof-of-concept based on Dynamic Graph Convolutional Neural Networks (\dgcnn{}) for tooth segmentation but was limited to per-tooth centroid extraction, lacked landmark-level precision, and produced a scalar quality score without staging simulation. \vtwo{} addresses all three limitations through three principal contributions: (i)~a second agent adopting the Conditioned Heatmap Regression Methodology (\charm{})~\cite{rodriguez2025charm} for direct, segmentation-free dental landmark detection, fused with Agent~1 via a confidence-weighted orchestrator in three modes (parallel, sequential, single-agent); (ii)~a composite six-category biomechanical scoring model (biomechanics $\times$ 0.30 + staging $\times$ 0.20 + attachments $\times$ 0.15 + IPR $\times$ 0.10 + occlusion $\times$ 0.10 + predictability $\times$ 0.15) replacing the binary pass/fail check of v1; (iii)~a multi-frame treatment simulator generating $F = A \times r$ temporally coherent 6-DoF tooth trajectories via SLERP interpolation and evidence-based staging rules, enabling ClinCheck 4D visualisation. On a synthetic benchmark of 200 crowding scenarios, the parallel ensemble of OrthoAI v2 reaches a planning quality score of $92.8 \pm 4.1$ vs.\ $76.4 \pm 8.3$ for OrthoAI v1, a $+21\%$ relative gain, while maintaining full CPU deployability ($4.2 \pm 0.8$~s).
Authors: Marcell Kegl, Andras Palffy, Csaba Benedek, Dariu M. Gavrila
Abstract: In this paper, we address extrinsic calibration for camera, lidar, and 4D radar sensors. Accurate extrinsic calibration of radar remains a challenge due to the sparsity of its data. We propose CLRNet, a novel, multi-modal end-to-end deep learning (DL) calibration network capable of addressing joint camera-lidar-radar calibration, or pairwise calibration between any two of these sensors. We incorporate equirectangular projection, camera-based depth image prediction, additional radar channels, and leverage lidar with a shared feature space and loop closure loss. In extensive experiments using the View-of-Delft and Dual-Radar datasets, we demonstrate superior calibration accuracy compared to existing state-of-the-art methods, reducing both median translational and rotational calibration errors by at least 50%. Finally, we examine the domain transfer capabilities of the proposed network and baselines, when evaluating across datasets. The code will be made publicly available upon acceptance at: https://github.com/tudelft-iv.
Authors: Umar Marikkar, Muhammad Awais, Sara Atito
Abstract: Computational methods on analyzing Whole Slide Images (WSIs) enable early diagnosis and treatments by supporting pathologists in detection and classification of tumors. However, the extremely high resolution of WSIs makes end-to-end training impractical compared to typical image analysis tasks. To address this, most approaches use pre-trained feature extractors to obtain fixed representations of whole slides, which are then combined with Multiple Instance Learning (MIL) for downstream tasks. These feature extractors are typically pre-trained on natural image datasets such as ImageNet, which fail to capture domain-specific characteristics. Although domain-specific pre-training on histopathology data yields more relevant feature representations, it remains computationally expensive and fail to capture task-specific characteristics within the domain. To address the computational cost and lack of task-specificity in domain-specific pre-training, we propose EfficientWSI (eWSI), a careful integration of Parameter-Efficient-Fine-Tuning (PEFT) and Multiple Instance Learning (MIL) that enables end-to-end training on WSI tasks. We evaluate eWSI on seven WSI-level tasks over Camelyon16, TCGA and BRACS datasets. Our results show that eWSI when applied with ImageNet feature extractors yields strong classification performance, matching or outperforming MILs with in-domain feature extractors, alleviating the need for extensive in-domain pre-training. Furthermore, when eWSI is applied with in-domain feature extractors, it further improves classification performance in most cases, demonstrating its ability to capture task-specific information where beneficial. Our findings suggest that eWSI provides a task-targeted, computationally efficient path for WSI tasks, offering a promising direction for task-specific learning in computational pathology.
Authors: Hippolyte Verninas, Caner Korkmaz, Stefanos Zafeiriou, Tolga Birdal, Simone Foti
Abstract: Machine learning has been progressively generalised to operate within non-Euclidean domains, but geometrically accurate methods for learning on surfaces are still falling behind. The lack of closed-form Riemannian operators, the non-differentiability of their discrete counterparts, and poor parallelisation capabilities have been the main obstacles to the development of the field on meshes. A principled framework to compute the exponential map on Riemannian surfaces discretised as meshes is straightest geodesics, which also allows to trace geodesics and parallel-transport vectors as a by-product. We provide a parallel GPU implementation and derive two different methods for differentiating through the straightest geodesics, one leveraging an extrinsic proxy function and one based upon a geodesic finite differences scheme. After proving our parallelisation performance and accuracy, we demonstrate how our differentiable exponential map can improve learning and optimisation pipelines on general geometries. In particular, to showcase the versatility of our method, we propose a new geodesic convolutional layer, a new flow matching method for learning on meshes, and a second-order optimiser that we apply to centroidal Voronoi tessellation. Our code, models, and pip-installable library (digeo) are available at: circle-group.github.io/research/DSG.
Authors: Ce Zhang, Jinxi He, Junyi He, Katia Sycara, Yaqi Xie
Abstract: Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on jailbreak defenses that detect and refuse explicitly unsafe inputs, such approaches often overlook contextual safety, which requires models to distinguish subtle contextual differences between scenarios that may appear similar but diverge significantly in safety intent. In this work, we present MM-SafetyBench++, a carefully curated benchmark designed for contextual safety evaluation. Specifically, for each unsafe image-text pair, we construct a corresponding safe counterpart through minimal modifications that flip the user intent while preserving the underlying contextual meaning, enabling controlled evaluation of whether models can adapt their safety behaviors based on contextual understanding. Further, we introduce EchoSafe, a training-free framework that maintains a self-reflective memory bank to accumulate and retrieve safety insights from prior interactions. By integrating relevant past experiences into current prompts, EchoSafe enables context-aware reasoning and continual evolution of safety behavior during inference. Extensive experiments on various multi-modal safety benchmarks demonstrate that EchoSafe consistently achieves superior performance, establishing a strong baseline for advancing contextual safety in MLLMs. All benchmark data and code are available at https://echosafe-mllm.github.io.
Authors: Malte Prinzler, Paulo Gotardo, Siyu Tang, Timo Bolkart
Abstract: We present MATCH (Multi-view Avatars from Topologically Corresponding Heads), a multi-view Gaussian registration method for high-quality head avatar creation and editing. State-of-the-art multi-view head avatar methods require time-consuming head tracking followed by expensive avatar optimization, often resulting in a total creation time of more than one day. MATCH, in contrast, directly predicts Gaussian splat textures in correspondence from calibrated multi-view images in just 0.5 seconds per frame, without requiring data preprocessing. The learned intra-subject correspondence across frames enables fast creation of personalized head avatars, while correspondence across subjects supports applications such as expression transfer, optimization-free tracking, semantic editing, and identity interpolation. We establish these correspondences end-to-end using a transformer-based model that predicts Gaussian splat textures in the fixed UV layout of a template mesh. To achieve this, we introduce a novel registration-guided attention block, where each UV-map token attends exclusively to image tokens depicting its corresponding mesh region. This design improves efficiency and performance compared to dense cross-view attention. MATCH outperforms existing methods in novel-view synthesis, geometry registration, and head avatar generation, while making avatar creation 10 times faster than the closest competing baseline. The code and model weights are available on the project website.
Authors: Aditya Iyer, Jack Roberts, Nora Ayanian
Abstract: Multi-View Multi-Object Tracking (MV-MOT) aims to localize and maintain consistent identities of objects observed by multiple sensors. This task is challenging, as viewpoint changes and occlusion disrupt identity consistency across views and time. Recent end-to-end approaches address this by jointly learning 2D Bird's Eye View (BEV) representations and identity associations, achieving high tracking accuracy. However, these methods offer no principled uncertainty accounting and remain tightly coupled to their training configuration, limiting generalization across sensor layouts, modalities, or datasets without retraining. We propose ModTrack, a modular MV-MOT system that matches end-to-end performance while providing cross-modal, sensor-agnostic generalization and traceable uncertainty. ModTrack confines learning methods to just the \textit{Detection and Feature Extraction} stage of the MV-MOT pipeline, performing all fusion, association, and tracking with closed-form analytical methods. Our design reduces each sensor's output to calibrated position-covariance pairs $(\mathbf{z}, R)$; cross-view clustering and precision-weighted fusion then yield unified estimates $(\hat{\mathbf{z}}, \hat{R})$ for identity assignment and temporal tracking. A feedback-coupled, identity-informed Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter with HMM motion modes uses these fused estimates to maintain identities under missed detections and heavy occlusion. ModTrack achieves 95.5 IDF1 and 91.4 MOTA on \textit{WildTrack}, surpassing all prior modular methods by over 21 points and rivaling the state-of-the-art end-to-end methods while providing deployment flexibility they cannot. Specifically, the same tracker core transfers unchanged to \textit{MultiviewX} and \textit{RadarScenes}, with only perception-module replacement required to extend to new domains and sensor modalities.
Authors: Salah Eddine Bekhouche, Hichem Telli, Azeddine Benlamoudi, Salah Eddine Herrouz, Abdelmalik Taleb-Ahmed, Abdenour Hadid
Abstract: Ambivalence and hesitancy (A/H) are subtle affective states where a person shows conflicting signals through different channels -- saying one thing while their face or voice tells another story. Recognising these states automatically is valuable in clinical settings, but it is hard for machines because the key evidence lives in the \emph{disagreements} between what is said, how it sounds, and what the face shows. We present \textbf{ConflictAwareAH}, a multimodal framework built for this problem. Three pre-trained encoders extract video, audio, and text representations. Pairwise conflict features -- element-wise absolute differences between modality embeddings -- serve as \emph{bidirectional} cues: large cross-modal differences flag A/H, while small differences confirm behavioural consistency and anchor the negative class. This conflict-aware design addresses a key limitation of text-dominant approaches, which tend to over-detect A/H (high F1-AH) while struggling to confirm its absence: our multimodal model improves F1-NoAH by +4.6 points over text alone and halves the class-performance gap. A complementary \emph{text-guided late fusion} strategy blends a text-only auxiliary head with the full model at inference, adding +4.1 Macro F1. On the BAH dataset from the ABAW10 Ambivalence/Hesitancy Challenge, our method reaches \textbf{0.694 Macro F1} on the labelled test split and \textbf{0.715} on the private leaderboard, outperforming published multimodal baselines by over 10 points -- all on a single GPU in under 25 minutes of training.
Authors: Renjie Liang, Yiling Ma, Yang Xing, Zhengkang Fan, Jinqian Pan, Chengkun Sun, Li Li, Kuang Gong, Jie Xu
Abstract: Automated radiology report generation from 3D CT volumes often suffers from incomplete pathology coverage. We provide empirical evidence that this limitation stems from a representational bottleneck: contrastive 3D CT embeddings encode discriminative pathology signals, yet exhibit severe dimensional concentration, with as few as 2 effective dimensions out of 512. Corroborating this, scaling the language model yields no measurable improvement, suggesting that the bottleneck lies in the visual representation rather than the generator. This bottleneck limits both generation and retrieval; naive static retrieval fails to improve clinical efficacy and can even degrade performance. We propose \textbf{AdaRAG-CT}, an adaptive augmentation framework that compensates for this visual bottleneck by introducing supplementary textual information through controlled retrieval and selectively integrating it during generation. On the CT-RATE benchmark, AdaRAG-CT achieves state-of-the-art clinical efficacy, improving Clinical F1 from 0.420 (CT-Agent) to 0.480 (+6 points); ablation studies confirm that both the retrieval and generation components contribute to the improvement. Code is available at https://github.com/renjie-liang/Adaptive-RAG-for-3DCT-Report-Generation.
URLs: https://github.com/renjie-liang/Adaptive-RAG-for-3DCT-Report-Generation.
Authors: Eadom Dessalene, Botao He, Michael Maynord, Yonatan Tussa, Pavan Mantripragada, Yianni Karabati, Nirupam Roy, Yiannis Aloimonos
Abstract: We introduce FEEL (Force-Enhanced Egocentric Learning), the first large-scale dataset pairing force measurements gathered from custom piezoresistive gloves with egocentric video. Our gloves enable scalable data collection, and FEEL contains approximately 3 million force-synchronized frames of natural unscripted manipulation in kitchen environments, with 45% of frames involving hand-object contact. Because force is the underlying cause that drives physical interaction, it is a critical primitive for physical action understanding. We demonstrate the utility of force for physical action understanding through application of FEEL to two families of tasks: (1) contact understanding, where we jointly perform temporal contact segmentation and pixel-level contacted object segmentation; and, (2) action representation learning, where force prediction serves as a self-supervised pretraining objective for video backbones. We achieve state-of-the-art temporal contact segmentation results and competitive pixel-level segmentation results without any need for manual contacted object segmentation annotations. Furthermore we demonstrate that action representation learning with FEEL improves transfer performance on action understanding tasks without any manual labels over EPIC-Kitchens, SomethingSomething-V2, EgoExo4D and Meccano.
Authors: Jakaria Rabbi, Nilanjan Ray, Dana Cobzas
Abstract: Disentangling pathological changes from physiological aging in 3D medical shapes is crucial for developing interpretable biomarkers and patient stratification. However, this separation is challenging when diagnosis labels are limited or unavailable, since disease and aging often produce overlapping effects on shape changes, obscuring clinically relevant shape patterns. To address this challenge, we propose a two-stage framework combining unsupervised disease discovery with self-supervised disentanglement of implicit shape representations. In the first stage, we train an implicit neural model with signed distance functions to learn stable shape embeddings. We then apply clustering on the shape latent space, which yields pseudo disease labels without using ground-truth diagnosis during discovery. In the second stage, we disentangle factors in a compact variational space using pseudo disease labels discovered in the first stage and the ground truth age labels available for all subjects. We enforce separation and controllability with a multi-objective disentanglement loss combining covariance and a supervised contrastive loss. On ADNI hippocampus and OAI distal femur shapes, we achieve near-supervised performance, improving disentanglement and reconstruction over state-of-the-art unsupervised baselines, while enabling high-fidelity reconstruction, controllable synthesis, and factor-based explainability. Code and checkpoints are available at https://github.com/anonymous-submission01/medical-shape-disentanglement
URLs: https://github.com/anonymous-submission01/medical-shape-disentanglement
Authors: Ruchika Gupta, Illya Bakurov, Nathan Haut, Wolfgang Banzhaf
Abstract: Traditional Image Quality Assessment (IQA) metrics typically fall into one of two extremes: rigid, hand-crafted mathematical models or "black-box" deep learning architectures that completely lack interpretability. To bridge this gap, we propose EvoIQA, a fully explainable symbolic regression framework based on Genetic Programming that Evolves explicit, human-readable mathematical formulas for image quality assessment (IQA). Utilizing a rich terminal set from the VSI, VIF, FSIM, and HaarPSI metrics, our framework inherently maps structural, chromatic, and information-theoretic degradations into observable mathematical equations. Our results demonstrate that the evolved GP models consistently achieve strong alignment between the predictions and human visual preferences. Furthermore, they not only outperform traditional hand-crafted metrics but also achieve performance parity with complex, state-of-the-art deep learning models like DB-CNN, proving that we no longer have to sacrifice interpretability for state-of-the-art performance.
Authors: Siyu Zhang
Abstract: Sparse neural networks are often hypothesized to be more interpretable than dense models, motivated by findings that weight sparsity can produce compact circuits in language models. However, it remains unclear whether structural sparsity itself leads to improved semantic interpretability. In this work, we systematically evaluate the relationship between weight sparsity and interpretability in Vision Transformers using DeiT-III B/16 models pruned with Wanda. To assess interpretability comprehensively, we introduce \textbf{IMPACT}, a multi-level framework that evaluates interpretability across four complementary levels: neurons, layer representations, task circuits, and model-level attribution. Layer representations are analyzed using BatchTopK sparse autoencoders, circuits are extracted via learnable node masking, and explanations are evaluated with transformer attribution using insertion and deletion metrics. Our results reveal a clear structural effect but limited interpretability gains. Sparse models produce circuits with approximately $2.5\times$ fewer edges than dense models, yet the fraction of active nodes remains similar or higher, indicating that pruning redistributes computation rather than isolating simpler functional modules. Consistent with this observation, sparse models show no systematic improvements in neuron-level selectivity, SAE feature interpretability, or attribution faithfulness. These findings suggest that structural sparsity alone does not reliably yield more interpretable vision models, highlighting the importance of evaluation frameworks that assess interpretability beyond circuit compactness.
Authors: James Song, Yifan Wang, Chuan Zhou, Liyue Shen
Abstract: Early diagnosis of lung cancer is challenging due to biological uncertainty and the limited understanding of the biological mechanisms driving nodule progression. To address this, we propose Nodule-Aligned Multimodal (Latent) Diffusion (NAMD), a novel framework that predicts lung nodule progression by generating 1-year follow-up nodule computed tomography images with baseline scans and the patient's and nodule's Electronic Health Record (EHR). NAMD introduces a nodule-aligned latent space, where distances between latents directly correspond to changes in nodule attributes, and utilizes an LLM-driven control mechanism to condition the diffusion backbone on patient data. On the National Lung Screening Trial (NLST) dataset, our method synthesizes follow-up nodule images that achieve an AUROC of 0.805 and an AUPRC of 0.346 for lung nodule malignancy prediction, significantly outperforming both baseline scans and state-of-the-art synthesis methods, while closely approaching the performance of real follow-up scans (AUROC: 0.819, AUPRC: 0.393). These results demonstrate that NAMD captures clinically relevant features of lung nodule progression, facilitating earlier and more accurate diagnosis.
Authors: Samuel Johnny, Blessed Guda, Frank Ebeledike, Goodness Obasi, Moise Busogi
Abstract: Automated diagnosis from chest computed tomography (CT) scans faces two persistent challenges in clinical deployment: distribution shift across acquisition sites and performance disparity across demographic subgroups. We address both simultaneously across two complementary tasks: binary COVID-19 classification from multi-site CT volumes (Task 1) and four-class lung pathology recognition with gender-based fairness constraints (Task 2). Our framework combines a lightweight MobileViT-XXS slice encoder with a two-layer SliceTransformer aggregator for volumetric reasoning, and trains with a KL-regularised Group Distributionally Robust Optimisation (Group DRO) objective that adaptively upweights underperforming acquisition centres and demographic subgroups. Unlike standard Group DRO, the KL penalty prevents group weight collapse, providing a stable balance between worst-case protection and average performance. For Task 2, we define groups at the granularity of gender class, directly targeting severely underrepresented combinations such as female Squamous cell carcinoma. On Task 1, our best configuration achieves a challenge F1 of 0.835, surpassing the best published challenge entry by +5.9. On Task 2, Group DRO with {\alpha} = 0.5 achieves a mean per-gender macro F1 of 0.815, outperforming the best challenge entry by +11.1 pp and improving Female Squamous F1 by +17.4 over the Fo- cal Loss baseline.
Authors: Harishwar Reddy Kasireddy, Patricio S. La Rosa, Akshita Gupta, Anindya S. Paul, Jamie L. Fermin, William L. Clapp, Meryl A. Waldman, Tarek M. El-Ashkar, Sanjay Jain, Luis Rodrigues, Kuang Yu Jen, Avi Z. Rosenberg, Michael T. Eadon, Jeffrey B. Hodgin, Pinaki Sarder
Abstract: Histopathology foundation models (HFMs), pretrained on large-scale cancer datasets, have advanced computational pathology. However, their applicability to non-cancerous chronic kidney disease remains underexplored, despite coexistence of renal pathology with malignancies such as renal cell and urothelial carcinoma. We systematically evaluate 11 publicly available HFMs across 11 kidney-specific downstream tasks spanning multiple stains (PAS, H&E, PASM, and IHC), spatial scales (tile and slide-level), task types (classification, regression, and copy detection), and clinical objectives, including detection, diagnosis, and prognosis. Tile-level performance is assessed using repeated stratified group cross-validation, while slide-level tasks are evaluated using repeated nested stratified cross-validation. Statistical significance is examined using Friedman test followed by pairwise Wilcoxon signed-rank testing with Holm-Bonferroni correction and compact letter display visualization. To promote reproducibility, we release an open-source Python package, kidney-hfm-eval, available at https://pypi.org/project/kidney-hfm-eval/ , that reproduces the evaluation pipelines. Results show moderate to strong performance on tasks driven by coarse meso-scale renal morphology, including diagnostic classification and detection of prominent structural alterations. In contrast, performance consistently declines for tasks requiring fine-grained microstructural discrimination, complex biological phenotypes, or slide-level prognostic inference, largely independent of stain type. Overall, current HFMs appear to encode predominantly static meso-scale representations and may have limited capacity to capture subtle renal pathology or prognosis-related signals. Our results highlight the need for kidney-specific, multi-stain, and multimodal foundation models to support clinically reliable decision-making in nephrology.
Authors: Xiaoyan Cong, Zekun Li, Zhiyang Dou, Hongyu Li, Omid Taheri, Chuan Guo, Abhay Mittal, Sizhe An, Taku Komura, Wojciech Matusik, Michael J. Black, Srinath Sridhar
Abstract: Large-scale foundation models (LFMs) have recently made impressive progress in text-to-motion generation by learning strong generative priors from massive 3D human motion datasets and paired text descriptions. However, how to effectively and efficiently leverage such single-purpose motion LFMs, i.e., text-to-motion synthesis, in more diverse cross-modal and in-context motion generation downstream tasks remains largely unclear. Prior work typically adapts pretrained generative priors to individual downstream tasks in a task-specific manner. In contrast, our goal is to unlock such priors to support a broad spectrum of downstream motion generation tasks within a single unified framework. To bridge this gap, we present UMO, a simple yet general unified formulation that casts diverse downstream tasks into compositions of atomic per-frame operations, enabling in-context adaptation to unlock the generative priors of pretrained DiT-based motion LFMs. Specifically, UMO introduces three learnable frame-level meta-operation embeddings to specify per-frame intent and employs lightweight temporal fusion to inject in-context cues into the pretrained backbone, with negligible runtime overhead compared to the base model. With this design, UMO finetunes the pretrained model, originally limited to text-to-motion generation, to support diverse previously unsupported tasks, including temporal inpainting, text-guided motion editing, text-serialized geometric constraints, and multi-identity reaction generation. Experiments demonstrate that UMO consistently outperforms task-specific and training-free baselines across a wide range of benchmarks, despite using a single unified model. Code and model will be publicly available. Project Page: https://oliver-cong02.github.io/UMO.github.io/
Authors: Sijie Li, Biao Qian, Jungong Han
Abstract: Network pruning is an effective technique for enabling lightweight Large Vision-Language Models (LVLMs), which primarily incorporates both weights and activations into the importance metric. However, existing efforts typically process calibration data from different modalities in a unified manner, overlooking modality-specific behaviors. This raises a critical challenge: how to address the divergent behaviors of textual and visual tokens for accurate pruning of LVLMs. To this end, we systematically investigate the sensitivity of visual and textual tokens to the pruning operation by decoupling their corresponding weights, revealing that: (i) the textual pathway should be calibrated via text tokens, since it exhibits higher sensitivity than the visual pathway; (ii) the visual pathway exhibits high redundancy, permitting even 50% sparsity. Motivated by these insights, we propose a simple yet effective Asymmetric Text-Visual Weight Pruning method for LVLMs, dubbed ATV-Pruning, which establishes the importance metric for accurate weight pruning by selecting the informative tokens from both textual and visual pathways. Specifically, ATV-Pruning integrates two primary innovations: first, a calibration pool is adaptively constructed by drawing on all textual tokens and a subset of visual tokens; second, we devise a layer-adaptive selection strategy to yield important visual tokens. Finally, extensive experiments across standard multimodal benchmarks verify the superiority of our ATV-Pruning over state-of-the-art methods.
Authors: Subhransu S. Bhattacharjee, Dylan Campbell, Rahul Shome
Abstract: A single egocentric image typically captures only a small portion of the floor, yet a complete metric traversability map of the surroundings would better serve applications such as indoor navigation. We introduce FlatLands, a dataset and benchmark for single-view bird's-eye view (BEV) floor completion. The dataset contains 270,575 observations from 17,656 real metric indoor scenes drawn from six existing datasets, with aligned observation, visibility, validity, and ground-truth BEV maps, and the benchmark includes both in- and out-of-distribution evaluation protocols. We compare training-free approaches, deterministic models, ensembles, and stochastic generative models. Finally, we instantiate the task as an end-to-end monocular RGB-to-floormaps pipeline. FlatLands provides a rigorous testbed for uncertainty-aware indoor mapping and generative completion for embodied navigation.
Authors: Jecia Z. Y. Mao, Francis X. Creighton, Russell H. Taylor, Manish Sahu
Abstract: We introduce a speech-guided embodied agent framework for video-guided skull base surgery that dynamically executes perception and image-guidance tasks in response to surgeon queries. The proposed system integrates natural language interaction with real-time visual perception directly on live intraoperative video streams, thereby enabling surgeons to request computational assistance without disengaging from operative tasks. Unlike conventional image-guided navigation systems that rely on external optical trackers and additional hardware setup, the framework operates purely on intraoperative video. The system begins with interactive segmentation and labeling of the surgical instrument. The segmented instrument is then used as a spatial anchor that is autonomously tracked in the video stream to support downstream workflows, including anatomical segmentation, interactive registration of preoperative 3D models, monocular video-based estimation of the surgical tool pose, and support image guidance through real-time anatomical overlays.We evaluate the proposed system in video-guided skull base surgery scenarios and benchmark its tracking performance against a commercially available optical tracking system. Results demonstrate that speech-guided embodied agents can achieve competitive spatial accuracy while improving workflow integration and enabling rapid deployment of video-guided surgical systems.
Authors: Yifan Li, Seunghyun Yoon, Viet Dac Lai, Franck Dernoncourt, Jason Kuen, Yu Kong, Trung Bui
Abstract: Vision Transformers (ViTs) based vision foundation models (VFMs) have achieved remarkable performance across diverse vision tasks, but suffer from quadratic complexity that limits scalability to long sequences. Existing linear attention approaches for ViTs are typically trained from scratch, requiring substantial computational resources, while linearization-based methods developed for large language model decoders do not transfer well to ViTs. To address these challenges, we propose ViT-AdaLA, a novel framework for effectively adapting and transferring prior knowledge from VFMs to linear attention ViTs. ViT-AdaLA consists of three stages: attention alignment, feature alignment, and supervised fine-tuning. In the attention alignment stage, we align vanilla linear attention with the original softmax-based attention in each block to approximate the behavior of softmax attention. However, residual approximation errors inevitably accumulate across layers. We mitigate this by fine-tuning the linearized ViT to align its final-layer features with a frozen softmax VFM teacher. Finally, the adapted prior knowledge is transferred to downstream tasks through supervised fine-tuning. Extensive experiments on classification and segmentation tasks demonstrate the effectiveness and generality of ViT-AdaLA over various state-of-the-art linear attention counterpart.
Authors: Vincenzo Buono, Peyman Sheikholharam Mashhadi, Mahmoud Rahat, Prayag Tiwari, Stefan Byttner
Abstract: Attribution methods in explainable AI rely on upsampling techniques that were designed for natural images, not saliency maps. Standard bilinear and bicubic interpolation systematically corrupts attribution signals through aliasing, ringing, and boundary bleeding, producing spurious high-importance regions that misrepresent model reasoning. We identify that the core issue is treating attribution upsampling as an interpolation problem that operates in isolation from the model's reasoning, rather than a mass redistribution problem where model-derived semantic boundaries must govern how importance flows. We present Universal Semantic-Aware Upsampling (USU), a principled method that reformulates upsampling through ratio-form mass redistribution operators, provably preserving attribution mass and relative importance ordering. Extending the axiomatic tradition of feature attribution to upsampling, we formalize four desiderata for faithful upsampling and prove that interpolation structurally violates three of them. These same three force any redistribution operator into a ratio form; the fourth selects the unique potential within this family, yielding USU. Controlled experiments on models with known attribution priors verify USU's formal guarantees; evaluation across ImageNet, CIFAR-10, and CUB-200 confirms consistent faithfulness improvements and qualitatively superior, semantically coherent explanations.
Authors: Athena Taymourtash, S. Mazdak Abulnaga, Esra Abaci Turk, P. Ellen Grant, Polina Golland
Abstract: Establishing dense volumetric correspondences across anatomical shapes is essential for group-level analysis but remains challenging for implicit neural representations. Most existing implicit registration methods rely on supervision near the zero-level set and thus capture only surface correspondences, leaving interior deformations under-constrained. We introduce a volumetrically consistent implicit model that couples reconstruction of signed distance functions (SDFs) with neural diffeomorphic flow to learn a shared canonical template of the placenta. Volumetric regularization, including Jacobian-determinant and biharmonic penalties, suppresses local folding and promotes globally coherent deformations. In the motivating application to placenta MRI, our formulation jointly reconstructs individual placentas, aligns them to a population-derived implicit template, and enables voxel-wise intensity mapping in a unified canonical space. Experiments on in-vivo placenta MRI scans demonstrate improved geometric fidelity and volumetric alignment over surface-based implicit baseline methods, yielding anatomically interpretable and topologically consistent flattening suitable for group analysis.
Authors: Jiahe Fan, Xiao Ma, Sergey Vityazev, George Giakos, Shaolong Shu, Rui Fan
Abstract: Driving scene parsing is critical for autonomous vehicles to operate reliably in complex real-world traffic environments. To reduce the reliance on costly pixel-level annotations, synthetic datasets with automatically generated labels have become a popular alternative. However, models trained on synthetic data often perform poorly when applied to real-world scenes due to the synthetic-to-real domain gap. Despite the success of unsupervised domain adaptation in narrowing this gap, most existing methods mainly focus on global feature alignment while overlooking the semantic structure of the feature space. As a result, semantic relations among classes are insufficiently modeled, limiting the model's ability to generalize. To address these challenges, this study introduces a novel unsupervised domain adaptation framework that explicitly regularizes semantic feature structures to significantly enhance driving scene parsing performance in real-world scenarios. Specifically, the proposed method enforces inter-class separation and intra-class compactness by leveraging class-specific prototypes, thereby enhancing the discriminability and structural coherence of feature clusters. An entropy-based noise filtering strategy improves the reliability of pseudo labels, while a pixel-level attention mechanism further refines feature alignment. Extensive experiments on representative benchmarks demonstrate that the proposed method consistently outperforms recent state-of-the-art methods. These results underscore the importance of preserving semantic structure for robust synthetic-to-real adaptation in driving scene parsing tasks.
Authors: Hui Shan, Keyang Luo, Ming Li, Sizhe Zheng, Yanwei Fu, Zhen Chen, Xiangru Huang
Abstract: Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets. However, generating 3D compositional objects from single images--particularly under occlusions--remains challenging. Existing methods often degrade geometric details in hidden regions and fail to preserve the underlying object-object spatial relationships (OOR). We present a novel framework Interact3D designed to generate physically plausible interacting 3D compositional objects. Our approach first leverages advanced generative priors to curate high-quality individual assets with a unified 3D guidance scene. To physically compose these assets, we then introduce a robust two-stage composition pipeline. Based on the 3D guidance scene, the primary object is anchored through precise global-to-local geometric alignment (registration), while subsequent geometries are integrated using a differentiable Signed Distance Field (SDF)-based optimization that explicitly penalizes geometry intersections. To reduce challenging collisions, we further deploy a closed-loop, agentic refinement strategy. A Vision-Language Model (VLM) autonomously analyzes multi-view renderings of the composed scene, formulates targeted corrective prompts, and guides an image editing module to iteratively self-correct the generation pipeline. Extensive experiments demonstrate that Interact3D successfully produces promising collsion-aware compositions with improved geometric fidelity and consistent spatial relationships.
Authors: Shin'ya Yamaguchi, Daiki Chijiwa, Tamao Sakao, Taku Hasegawa
Abstract: Large vision-language models (LVLMs) employ multi-modal in-context learning (MM-ICL) to adapt to new tasks by leveraging demonstration examples. While increasing the number of demonstrations boosts performance, they incur significant inference latency due to the quadratic computational cost of Transformer attention with respect to the context length. To address this trade-off, we propose Parallel In-Context Learning (Parallel-ICL), a plug-and-play inference algorithm. Parallel-ICL partitions the long demonstration context into multiple shorter, manageable chunks. It processes these chunks in parallel and integrates their predictions at the logit level, using a weighted Product-of-Experts (PoE) ensemble to approximate the full-context output. Guided by ensemble learning theory, we introduce principled strategies for Parallel-ICL: (i) clustering-based context chunking to maximize inter-chunk diversity and (ii) similarity-based context compilation to weight predictions by query relevance. Extensive experiments on VQA, image captioning, and classification benchmarks demonstrate that Parallel-ICL achieves performance comparable to full-context MM-ICL, while significantly improving inference speed. Our work offers an effective solution to the accuracy-efficiency trade-off in MM-ICL, enabling dynamic task adaptation with substantially reduced inference overhead.
Authors: Elad Hirsch, Shubham Yadav, Mohit Garg, Purvanshi Mehta
Abstract: We introduce LICA (Layered Image Composition Annotations), a large-scale dataset of 1,550,244 multi-layer graphic design compositions designed to advance structured understanding and generation of graphic layouts1. In addition to ren- dered PNG images, LICA represents each design as a hierarchical composition of typed components including text, image, vector, and group elements, each paired with rich per-element metadata such as spatial geometry, typographic attributes, opacity, and visibility. The dataset spans 20 design categories and 971,850 unique templates, providing broad coverage of real-world design structures. We further introduce graphic design video as a new and largely unexplored challenge for current vision-language models through 27,261 animated layouts annotated with per-component keyframes and motion parameters. Beyond scale, LICA establishes a new paradigm of research tasks for graphic design, enabling structured investiga- tions into problems such as layer-aware inpainting, structured layout generation, controlled design editing, and temporally-aware generative modeling. By repre- senting design as a system of compositional layers and relationships, the dataset supports research on models that operate directly on design structure rather than pixels alone.
Authors: Sensen Gao, Zhaoqing Wang, Qihang Cao, Dongdong Yu, Changhu Wang, Tongliang Liu, Mingming Gong, Jiawang Bian
Abstract: Existing diffusion-based 3D scene generation methods primarily operate in 2D image/video latent spaces, which makes maintaining cross-view appearance and geometric consistency inherently challenging. To bridge this gap, we present OneWorld, a framework that performs diffusion directly within a coherent 3D representation space. Central to our approach is the 3D Unified Representation Autoencoder (3D-URAE); it leverages pretrained 3D foundation models and augments their geometry-centric nature by injecting appearance and distilling semantics into a unified 3D latent space. Furthermore, we introduce token-level Cross-View-Correspondence (CVC) consistency loss to explicitly enforce structural alignment across views, and propose Manifold-Drift Forcing (MDF) to mitigate train-inference exposure bias and shape a robust 3D manifold by mixing drifted and original representations. Comprehensive experiments demonstrate that OneWorld generates high-quality 3D scenes with superior cross-view consistency compared to state-of-the-art 2D-based methods. Our code will be available at https://github.com/SensenGao/OneWorld.
Authors: Jonas Herzog, Yue Wang
Abstract: Recent research suggested that the embeddings produced by CLIP-like contrastive language-image training are suboptimal for image-only tasks. The main theory is that the inter-modal (language-image) alignment loss ignores intra-modal (image-image) alignment, leading to poorly calibrated distances between images. In this study, we question this intra-modal misalignment hypothesis. We reexamine its foundational theoretical argument, the indicators used to support it, and the performance metrics affected. For the theoretical argument, we demonstrate that there are no such supposed degrees of freedom for image embedding distances. For the empirical measures, our findings reveal they yield similar results for language-image trained models (CLIP, SigLIP) and image-image trained models (DINO, SigLIP2). This indicates the observed phenomena do not stem from a misalignment specific to the former. Experiments on the commonly studied intra-modal tasks retrieval and few-shot classification confirm that addressing task ambiguity, not supposed misalignment, is key for best results.
Authors: Butian Xiong, Rong Liu, Tiantian Zhou, Meida Chen, Zhiwen Fan, Andrew Feng
Abstract: 3D Gaussian Splat (3DGS) enables high-fidelity, real-time novel view synthesis by representing scenes with large sets of anisotropic primitives, but often requires millions of Splats, incurring significant storage and transmission costs. Most existing compression methods rely on GPU-intensive post-training optimization with calibrated images, limiting practical deployment. We introduce NanoGS, a training-free and lightweight framework for Gaussian Splat simplification. Instead of relying on image-based rendering supervision, NanoGS formulates simplification as local pairwise merging over a sparse spatial graph. The method approximates a pair of Gaussians with a single primitive using mass preserved moment matching and evaluates merge quality through a principled merge cost between the original mixture and its approximation. By restricting merge candidates to local neighborhoods and selecting compatible pairs efficiently, NanoGS produces compact Gaussian representations while preserving scene structure and appearance. NanoGS operates directly on existing Gaussian Splat models, runs efficiently on CPU, and preserves the standard 3DGS parameterization, enabling seamless integration with existing rendering pipelines. Experiments demonstrate that NanoGS substantially reduces primitive count while maintaining high rendering fidelity, providing an efficient and practical solution for Gaussian Splat simplification. Our project website is available at https://saliteta.github.io/NanoGS/.
Authors: Minbing Chen, Zhu Meng, Fei Su
Abstract: Vision-Language Models (VLMs) offer significant potential in computational pathology by enabling interpretable image analysis, automated reporting, and scalable decision support. However, their widespread clinical adoption remains limited due to the absence of reliable, automated evaluation metrics capable of identifying subtle failures such as hallucinations. To address this gap, we propose PathGLS, a novel reference-free evaluation framework that assesses pathology VLMs across three dimensions: Grounding (fine-grained visual-text alignment), Logic (entailment graph consistency using Natural Language Inference), and Stability (output variance under adversarial visual-semantic perturbations). PathGLS supports both patch-level and whole-slide image (WSI)-level analysis, yielding a comprehensive trust score. Experiments on Quilt-1M, TCGA, REG2025, PathMMU and TCGA-Sarcoma datasets demonstrate the superiority of PathGLS. Specifically, on the Quilt-1M dataset, PathGLS reveals a steep sensitivity drop of 40.2% for hallucinated reports compared to only 2.1% for BERTScore. Moreover, validation against expert-defined clinical error hierarchies reveals that PathGLS achieves a strong Spearman's rank correlation of $\rho=0.71$ ($p < 0.0001$), significantly outperforming Large Language Model (LLM)-based approaches (Gemini 3.0 Pro: $\rho=0.39$, $p < 0.0001$). These results establish PathGLS as a robust reference-free metric. By directly quantifying hallucination rates and domain shift robustness, it serves as a reliable criterion for benchmarking VLMs on private clinical datasets and informing safe deployment. Code can be found at: https://github.com/My13ad/PathGLS
Authors: Sadia Ilyas, Annika M\"utze, Klaus Friedrichs, Thomas Kurbiel, Matthias Rottmann
Abstract: Out-of-distribution (OOD) object detection is an important yet underexplored task. A reliable object detector should be able to handle OOD objects by localizing and correctly classifying them as OOD. However, a critical issue arises when such atypical objects are completely missed by the object detector and incorrectly treated as background. Existing OOD detection approaches in object detection often rely on complex architectures or auxiliary branches and typically do not provide a framework that treats in-distribution (ID) and OOD in a unified way. In this work, we address these limitations by enabling a single detector to detect OOD objects, that are otherwise silently overlooked, alongside ID objects. We present \textbf{SynOE-OD}, a \textbf{Syn}thetic \textbf{O}utlier-\textbf{E}xposure-based \textbf{O}bject \textbf{D}etection framework, that leverages strong generative models, like Stable Diffusion, and Open-Vocabulary Object Detectors (OVODs) to generate semantically meaningful, object-level data that serve as outliers during training. The generated data is used for transfer-learning to establish strong ID task performance and supplement detection models with OOD object detection robustness. Our approach achieves state-of-the-art average precision on an established OOD object detection benchmark, where OVODs, such as GroundingDINO, show limited zero-shot performance in detecting OOD objects in street-scenes.
Authors: Da Zhang, Bingyu Li, Feiyu Wang, Zhiyuan Zhao, Junyu Gao
Abstract: Zero-shot object counting (ZSOC) aims to enumerate objects of arbitrary categories specified by text descriptions without requiring visual exemplars. However, existing methods often treat counting as a coarse retrieval task, suffering from a lack of fine-grained quantity awareness. Furthermore, they frequently exhibit spatial insensitivity and degraded generalization due to feature space distortion during model adaptation.To address these challenges, we present \textbf{QICA}, a novel framework that synergizes \underline{q}uantity percept\underline{i}on with robust spatial \underline{c}ast \underline{a}ggregation. Specifically, we introduce a Synergistic Prompting Strategy (\textbf{SPS}) that adapts vision and language encoders through numerically conditioned prompts, bridging the gap between semantic recognition and quantitative reasoning. To mitigate feature distortion, we propose a Cost Aggregation Decoder (\textbf{CAD}) that operates directly on vision-text similarity maps. By refining these maps through spatial aggregation, CAD prevents overfitting while preserving zero-shot transferability. Additionally, a multi-level quantity alignment loss ($\mathcal{L}_{MQA}$) is employed to enforce numerical consistency across the entire pipeline. Extensive experiments on FSC-147 demonstrate competitive performance, while zero-shot evaluation on CARPK and ShanghaiTech-A validates superior generalization to unseen domains.
Authors: Zhiwei Wang, Yayu Zheng, Defeng He, Li Zhao, Xiaoqin Zhang, Yuxing Li, Edmund Y. Lam
Abstract: Overexposure frequently occurs in practical scenarios, causing the loss of critical visual information. However, existing infrared and visible fusion methods still exhibit unsatisfactory performance in highly bright regions. To address this, we propose EPOFusion, an exposure-aware fusion model. Specifically, a guidance module is introduced to facilitate the encoder in extracting fine-grained infrared features from overexposed regions. Meanwhile, an iterative decoder incorporating a multiscale context fusion module is designed to progressively enhance the fused image, ensuring consistent details and superior visual quality. Finally, an adaptive loss function dynamically constrains the fusion process, enabling an effective balance between the modalities under varying exposure conditions. To achieve better exposure awareness, we construct the first infrared and visible overexposure dataset (IVOE) with high quality infrared guided annotations for overexposed regions. Extensive experiments show that EPOFusion outperforms existing methods. It maintains infrared cues in overexposed regions while achieving visually faithful fusion in non-overexposed areas, thereby enhancing both visual fidelity and downstream task performance. Code, fusion results and IVOE dataset will be made available at https://github.com/warren-wzw/EPOFusion.git.
Authors: Xiaoxu Meng, Zhongmin Chen, Bo Yang, Weikai Chen, Weixiao Liu, Lin Gao
Abstract: Neural reconstructions often trade structure for fidelity, yielding dense and unstructured meshes with irregular topology and weak part boundaries that hinder editing, animation, and downstream asset reuse. We present DualPrim, a compact and structured 3D reconstruction framework. Unlike additive-only implicit or primitive methods, DualPrim represents shapes with positive and negative superquadrics: the former builds the bases while the latter carves local volumes through a differentiable operator, enabling topology-aware modeling of holes and concavities. This additive-subtractive design increases the representational power without sacrificing compactness or differentiability. We embed DualPrim in a volumetric differentiable renderer, enabling end-to-end learning from multi-view images and seamless mesh export via closed-form boolean difference. Empirically, DualPrim delivers state-of-the-art accuracy and produces compact, structured, and interpretable outputs that better satisfy downstream needs than additive-only alternatives.
Authors: Shesh Narayan Gupta, Nik Bear Brown
Abstract: Generative models are widely used to compensate for class imbalance in AI training pipelines, yet their failure modes under low-data conditions are poorly understood. This paper reports a controlled benchmark comparing three augmentation strategies applied to a fine-grained animal classification task: traditional transforms, FastGAN, and Stable Diffusion 1.5 fine-tuned with Low-Rank Adaptation (LoRA). Using the Oxford-IIIT Pet Dataset with eight artificially underrepresented breeds, we find that FastGAN augmentation does not merely underperform at very low training set sizes but actively increases classifier bias, with a statistically significant large effect across three random seeds (bias gap increase: +20.7%, Cohen's d = +5.03, p = 0.013). The effect size here is large enough to give confidence in the direction of the finding despite the small number of seeds. Feature embedding analysis using t-distributed Stochastic Neighbor Embedding reveals that FastGAN images for severe-minority breeds form tight isolated clusters outside the real image distribution, a pattern consistent with mode collapse. Stable Diffusion with Low-Rank Adaptation produced the best results overall, achieving the highest macro F1 (0.9125 plus or minus 0.0047) and a 13.1% reduction in the bias gap relative to the unaugmented baseline. The data suggest a sample-size boundary somewhere between 20 and 50 training images per class below which GAN augmentation becomes harmful in this setting, though further work across additional domains is needed to establish where that boundary sits more precisely. All experiments run on a consumer-grade GPU with 6 to 8 GB of memory, with no cloud compute required.
Authors: Peng Sun, Jun Xie, Tao Lin
Abstract: Unified Multimodal Models (UMMs) are often constrained by the pre-training of their $\textbf{visual generation components}$, which typically relies on inefficient paradigms and scarce, high-quality text-image paired data. In this paper, we systematically analyze pre-training recipes for $\textbf{UMM visual generation}$ and identify these two issues as the major bottlenecks. To address them, we propose $\textbf{Image-Only Training for UMMs (IOMM)}$, a data-efficient two-stage training framework. The first stage pre-trains the visual generative component $\textbf{exclusively}$ using abundant unlabeled image-only data, thereby removing the dependency on paired data $\textbf{for this costly phase}$. The second stage fine-tunes the model using a mixture of unlabeled images and a small curated set of text-image pairs, leading to improved instruction alignment and generative quality. Extensive experiments show that IOMM not only improves training efficiency but also achieves state-of-the-art (SOTA) performance. For example, our IOMM-B (3.6B) model was trained from scratch using only $\sim \textbf{1050}$ H800 GPU hours (with the vast majority, $\textbf{1000}$ hours, dedicated to the efficient $\textbf{image-only pre-training stage}$). It achieves $\textbf{0.89}$ on GenEval and $\textbf{0.55}$ on WISE--surpassing strong baselines such as BAGEL-7B (0.82 & 0.55) and BLIP3-o-4B (0.84 & 0.50). Code is available $\href{https://github.com/LINs-lab/IOMM}{https://github.com/LINs-lab/IOMM}$.
URLs: https://github.com/LINs-lab/IOMM, https://github.com/LINs-lab/IOMM
Authors: Yukun Zhao, Zichen Zhong, Yongshun Gong, Yilong Yin, Haoliang Sun
Abstract: Denoising generative models have recently become the dominant paradigm for dexterous grasp generation, owing to their ability to model complex grasp distributions from large-scale data. However, existing diffusion-based methods typically formulate generation as a stochastic differential equation (SDE), which often requires many sequential denoising steps and introduces trajectory instability that can lead to physically infeasible grasps. In this paper, we propose EFF-Grasp, a novel Flow-Matching-based framework for physics-aware dexterous grasp generation. Specifically, we reformulate grasp synthesis as a deterministic ordinary differential equation (ODE) process, which enables efficient and stable generation through smooth probability flows. To further enforce physical feasibility, we introduce a training-free physics-aware energy guidance strategy. Our method defines an energy-guided target distribution using adapted explicit physical energy functions that capture key grasp constraints, and estimates the corresponding guidance term via a local Monte Carlo approximation during inference. In this way, EFF-Grasp dynamically steers the generation trajectory toward physically feasible regions without requiring additional physics-based training or simulation feedback. Extensive experiments on five benchmark datasets show that EFF-Grasp achieves superior performance in grasp quality and physical feasibility, while requiring substantially fewer sampling steps than diffusion-based baselines.
Authors: Jiayi Tian, Jiaze Wang
Abstract: Understanding 4D point cloud videos is essential for enabling intelligent agents to perceive dynamic environments. However, temporal scale bias across varying frame rates and distributional uncertainty in irregular point clouds make it highly challenging to design a unified and robust 4D backbone. Existing CNN or Transformer based methods are constrained either by limited receptive fields or by quadratic computational complexity, while neglecting these implicit distortions. To address this problem, we propose a novel dual invariant framework, termed \textbf{Gaussian Aware Temporal Scaling (GATS)}, which explicitly resolves both distributional inconsistencies and temporal. The proposed \emph{Uncertainty Guided Gaussian Convolution (UGGC)} incorporates local Gaussian statistics and uncertainty aware gating into point convolution, thereby achieving robust neighborhood aggregation under density variation, noise, and occlusion. In parallel, the \emph{Temporal Scaling Attention (TSA)} introduces a learnable scaling factor to normalize temporal distances, ensuring frame partition invariance and consistent velocity estimation across different frame rates. These two modules are complementary: temporal scaling normalizes time intervals prior to Gaussian estimation, while Gaussian modeling enhances robustness to irregular distributions. Our experiments on mainstream benchmarks MSR-Action3D (\textbf{+6.62\%} accuracy), NTU RGBD (\textbf{+1.4\%} accuracy), and Synthia4D (\textbf{+1.8\%} mIoU) demonstrate significant performance gains, offering a more efficient and principled paradigm for invariant 4D point cloud video understanding with superior accuracy, robustness, and scalability compared to Transformer based counterparts.
Authors: Davie Chen
Abstract: The rapid advancement of generative AI has introduced a new class of tools capable of producing publication-quality scientific figures, graphical abstracts, and data visualizations. However, academic publishers have responded with inconsistent and often ambiguous policies regarding AI-generated imagery. This paper surveys the current stance of major journals and publishers -- including Nature, Science, Cell Press, Elsevier, and PLOS -- on the use of AI-generated figures. We identify key concerns raised by publishers, including reproducibility, authorship attribution, and potential for visual misinformation. Drawing on practical examples from tools such as SciDraw, an AI-powered platform designed specifically for scientific illustration, we propose a set of best-practice guidelines for researchers seeking to use AI figure-generation tools in a compliant and transparent manner. Our findings suggest that, with appropriate disclosure and quality control, AI-generated figures can meaningfully accelerate scientific communication without compromising integrity.
Authors: Junhyeok Lee, Han Jang, Heeseong Eum, Joon Jang, Kyu Sung Choi
Abstract: Multiplex immunofluorescence (mIF) enables simultaneous single-cell quantification of multiple biomarkers within intact tissue architecture, yet its high reagent cost, multi-round staining protocols, and need for specialized imaging platforms limit routine clinical adoption. Virtual staining can synthesize mIF channels from widely available brightfield immunohistochemistry (IHC), but current translators optimize pixel-level fidelity without explicitly constraining nuclear morphology. In pathology, this gap is clinically consequential: subtle distortions in nuclei count, shape, or spatial arrangement propagate directly to quantification endpoints such as the Ki67 proliferation index, where errors of a few percent can shift treatment-relevant risk categories. This work introduces a supervision-free, architecture-agnostic conditioning strategy that injects a continuous cell probability map from a pretrained nuclei segmentation foundation model as an explicit input prior, together with a variance-preserving regularization term that matches local intensity statistics to maintain cell-level heterogeneity in synthesized fluorescence channels. The soft prior retains gradient-level boundary information lost by binary thresholding, providing a richer conditioning signal without task-specific tuning. Controlled experiments across Pix2Pix with U-Net and ResNet generators, deterministic regression U-Net, and conditional diffusion on two independent datasets demonstrate consistent improvements in nuclei count fidelity and perceptual quality, as the sole modifications. Code will be made publicly available upon acceptance.
Authors: Suvajit Patra, Soumitra Samanta
Abstract: Continuous Sign Language Recognition (CSLR) is a crucial task for understanding the languages of deaf communities. Contemporary keypoint-based approaches typically rely on spatio-temporal encoding, where spatial interactions among keypoints are modeled using Graph Convolutional Networks or attention mechanisms, while temporal dynamics are captured using 1D convolutional networks. However, such designs often introduce a large number of parameters in both the encoder and the decoder. This paper introduces a unified spatio-temporal attention network that computes attention scores both spatially (across keypoints) and temporally (within local windows), and aggregates features to produce a local context-aware spatio-temporal representation. The proposed encoder contains approximately $70-80\%$ fewer parameters than existing state-of-the-art models while achieving comparable performance to keypoint-based methods on the Phoenix-14T dataset.
Authors: Yiming Wang
Abstract: Visible-infrared person re-identification faces greater challenges than traditional person re-identification due to the significant differences between modalities. In particular, the differences between these modalities make effective matching even more challenging, mainly because existing re-ranking algorithms cannot simultaneously address the intra-modal variations and inter-modal discrepancy in cross-modal person re-identification. To address this problem, we propose a novel Progressive Modal Relationship Re-ranking method consisting of two modules, called heterogeneous and homogeneous consistency re-ranking(HHCR). The first module, heterogeneous consistency re-ranking, explores the relationship between the query and the gallery modalities in the test set. The second module, homogeneous consistency reranking, investigates the intrinsic relationship within each modality between the query and the gallery in the test set. Based on this, we propose a baseline for cross-modal person re-identification, called a consistency re-ranking inference network (CRI). We conducted comprehensive experiments demonstrating that our proposed re-ranking method is generalized, and both the re-ranking and the baseline achieve state-of-the-art performance.
Authors: Huyen T. T. Tran, Van-Quang Nguyen, Farros Alferro, Kang-Jun Liu, Takayuki Okatani
Abstract: Multimodal Large Language Models (MLLMs) have shown impressive abilities in understanding and reasoning over conventional images. However, their perception of 360{\deg} images remains largely underexplored. Unlike conventional images, 360{\deg} images capture the entire surrounding environment, enabling holistic spatial reasoning but introducing challenges such as geometric distortion and complex spatial relations. To comprehensively assess MLLMs' capabilities to perceive 360{\deg} images, we introduce 360Bench, a Visual Question Answering (VQA) benchmark featuring 7K-resolution 360{\deg} images, seven representative (sub)tasks with annotations carefully curated by human annotators. Using 360Bench, we systematically evaluate seven MLLMs and six enhancement methods, revealing their shortcomings in 360{\deg} image perception. To address these challenges, we propose Free360, a training-free scene-graph-based framework for high-resolution 360{\deg} VQA. Free360 decomposes the reasoning process into modular steps, applies adaptive spherical image transformations to 360{\deg} images tailored to each step, and seamlessly integrates the resulting information into a unified graph representation for answer generation. Experiments show that Free360 consistently improves its base MLLM and provides a strong training-free solution for 360{\deg} VQA tasks. The source code and dataset will be publicly released upon acceptance.
Authors: Viraj Panchal, Tanmay Talsaniya, Parag Patel, Meet Patel
Abstract: We present KidsNanny, a two-stage multimodal content moderation architecture for child safety. Stage 1 combines a vision transformer (ViT) with an object detector for visual screening (11.7 ms); outputs are routed as text not raw pixels to Stage 2, which applies OCR and a text based 7B language model for contextual reasoning (120 ms total pipeline). We evaluate on the UnsafeBench Sexual category (1,054 images) under two regimes: vision-only, isolating Stage 1, and multimodal, evaluating the full Stage 1+2 pipeline. Stage 1 achieves 80.27% accuracy and 85.39% F1 at 11.7 ms; vision-only baselines range from 59.01% to 77.04% accuracy. The full pipeline achieves 81.40% accuracy and 86.16% F1 at 120 ms, compared to ShieldGemma-2 (64.80% accuracy, 1,136 ms) and LlavaGuard (80.36% accuracy, 4,138 ms). To evaluate text-awareness, we filter two subsets: a text+visual subset (257 images) and a text-only subset (44 images where safety depends primarily on embedded text). On text-only images, KidsNanny achieves 100% recall (25/25 positives; small sample) and 75.76% precision; ShieldGemma-2 achieves 84% recall and 60% precision at 1,136 ms. Results suggest that dedicated OCR-based reasoning may offer recall-precision advantages on text-embedded threats at lower latency, though the small text-only subset limits generalizability. By documenting this architecture and evaluation methodology, we aim to contribute to the broader research effort on efficient multimodal content moderation for child safety.
Authors: Haozhe Jia, Jianfei Song, Yuan Zhang, Honglei Jin, Youcheng Fan, Wenshuo Chen, Wei Zhang, Yutao Yue
Abstract: We present ECHO, an edge--cloud framework for language-driven whole-body control of humanoid robots. A cloud-hosted diffusion-based text-to-motion generator synthesizes motion references from natural language instructions, while an edge-deployed reinforcement-learning tracker executes them in closed loop on the robot. The two modules are bridged by a compact, robot-native 38-dimensional motion representation that encodes joint angles, root planar velocity, root height, and a continuous 6D root orientation per frame, eliminating inference-time retargeting from human body models and remaining directly compatible with low-level PD control. The generator adopts a 1D convolutional UNet with cross-attention conditioned on CLIP-encoded text features; at inference, DDIM sampling with 10 denoising steps and classifier-free guidance produces motion sequences in approximately one second on a cloud GPU. The tracker follows a Teacher--Student paradigm: a privileged teacher policy is distilled into a lightweight student equipped with an evidential adaptation module for sim-to-real transfer, further strengthened by morphological symmetry constraints and domain randomization. An autonomous fall recovery mechanism detects falls via onboard IMU readings and retrieves recovery trajectories from a pre-built motion library. We evaluate ECHO on a retargeted HumanML3D benchmark, where it achieves strong generation quality (FID 0.029, R-Precision Top-1 0.686) under a unified robot-domain evaluator, while maintaining high motion safety and trajectory consistency. Real-world experiments on a Unitree G1 humanoid demonstrate stable execution of diverse text commands with zero hardware fine-tuning.
Authors: Haomin Wang, Qi Wei, Qianli Ma, Shengyuan Ding, Jinhui Yin, Kai Chen, Hongjie Zhang
Abstract: With the rapid advancement of vision-language models, an increasing number of studies have explored their potential for SVG generation tasks. Although existing approaches improve performance by constructing large-scale SVG datasets and introducing SVG-specific tokens, they still suffer from limited generalization, redundant paths in code outputs, and a lack of explicit reasoning. In this work, we present CTRL-S (Chain-of-Thought Reinforcement Learning for SVG), a unified framework that introduces a chain-of-thought mechanism to explicitly expose the model's reasoning process during SVG generation. To support this structured reasoning, we construct SVG-Sophia, a high-quality dataset containing 145K samples across SVG code refinement, Text-to-SVG, and Image-to-SVG tasks. By training the model to generate group-level structured SVG code, CTRL-S significantly improves structural coherence and visual fidelity. Furthermore, we adopt the GRPO algorithm and design a multi-reward optimization framework, incorporating DINO, image-text similarity, format, and code efficiency rewards. Through joint multi-reward optimization and multi-task training, our approach systematically enhances overall generation capabilities. Extensive experiments show that CTRL-S outperforms existing methods, achieving higher task success rates, superior SVG code quality, and exceptional visual fidelity.
Authors: Haodong Yan, Zhide Zhong, Jiaguan Zhu, Junjie He, Weilin Yuan, Wenxuan Song, Xin Gong, Yingjie Cai, Guanyi Zhao, Xu Yan, Bingbing Liu, Ying-Cong Chen, Haoang Li
Abstract: Video action models (VAMs) have emerged as a promising paradigm for robot learning, owing to their powerful visual foresight for complex manipulation tasks. However, current VAMs, typically relying on either slow multi-step video generation or noisy one-step feature extraction, cannot simultaneously guarantee real-time inference and high-fidelity foresight. To address this limitation, we propose S-VAM, a shortcut video-action model that foresees coherent geometric and semantic representations via a single forward pass. Serving as a stable blueprint, these foreseen representations significantly simplify the action prediction. To enable this efficient shortcut, we introduce a novel self-distillation strategy that condenses structured generative priors of multi-step denoising into one-step inference. Specifically, vision foundation model (VFM) representations extracted from the diffusion model's own multi-step generated videos provide teacher targets. Lightweight decouplers, as students, learn to directly map noisy one-step features to these targets. Extensive experiments in simulation and the real world demonstrate that our S-VAM outperforms state-of-the-art methods, enabling efficient and precise manipulation in complex environments. Our project page is https://haodong-yan.github.io/S-VAM/
Authors: Yiming Huang, Baixiang Huang, Beilei Cui, Chi Kit Ng, Long Bai, Hongliang Ren
Abstract: Feed-forward 3D reconstruction has revolutionized 3D vision, providing a powerful baseline for downstream tasks such as novel-view synthesis with 3D Gaussian Splatting. Previous works explore fixing the corrupted rendering results with a diffusion model. However, they lack geometric concern and fail at filling the missing area on the extrapolated view. In this work, we introduce Leveling3D, a novel pipeline that integrates feed-forward 3D reconstruction with geometrical-consistent generation to enable holistic simultaneous reconstruction and generation. We propose a geometry-aware leveling adapter, a lightweight technique that aligns internal knowledge in the diffusion model with the geometry prior from the feed-forward model. The leveling adapter enables generation on the artifact area of the extrapolated novel views caused by underconstrained regions of the 3D representation. Specifically, to learn a more diverse distributed generation, we introduce the palette filtering strategy for training, and a test-time masking refinement to prevent messy boundaries along the fixing regions. More importantly, the enhanced extrapolated novel views from Leveling3D could be used as the inputs for feed-forward 3DGS, leveling up the 3D reconstruction. We achieve SOTA performance on public datasets, including tasks such as novel-view synthesis and depth estimation.
Authors: Ryosuke Hori, Jyun-Ting Song, Zhengyi Luo, Jinkun Cao, Soyong Shin, Hideo Saito, Kris Kitani
Abstract: We propose Ground Reaction Inertial Poser (GRIP), a method that reconstructs physically plausible human motion using four wearable devices. Unlike conventional IMU-only approaches, GRIP combines IMU signals with foot pressure data to capture both body dynamics and ground interactions. Furthermore, rather than relying solely on kinematic estimation, GRIP uses a digital twin of a person, in the form of a synthetic humanoid in a physics simulator, to reconstruct realistic and physically plausible motion. At its core, GRIP consists of two modules: KinematicsNet, which estimates body poses and velocities from sensor data, and DynamicsNet, which controls the humanoid in the simulator using the residual between the KinematicsNet prediction and the simulated humanoid state. To enable robust training and fair evaluation, we introduce a large-scale dataset, Pressure and Inertial Sensing for Human Motion and Interaction (PRISM), that captures diverse human motions with synchronized IMUs and insole pressure sensors. Experimental results show that GRIP outperforms existing IMU-only and IMU-pressure fusion methods across all evaluated datasets, achieving higher global pose accuracy and improved physical consistency.
Authors: Ryutaro Miya, Kazuyoshi Fushinobu, Tatsuya Kawaguchi
Abstract: We propose PureCLIP-Depth, a completely prompt-free, decoder-free Monocular Depth Estimation (MDE) model that operates entirely within the Contrastive Language-Image Pre-training (CLIP) embedding space. Unlike recent models that rely heavily on geometric features, we explore a novel approach to MDE driven by conceptual information, performing computations directly within the conceptual CLIP space. The core of our method lies in learning a direct mapping from the RGB domain to the depth domain strictly inside this embedding space. Our approach achieves state-of-the-art performance among CLIP embedding-based models on both indoor and outdoor datasets. The code used in this research is available at: https://github.com/ryutaroLF/PureCLIP-Depth
Authors: Jiyang Huang, Hongru Cheng, Wei Lin, Jia Wan, Antoni B. Chan
Abstract: Semi-supervised crowd analysis is a prominent area of research, as unlabeled data are typically abundant and inexpensive to obtain. However, traditional point-based annotations constrain performance because individual regions are inherently ambiguous, and consequently, learning fine-grained structural semantics from sparse anno tations remains an unresolved challenge. In this paper, we first propose an Exclusion-Constrained Dual-Prompt SAM (EDP-SAM), based on our Nearest Neighbor Exclusion Circle (NNEC) constraint, to generate mask supervision for current datasets. With the aim of segmenting individuals in dense scenes, we then propose Exclusivity-Guided Mask Learning (XMask), which enforces spatial separation through a discriminative mask objective. Gaussian smoothing and a differentiable center sampling strategy are utilized to improve feature continuity and training stability. Building on XMask, we present a semi-supervised crowd counting framework that uses instance mask priors as pseudo-labels, which contain richer shape information than traditional point cues. Extensive experiments on the ShanghaiTech A, UCF-QNRF, and JHU++ datasets (using 5%, 10%, and 40% labeled data) verify that our end-to-end model achieves state-of-the-art semi-supervised segmentation and counting performance, effectively bridging the gap between counting and instance segmentation within a unified framework.
Authors: Zeqiang Wei, Kai Jin, Kuan Song, Xiuzhuang Zhou, Wenlong Chen, Min Xu
Abstract: Current SSM-based light field super-resolution (LFSR) methods often fail to fully leverage the complementarity among various LF representations, leading to the loss of fine textures and geometric misalignments across views. To address these issues, we propose RASLF, a representation-aware state-space framework that explicitly models structural correlations across multiple LF representations. Specifically, a Progressive Geometric Refinement (PGR) block is created that uses a panoramic epipolar representation to explicitly encode multi-view parallax differences, thereby enabling integration across different LF representations. Furthermore, we introduce a Representation Aware Asymmetric Scanning (RAAS) mechanism that dynamically adjusts scanning paths based on the physical properties of different representation spaces, optimizing the balance between performance and efficiency through path pruning. Additionally, a Dual-Anchor Aggregation (DAA) module improves hierarchical feature flow, reducing redundant deeplayer features and prioritizing important reconstruction information. Experiments on various public benchmarks show that RASLF achieves the highest reconstruction accuracy while remaining highly computationally efficient.
Authors: Jiancheng Dong, Pengyue Jia, Derong Xu, Jiawei Cheng, Jingyu Peng, Chao Zhang, Bowen Liu, Xin Sun, Lixin Su, Shuaiqiang Wang, Dawei Yin, Xiangyu Zhao
Abstract: LLMs typically linearize 2D tables into 1D sequences to fit their autoregressive architecture, which weakens row-column adjacency and other layout cues. In contrast, purely visual encoders can capture spatial cues, yet often struggle to preserve exact cell text. Our analysis reveals that these two modalities provide highly distinct information to LLMs and exhibit strong complementarity. However, direct concatenation and other fusion methods yield limited gains and frequently introduce cross-modal interference. To address this issue, we propose DiVA-Former, a lightweight architecture designed to effectively integrate vision and text information. DiVA-Former leverages visual tokens as dynamic queries to distill long textual sequences into digest vectors, thereby effectively exploiting complementary vision--text information. Evaluated across 13 table benchmarks, DiVA-Former improves upon the pure-text baseline by 23.9\% and achieves consistent gains over existing baselines using visual inputs, textual inputs, or a combination of both.
Authors: Duc T. Nguyen, Hoang-Long Nguyen, Huy-Hieu Pham
Abstract: Automated white blood cell (WBC) classification is essential for leukemia screening but remains challenged by extreme class imbalance, long-tail distributions, and domain shift, leading deep models to overfit dominant classes and fail on rare subtypes. We propose a hybrid framework for rare-class generalization that integrates a generative Pix2Pix-based restoration module for artifact removal, a Swin Transformer ensemble with MedSigLIP contrastive embeddings for robust representation learning, and a biologically-inspired refinement step using geometric spikiness and Mahalanobis-based morphological constraints to recover out-of-distribution predictions. Evaluated on the WBCBench 2026 challenge, our method achieves a Macro-F1 of 0.77139 on the private leaderboard, demonstrating strong performance under severe imbalance and highlighting the value of incorporating biological priors into deep learning for hematological image analysis.
Authors: Jaechang Kim, Yotaro Shimose, Zhao Wang, Kuang-Da Wang, Jungseul Ok, Shingo Takamatsu
Abstract: LVLMs encounter significant challenges in image understanding and visual reasoning, leading to critical perception failures. Visual prompts, which incorporate image manipulation code, have shown promising potential in mitigating these issues. While emerged as a promising direction, previous methods for visual prompt generation have focused on tool selection rather than diagnosing and mitigating the root causes of LVLM perception failures. Because of the opacity and unpredictability of LVLMs, optimal visual prompts must be discovered through empirical experiments, which have relied on manual human trial-and-error. We propose an automated semantic exploration framework for discovering task-wise visual prompts. Our approach enables diverse yet efficient exploration through agent-driven experiments, minimizing human intervention and avoiding the inefficiency of per-sample generation. We introduce a semantic exploration algorithm named SEVEX, which addresses two major challenges of visual prompt exploration: (1) the distraction caused by lengthy, low-level code and (2) the vast, unstructured search space of visual prompts. Specifically, our method leverages an abstract idea space as a search space, a novelty-guided selection algorithm, and a semantic feedback-driven ideation process to efficiently explore diverse visual prompts based on empirical results. We evaluate SEVEX on the BlindTest and BLINK benchmarks, which are designed to assess LVLM perception. Experimental results demonstrate that SEVEX significantly outperforms baseline methods in task accuracy, inference efficiency, exploration efficiency, and exploration stability. Notably, our framework discovers sophisticated and counter-intuitive visual strategies that go beyond conventional tool usage, offering a new paradigm for enhancing LVLM perception through automated, task-wise visual prompts.
Authors: Junxin Wang, Dai Guan, Weijie Qiu, Zhihang Li, Yongbo Gai, Zhengyi Yang, Mengyu Zhou, Erchao Zhao, Xiaoxi Jiang, Guanjun Jiang
Abstract: Vision-language process reward models (VL-PRMs) are increasingly used to score intermediate reasoning steps and rerank candidates under test-time scaling. However, they often function as black-box judges: a low step score may reflect a genuine reasoning mistake or simply the verifier's misperception of the image. This entanglement between perception and reasoning leads to systematic false positives (rewarding hallucinated visual premises) and false negatives (penalizing correct grounded statements), undermining both reranking and error localization. We introduce Explicit Visual Premise Verification (EVPV), a lightweight verification interface that conditions step scoring on the reliability of the visual premises a step depends on. The policy is prompted to produce a step-wise visual checklist that makes required visual facts explicit, while a constraint extractor independently derives structured visual constraints from the input image. EVPV matches checklist claims against these constraints to compute a scalar visual reliability signal, and calibrates PRM step rewards via reliability gating: rewards for visually dependent steps are attenuated when reliability is low and preserved when reliability is high. This decouples perceptual uncertainty from logical evaluation without per-step tool calls. Experiments on VisualProcessBench and six multimodal reasoning benchmarks show that EVPV improves step-level verification and consistently boosts Best-of-N reranking accuracy over strong baselines. Furthermore, injecting controlled corruption into the extracted constraints produces monotonic performance degradation, providing causal evidence that the gains arise from constraint fidelity and explicit premise verification rather than incidental prompt effects. Code is available at: https://github.com/Qwen-Applications/EVPV-PRM
Authors: Xiaokun Sun, Yubo Wang, Haoyu Cao, Linli Xu
Abstract: Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant potential in complex visual tasks through the integration of Chain-of-Thought (CoT) reasoning. However, in Video Question Answering, extended thinking processes do not consistently yield performance gains and may even lead to degradation due to ``visual anchor drifting'', where models increasingly rely on self-generated text, sidelining visual inputs and causing hallucinations. While existing mitigations typically introduce specific mechanisms for the model to re-attend to visual inputs during inference, these approaches often incur prohibitive training costs and suffer from poor generalizability across different architectures. To address this, we propose FrameRepeat, an automated enhancement framework which features a lightweight repeat scoring module that enables Video-LLMs to autonomously identify which frames should be reinforced. We introduce a novel training strategy, Add-One-In (AOI), that uses MLLM output probabilities to generate supervision signals representing repeat gain. This can be used to train a frame scoring network, which guides the frame repetition behavior. Experimental results across multiple models and datasets demonstrate that FrameRepeat is both effective and generalizable in strengthening important visual cues during the reasoning process.
Authors: Weihua Gao, Wenlong Niu, Jie Tang, Man Yang, Jiafeng Zhang, Xiaodong Peng
Abstract: Infrared small target detection (IRSTD) methods predominantly formulate the task as pixel-level segmentation, which requires costly dense annotations and is not well suited to tiny targets with weak texture and ambiguous boundaries. To address this issue, we propose Point-to-Mask, a framework that bridges low-cost point supervision and mask-level detection through two components: a Physics-driven Adaptive Mask Generation (PAMG) module that converts point annotations into compact target masks and geometric cues, and a lightweight Radius-aware Point Regression Network (RPR-Net) that reformulates IRSTD as target center localization and effective radius regression using spatiotemporal motion cues. The two modules form a closed loop: PAMG generates pseudo masks and geometric supervision during training, while the geometric predictions of RPR-Net are fed back to PAMG for pixel-level mask recovery during inference. To facilitate systematic evaluation, we further construct SIRSTD-Pixel, a sequential dataset with refined pixel-level annotations. Experiments show that the proposed framework achieves strong pseudo-label quality, high detection accuracy, and efficient inference, approaching full-supervision performance under point-supervised settings with substantially lower annotation cost. Code and datasets will be available at: https://github.com/GaoScience/point-to-mask.
Authors: Hongwei Lin, Xun Huang, Chenglu Wen, Cheng Wang
Abstract: Robust 3D object detection under adverse weather conditions is crucial for autonomous driving. However, most existing methods simply combine all weather samples for training while overlooking data distribution discrepancies across different weather scenarios, leading to performance conflicts. To address this issue, we introduce AW-MoE, the framework that innovatively integrates Mixture of Experts (MoE) into weather-robust multi-modal 3D object detection approaches. AW-MoE incorporates Image-guided Weather-aware Routing (IWR), which leverages the superior discriminability of image features across weather conditions and their invariance to scene variations for precise weather classification. Based on this accurate classification, IWR selects the top-K most relevant Weather-Specific Experts (WSE) that handle data discrepancies, ensuring optimal detection under all weather conditions. Additionally, we propose a Unified Dual-Modal Augmentation (UDMA) for synchronous LiDAR and 4D Radar dual-modal data augmentation while preserving the realism of scenes. Extensive experiments on the real-world dataset demonstrate that AW-MoE achieves ~ 15% improvement in adverse-weather performance over state-of-the-art methods, while incurring negligible inference overhead. Moreover, integrating AW-MoE into established baseline detectors yields performance improvements surpassing current state-of-the-art methods. These results show the effectiveness and strong scalability of our AW-MoE. We will release the code publicly at https://github.com/windlinsherlock/AW-MoE.
Authors: Jinsheng Wei, Zhaodi Xu, Guanming Lu, Haoyu Chen, Jingjie Yan
Abstract: Micro-gesture recognition (MGR) is challenging due to subtle inter-class variations. Existing methods rely on category-level supervision, which is insufficient for capturing subtle and localized motion differences. Thus, this paper proposes a Fine-Grained Semantic Guidance Learning (FG-SGL) framework that jointly integrates fine-grained and category-level semantics to guide vision--language models in perceiving local MG motions. FG-SA adopts fine-grained semantic cues to guide the learning of local motion features, while CP-A enhances the separability of MG features through category-level semantic guidance. To support fine-grained semantic guidance, this work constructs a fine-grained textual dataset with human annotations that describes the dynamic process of MGs in four refined semantic dimensions. Furthermore, a Multi-Level Contrastive Optimization strategy is designed to jointly optimize both modules in a coarse-to-fine pattern. Experiments show that FG-SGL achieves competitive performance, validating the effectiveness of fine-grained semantic guidance for MGR.
Authors: Tengjiao Yin, Jinglei Shi, Heng Guo, Xi Wang
Abstract: Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial drift, and depth violations in generated videos. To address this limitation, we propose a geometry-based reward model that leverages pretrained geometric foundation models to evaluate multi-view consistency through cross-frame reprojection error. Unlike previous geometric metrics that measure inconsistency in pixel space, where pixel intensity may introduce additional noise, our approach conducts error computation in a pointwise fashion, yielding a more physically grounded and robust error metric. Furthermore, we introduce a geometry-aware sampling strategy that filters out low-texture and non-semantic regions, focusing evaluation on geometrically meaningful areas with reliable correspondences to improve robustness. We apply this reward model to align video diffusion models through two complementary pathways: post-training of a bidirectional model via SFT or Reinforcement Learning and inference-time optimization of a Causal Video Model (e.g., Streaming video generator) via test-time scaling with our reward as a path verifier. Experimental results validate the effectiveness of our design, demonstrating that our geometry-based reward provides superior robustness compared to other variants. By enabling efficient inference-time scaling, our method offers a practical solution for enhancing open-source video models without requiring extensive computational resources for retraining.
Authors: TianTian Dang, Chao Bi, Shufan Shen, Jinzhe Liu, Qingming Huang, Shuhui Wang
Abstract: Despite the significant advancements in Large Vision-Language Models (LVLMs), their tendency to generate hallucinations undermines reliability and restricts broader practical deployment. Among the hallucination mitigation methods, feature steering emerges as a promising approach that reduces erroneous outputs in LVLMs without increasing inference costs. However, current methods apply uniform feature steering across all layers. This heuristic strategy ignores inter-layer differences, potentially disrupting layers unrelated to hallucinations and ultimately leading to performance degradation on general tasks. In this paper, we propose a plug-and-play framework called Locate-Then-Sparsify for Feature Steering (LTS-FS), which controls the steering intensity according to the hallucination relevance of each layer. We first construct a synthetic dataset comprising token-level and sentence-level hallucination cases. Based on this dataset, we introduce an attribution method based on causal interventions to quantify the hallucination relevance of each layer. With the attribution scores across layers, we propose a layerwise strategy that converts these scores into feature steering intensities for individual layers, enabling more precise adjustments specifically on hallucination-relevant layers. Extensive experiments across multiple LVLMs and benchmarks demonstrate that our LTS-FS framework effectively mitigates hallucination while preserving strong performance.
Authors: Jinlu Zhang, Qiyun Wang, Baoxiang Du, Jiayi Ji, Jing He, Rongsheng Zhang, Tangjie Lv, Xiaoshuai Sun, Rongrong Ji
Abstract: Story visualization has gained increasing attention in computer vision. However, current methods often fail to achieve a synergy between accurate character customization, semantic alignment, and continuous integration of new identities. To tackle this challenge, in this paper we present EverTale, a story world simulator for continuous story character customization. We first propose an All-in-One-World Character Integrator to achieve continuous character adaptation within unified LoRA module, eliminating the need for per-character optimization modules of previous methods. Then, we incorporate a Character Quality Gate via MLLM-as-Judge to ensure the fidelity of each character adaptation process through chain-of-thought reasoning, determining whether the model can proceed to the next character or require additional training on the current one. We also introduce a Character-Aware Region-Focus Sampling strategy to address the identity degradation and layout conflicts in existing multi-character visual storytelling, ensuring natural multi-character generation by harmonizing local character-specific details with global scene context with higher efficiency. Experimental results show that our EverTale achieves superior performance against a wider range of compared methods on both single- and multi-character story visualization. Codes will be available.
Authors: Zhengbo Zhang, Jinbo Su, Zhaowen Zhou, Changtao Miao, Yuhan Hong, Qimeng Wu, Yumeng Liu, Feier Wu, Yihe Tian, Yuhao Liang, Zitong Shan, Wanke Xia, Yi-Fan Zhang, Bo Zhang, Zhe Li, Shiming Xiang, Ying Yan
Abstract: The rapid advancement of Multimodal Large Language Models (MLLMs) has enabled browsing agents to acquire and reason over multimodal information in the real world. But existing benchmarks suffer from two limitations: insufficient evaluation of visual reasoning ability and the neglect of native visual information of web pages in the reasoning chains. To address these challenges, we introduce a new benchmark for visual-native search, VisBrowse-Bench. It contains 169 VQA instances covering multiple domains and evaluates the models' visual reasoning capabilities during the search process through multimodal evidence cross-validation via text-image retrieval and joint reasoning. These data were constructed by human experts using a multi-stage pipeline and underwent rigorous manual verification. We additionally propose an agent workflow that can effectively drive the browsing agent to actively collect and reason over visual information during the search process. We comprehensively evaluated both open-source and closed-source models in this workflow. Experimental results show that even the best-performing model, Claude-4.6-Opus only achieves an accuracy of 47.6%, while the proprietary Deep Research model, o3-deep-research only achieves an accuracy of 41.1%. The code and data can be accessed at: https://github.com/ZhengboZhang/VisBrowse-Bench
Authors: Jinsheng Wei, Fengzhou Guo, Yante Li, Haoyu Chen, Guanming Lu, Guoying Zhao
Abstract: Micro-expression (ME) action units (Micro-AUs) provide objective clues for fine-grained genuine emotion analysis. Most existing Micro-AU detection methods learn AU features from the whole facial image/video, which conflicts with the inherent locality of AU, resulting in insufficient perception of AU regions. In fact, each AU independently corresponds to specific localized facial muscle movements (local independence), while there is an inherent dependency between some AUs under specific emotional states (global dependency). Thus, this paper explores the effectiveness of the independence-to-dependency pattern and proposes a novel micro-AU detection framework, micro-AU CLIP, that uniquely decomposes the AU detection process into local semantic independence modeling (LSI) and global semantic dependency (GSD) modeling. In LSI, Patch Token Attention (PTA) is designed, mapping several local features within the AU region to the same feature space; In GSD, Global Dependency Attention (GDA) and Global Dependency Loss (GDLoss) are presented to model the global dependency relationships between different AUs, thereby enhancing each AU feature. Furthermore, considering CLIP's native limitations in micro-semantic alignment, a microAU contrastive loss (MiAUCL) is designed to learn AU features by a fine-grained alignment of visual and text features. Also, Micro-AU CLIP is effectively applied to ME recognition in an emotion-label-free way. The experimental results demonstrate that Micro-AU CLIP can fully learn fine-grained micro-AU features, achieving state-of-the-art performance.
Authors: Heyu Si, Brandon James Denis, Muyang Sun, Dragos Datcu, Yaoru Li, Xin Jin, Ruiju Fu, Yuliia Tatarinova, Federico Landi, Jie Song, Mingli Song, Qi Guo
Abstract: Recent advancements in 4D scene reconstruction, particularly those leveraging diffusion priors, have shown promise for novel view synthesis in autonomous driving. However, these methods often process frames independently or in a view-by-view manner, leading to a critical lack of spatio-temporal synergy. This results in spatial misalignment across cameras and temporal drift in sequences. We propose DriveFix, a novel multi-view restoration framework that ensures spatio-temporal coherence for driving scenes. Our approach employs an interleaved diffusion transformer architecture with specialized blocks to explicitly model both temporal dependencies and cross-camera spatial consistency. By conditioning the generation on historical context and integrating geometry-aware training losses, DriveFix enforces that the restored views adhere to a unified 3D geometry. This enables the consistent propagation of high-fidelity textures and significantly reduces artifacts. Extensive evaluations on the Waymo, nuScenes, and PandaSet datasets demonstrate that DriveFix achieves state-of-the-art performance in both reconstruction and novel view synthesis, marking a substantial step toward robust 4D world modeling for real-world deployment.
Authors: Ann Rachel, Pranav M Pawar, Mithun Mukharjee, Raja M, Tojo Mathew
Abstract: Lung cancer is a condition where there is abnormal growth of malignant cells that spread in an uncontrollable fashion in the lungs. Some common treatment strategies are surgery, chemotherapy, and radiation which aren't the best options due to the heterogeneous nature of cancer. In personalized medicine, treatments are tailored according to the individual's genetic information along with lifestyle aspects. In addition, AI-based deep learning methods can analyze large sets of data to find early signs of cancer, types of tumor, and prospects of treatment. The paper focuses on the development of personalized treatment plans using specific patient data focusing primarily on the genetic profile. Multi-Omics data from Genomics of Drug Sensitivity in Cancer have been used to build a predictive model along with machine learning techniques. The value of the target variable, LN-IC50, determines how sensitive or resistive a drug is. An XGBoost regressor is utilized to predict the drug response focusing on molecular and cellular features extracted from cancer datasets. Cross-validation and Randomized Search are performed for hyperparameter tuning to further optimize the model's predictive performance. For explanation purposes, SHAP (SHapley Additive exPlanations) was used. SHAP values measure each feature's impact on an individual prediction. Furthermore, interpreting feature relationships was performed using DeepSeek, a large language model trained to verify the biological validity of the features. Contextual explanations regarding the most important genes or pathways were provided by DeepSeek alongside the top SHAP value constituents, supporting the predictability of the model.
Authors: Maxime Vaillant, Axel Carlier, Lai Xing Ng, Christophe Hurter, Benoit R. Cottereau
Abstract: Event-based vision sensors provide significant advantages for high-speed perception, including microsecond temporal resolution, high dynamic range, and low power consumption. When combined with Spiking Neural Networks (SNNs), they can be deployed on neuromorphic hardware, enabling energy-efficient applications on embedded systems. However, this potential is severely limited by the scarcity of large-scale labeled datasets required to effectively train such models. In this work, we introduce SpikeCLR, a contrastive self-supervised learning framework that enables SNNs to learn robust visual representations from unlabeled event data. We adapt prior frame-based methods to the spiking domain using surrogate gradient training and introduce a suite of event-specific augmentations that leverage spatial, temporal, and polarity transformations. Through extensive experiments on CIFAR10-DVS, N-Caltech101, N-MNIST, and DVS-Gesture benchmarks, we demonstrate that self-supervised pretraining with subsequent fine-tuning outperforms supervised learning in low-data regimes, achieving consistent gains in few-shot and semi-supervised settings. Our ablation studies reveal that combining spatial and temporal augmentations is critical for learning effective spatio-temporal invariances in event data. We further show that learned representations transfer across datasets, contributing to efforts for powerful event-based models in label-scarce settings.
Authors: Xinhao Cai, Gensheng Pei, Zeren Sun, Yazhou Yao, Fumin Shen, Wenguan Wang
Abstract: In this paper, we propose \textbf{Iris}, a deterministic framework for Monocular Depth Estimation (MDE) that integrates real-world priors into the diffusion model. Conventional feed-forward methods rely on massive training data, yet still miss details. Previous diffusion-based methods leverage rich generative priors yet struggle with synthetic-to-real domain transfer. Iris, in contrast, preserves fine details, generalizes strongly from synthetic to real scenes, and remains efficient with limited training data. To this end, we introduce a two-stage Priors-to-Geometry Deterministic (PGD) schedule: the prior stage uses Spectral-Gated Distillation (SGD) to transfer low-frequency real priors while leaving high-frequency details unconstrained, and the geometry stage applies Spectral-Gated Consistency (SGC) to enforce high-frequency fidelity while refining with synthetic ground truth. The two stages share weights and are executed with a high-to-low timestep schedule. Extensive experimental results confirm that Iris achieves significant improvements in MDE performance with strong in-the-wild generalization.
Authors: Xinhao Cai, Liulei Li, Gensheng Pei, Zeren Sun, Yazhou Yao, Wenguan Wang
Abstract: Object detection in remote sensing images (RSIs) is challenged by the coexistence of geometric and spatial complexity: targets may appear with diverse aspect ratios, while spanning a wide range of object sizes under varied contexts. Existing RSI backbones address the two challenges separately, either by adopting anisotropic strip kernels to model slender targets or by using isotropic large kernels to capture broader context. However, such isolated treatments lead to complementary drawbacks: the strip-only design can disrupt spatial coherence for regular-shaped objects and weaken tiny details, whereas isotropic large kernels often introduce severe background noise and geometric mismatch for slender structures. In this paper, we extend PKINet, and present a powerful and efficient backbone that jointly handles both challenges within a unified paradigm named Poly Kernel Inception Network v2 (PKINet-v2). PKINet-v2 synergizes anisotropic axial-strip convolutions with isotropic square kernels and builds a multi-scope receptive field, preserving fine-grained local textures while progressively aggregating long-range context across scales. To enable efficient deployment, we further introduce a Heterogeneous Kernel Re-parameterization (HKR) Strategy that fuses all heterogeneous branches into a single depth-wise convolution for inference, eliminating fragmented kernel launches without accuracy loss. Extensive experiments on four widely-used benchmarks, including DOTA-v1.0, DOTA-v1.5, HRSC2016, and DIOR-R, demonstrate that PKINet-v2 achieves state-of-the-art accuracy while delivering a $\textbf{3.9}\times$ FPS acceleration compared to PKINet-v1, surpassing previous remote sensing backbones in both effectiveness and efficiency.
Authors: Daniel Sungho Jung, Dohee Cho, Kyoung Mu Lee
Abstract: Understanding humans from LiDAR point clouds is one of the most critical tasks in autonomous driving due to its close relationships with pedestrian safety, yet it remains challenging in the presence of diverse human-object interactions and cluttered backgrounds. Nevertheless, existing methods largely overlook the potential of leveraging human-object interactions to build robust 3D human pose estimation frameworks. There are two major challenges that motivate the incorporation of human-object interaction. First, human-object interactions introduce spatial ambiguity between human and object points, which often leads to erroneous 3D human keypoint predictions in interaction regions. Second, there exists severe class imbalance in the number of points between interacting and non-interacting body parts, with the interaction-frequent regions such as hand and foot being sparsely observed in LiDAR data. To address these challenges, we propose a Human-Object Interaction Learning (HOIL) framework for robust 3D human pose estimation from LiDAR point clouds. To mitigate the spatial ambiguity issue, we present human-object interaction-aware contrastive learning (HOICL) that effectively enhances feature discrimination between human and object points, particularly in interaction regions. To alleviate the class imbalance issue, we introduce contact-aware part-guided pooling (CPPool) that adaptively reallocates representational capacity by compressing overrepresented points while preserving informative points from interacting body parts. In addition, we present an optional contact-based temporal refinement that refines erroneous per-frame keypoint estimates using contact cues over time. As a result, our HOIL effectively leverages human-object interaction to resolve spatial ambiguity and class imbalance in interaction regions. Codes will be released.
Authors: Joao Manoel Herrera Pinheiro, Gabriela Do Nascimento Herrera, Alvaro Doria Dos Santos, Luciana Bueno Dos Reis Fernandes, Ricardo V. Godoy, Eduardo A. B. Almeida, Helena Carolina Onody, Marcelo Andrade Da Costa Vieira, Angelica Maria Penteado-Dias, Marcelo Becker
Abstract: Accurate taxonomic identification of parasitoid wasps within the superfamily Ichneumonoidea is essential for biodiversity assessment, ecological monitoring, and biological control programs. However, morphological similarity, small body size, and fine-grained interspecific variation make manual identification labor-intensive and expertise-dependent. This study proposes a deep learning-based framework for the automated identification of Ichneumonoidea wasps using a YOLO-based architecture integrated with High-Resolution Class Activation Mapping (HiResCAM) to enhance interpretability. The proposed system simultaneously identifies wasp families from high-resolution images. The dataset comprises 3556 high-resolution images of Hymenoptera specimens. The taxonomic distribution is primarily concentrated among the families Ichneumonidae (n = 786), Braconidae (n = 648), Apidae (n = 466), and Vespidae (n = 460). Extensive experiments were conducted using a curated dataset, with model performance evaluated through precision, recall, F1 score, and accuracy. The results demonstrate high accuracy of over 96 % and robust generalization across morphological variations. HiResCAM visualizations confirm that the model focuses on taxonomically relevant anatomical regions, such as wing venation, antennae segmentation, and metasomal structures, thereby validating the biological plausibility of the learned features. The integration of explainable AI techniques improves transparency and trustworthiness, making the system suitable for entomological research to accelerate biodiversity characterization in an under-described parasitoid superfamily.
Authors: Ruizhi Wang, Weihan Li, Zunlei Feng, Haofei Zhang, Mingli Song, Jiayu Wang, Jie Song, Li Sun
Abstract: Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications, yet existing methods face a stark trade-off between accuracy and efficiency. Although using Vision Transformer (ViT) backbones for dense prediction is fast, they often exhibit poor perceptual quality. Conversely, diffusion models offer high fidelity but at a prohibitive computational cost. To overcome these limitations, we propose Depth Detail Diffusion for Remote Sensing Monocular Depth Estimation ($D^3$-RSMDE), an efficient framework designed to achieve an optimal balance between speed and quality. Our framework first leverages a ViT-based module to rapidly generate a high-quality preliminary depth map construction, which serves as a structural prior, effectively replacing the time-consuming initial structure generation stage of diffusion models. Based on this prior, we propose a Progressive Linear Blending Refinement (PLBR) strategy, which uses a lightweight U-Net to refine the details in only a few iterations. The entire refinement step operates efficiently in a compact latent space supported by a Variational Autoencoder (VAE). Extensive experiments demonstrate that $D^3$-RSMDE achieves a notable 11.85% reduction in the Learned Perceptual Image Patch Similarity (LPIPS) perceptual metric over leading models like Marigold, while also achieving over a 40x speedup in inference and maintaining VRAM usage comparable to lightweight ViT models.
Authors: Yiqiang Zhou, Yifan Chen, Zhe Sun, Jijun Lu, Ye Zheng, Xuelong Li
Abstract: Underwater image enhancement plays a crucial role in providing reliable visual information for underwater platforms, since strong absorption and scattering in water-related environments generally lead to image quality degradation. Existing high-performance methods often rely on complex architectures, which hinder deployment on underwater devices. Lightweight methods often sacrifice quality for speed and struggle to handle severely degraded underwater images. To address this limitation, we present a real-time underwater image enhancement framework with accurate color restoration. First, an Adaptive Weighted Channel Compensation module is introduced to achieve dynamic color recovery of the red and blue channels using the green channel as a reference anchor. Second, we design a Multi-branch Re-parameterized Dilated Convolution that employs multi-branch fusion during training and structural re-parameterization during inference, enabling large receptive field representation with low computational overhead. Finally, a Statistical Global Color Adjustment module is employed to optimize overall color performance based on statistical priors. Extensive experiments on eight datasets demonstrate that the proposed method achieves state-of-the-art performance across seven evaluation metrics. The model contains only 3,880 inference parameters and achieves an inference speed of 409 FPS. Our method improves the UCIQE score by 29.7% under diverse environmental conditions, and the deployment on ROV platforms and performance gains in downstream tasks further validate its superiority for real-time underwater missions.
Authors: Zhisong Wang, Ziyang Chen, Zanting Ye, Hongze Zhu, Yefeng Zheng, Yong Xia
Abstract: Medical visual question answering (Med-VQA) aims to answer clinically relevant questions grounded in medical images. However, existing multimodal large language models (MLLMs) often exhibit shortcut answering, producing plausible responses by exploiting language priors or dataset biases while insufficiently attending to visual evidence. This behavior undermines clinical reliability, especially when subtle imaging findings are decisive. We propose a lightweight plug-in framework, termed Intent-aware Visual Cues (InViC), to explicitly enhance image-based answer generation in medical VQA. InViC introduces a Cue Tokens Extraction (CTE) module that distills dense visual tokens into a compact set of K question-conditioned cue tokens, which serve as structured visual intermediaries injected into the LLM decoder to promote intent-aligned visual evidence. To discourage bypassing of visual information, we further design a two-stage fine-tuning strategy with a cue-bottleneck attention mask. In Stage I, we employ an attention mask to block the LLM's direct view of raw visual features, thereby funneling all visual evidence through the cue pathway. In Stage II, standard causal attention is restored to train the LLM to jointly exploit the visual and cue tokens. We evaluate InViC on three public Med-VQA benchmarks (VQA-RAD, SLAKE, and ImageCLEF VQA-Med 2019) across multiple representative MLLMs. InViC consistently improves over zero-shot inference and standard LoRA fine-tuning, demonstrating that intent-aware visual cues with bottlenecked training is a practical and effective strategy for improving trustworthy Med-VQA.
Authors: Yunpeng Qu, Kaidong Zhang, Yukang Ding, Ying Chen, Jian Wang
Abstract: Visual generative models based on latent space have achieved great success, underscoring the significance of visual tokenization. Mapping images to latents boosts efficiency and enables multimodal alignment for scaling up in downstream tasks. Existing visual tokenizers primarily map images into fixed 2D spatial grids and focus on pixel-level restoration, which hinders the capture of representations with compact global semantics. To address these issues, we propose \textbf{SemTok}, a semantic one-dimensional tokenizer that compresses 2D images into 1D discrete tokens with high-level semantics. SemTok sets a new state-of-the-art in image reconstruction, achieving superior fidelity with a remarkably compact token representation. This is achieved via a synergistic framework with three key innovations: a 2D-to-1D tokenization scheme, a semantic alignment constraint, and a two-stage generative training strategy. Building on SemTok, we construct a masked autoregressive generation framework, which yields notable improvements in downstream image generation tasks. Experiments confirm the effectiveness of our semantic 1D tokenization. Our code will be open-sourced.
Authors: Zhan Tong, ChenXu Zhou, Fei Tang, Yiming Tu, Tianyu Qin, Kaihao Fang
Abstract: Defense Meteorological Satellite Program (DMSP-OLS) and Suomi National Polar-orbiting Partnership (SNPP-VIIRS) nighttime light (NTL) data are vital for monitoring urbanization, yet sensor incompatibilities hinder long-term analysis. This study proposes a cross-sensor calibration method using Contrastive Unpaired Translation (CUT) network to transform DMSP data into VIIRS-like format, correcting DMSP defects. The method employs multilayer patch-wise contrastive learning to maximize mutual information between corresponding patches, preserving content consistency while learning cross-domain similarity. Utilizing 2012-2013 overlapping data for training, the network processes 1992-2013 DMSP imagery to generate enhanced VIIRS-style raster data. Validation results demonstrate that generated VIIRS-like data exhibits high consistency with actual VIIRS observations (R-squared greater than 0.87) and socioeconomic indicators. This approach effectively resolves cross-sensor data fusion issues and calibrates DMSP defects, providing reliable attempt for extended NTL time-series.
Authors: Stathis Galanakis, Alexandros Koliousis, Stefanos Zafeiriou
Abstract: Despite recent advances in deep generative modeling, skin lesion classification systems remain constrained by the limited availability of large, diverse, and well-annotated clinical datasets, resulting in class imbalance between benign and malignant lesions and consequently reduced generalization performance. We introduce DermaFlux, a rectified flow-based text-to-image generative framework that synthesizes clinically grounded skin lesion images from natural language descriptions of dermatological attributes. Built upon Flux.1, DermaFlux is fine-tuned using parameter-efficient Low-Rank Adaptation (LoRA) on a large curated collection of publicly available clinical image datasets. We construct image-text pairs using synthetic textual captions generated by Llama 3.2, following established dermatological criteria including lesion asymmetry, border irregularity, and color variation. Extensive experiments demonstrate that DermaFlux generates diverse and clinically meaningful dermatology images that improve binary classification performance by up to 6% when augmenting small real-world datasets, and by up to 9% when classifiers are trained on DermaFlux-generated synthetic images rather than diffusion-based synthetic images. Our ImageNet-pretrained ViT fine-tuned with only 2,500 real images and 4,375 DermaFlux-generated samples achieves 78.04% binary classification accuracy and an AUC of 0.859, surpassing the next best dermatology model by 8%.
Authors: Lilika Makabe, Heng Guo, Hiroaki Santo, Fumio Okura, Yasuyuki Matsushita
Abstract: This paper describes a linear solution method for near-light photometric stereo by exploiting symmetric light source arrangements. Unlike conventional non-convex optimization approaches, by arranging multiple sets of symmetric nearby light source pairs, our method derives a closed-form solution for surface normal and depth without requiring initialization. In addition, our method works as long as the light sources are symmetrically distributed about an arbitrary point even when the entire spatial offset is uncalibrated. Experiments showcase the accuracy of shape recovery accuracy of our method, achieving comparable results to the state-of-the-art calibrated near-light photometric stereo method while significantly reducing requirements of careful depth initialization and light calibration.
Authors: Jing Dai, Chen Wu, Ming Wu, Qibin Zhang, Zexi Wu, Jingdong Zhang, Hongming Xu
Abstract: Recent advances in multimodal learning have significantly improved cancer survival risk prediction. However, the joint prognostic potential of protein markers and histopathology images remains underexplored, largely due to the high cost and limited availability of protein expression profiling. To address this challenge, we propose HGP-Mamba, a Mamba-based multimodal framework that efficiently integrates histological with generated protein features for survival risk prediction. Specifically, we introduce a protein feature extractor (PFE) that leverages pretrained foundation models to derive high-throughput protein embeddings directly from Whole Slide Images (WSIs), enabling data-efficient incorporation of molecular information. Together with histology embeddings that capture morphological patterns, we further introduce the Local Interaction-aware Mamba (LiAM) for fine-grained feature interaction and the Global Interaction-enhanced Mamba (GiEM) to promote holistic modality fusion at the slide level, thus capture complex cross-modal dependencies. Experiments on four public cancer datasets demonstrate that HGP-Mamba achieves state-of-the-art performance while maintaining superior computational efficiency compared with existing methods. Our source code is publicly available at https://github.com/Daijing-ai/HGP-Mamba.git.
Authors: Masakazu Yoshimura, Teruaki Hayashi, Yuki Hoshino, Wei-Yao Wang, Takeshi Ohashi
Abstract: The realm of Mamba for vision has been advanced in recent years to strike for the alternatives of Vision Transformers (ViTs) that suffer from the quadratic complexity. While the recurrent scanning mechanism of Mamba offers computational efficiency, it inherently limits non-causal interactions between image patches. Prior works have attempted to address this limitation through various multi-scan strategies; however, these approaches suffer from inefficiencies due to suboptimal scan designs and frequent data rearrangement. Moreover, Mamba exhibits relatively slow computational speed under short token lengths, commonly used in visual tasks. In pursuit of a truly efficient vision encoder, we rethink the scan operation for vision and the computational efficiency of Mamba. To this end, we propose SF-Mamba, a novel visual Mamba with two key proposals: auxiliary patch swapping for encoding bidirectional information flow under an unidirectional scan and batch folding with periodic state reset for advanced GPU parallelism. Extensive experiments on image classification, object detection, and instance and semantic segmentation consistently demonstrate that our proposed SF-Mamba significantly outperforms state-of-the-art baselines while improving throughput across different model sizes. We will release the source code after publication.
Authors: Muhammad Ahmad
Abstract: Hyperspectral image classification (HSIC) has been significantly advanced by deep learning methods that exploit rich spatial-spectral correlations. However, existing approaches still face fundamental limitations: transformer-based models suffer from poor scalability due to the quadratic complexity of self-attention, while recent Fourier transform-based methods typically rely on 2D spatial FFTs and largely ignore critical inter-band spectral dependencies inherent to hyperspectral data. To address these challenges, we propose Hybrid GFNet (HGFNet), a novel architecture that integrates localized 3D convolutional feature extraction with frequency-domain global filtering via GFNet-style blocks for efficient and robust spatial-spectral representation learning. HGFNet introduces three complementary frequency transforms tailored to hyperspectral imagery: Spectral Fourier Transform (a 1D FFT along the spectral axis), Spatial Fourier Transform (a 2D FFT over spatial dimensions), and Spatial-Spatial Fourier Transform (a 3D FFT jointly over spectral and spatial dimensions), enabling comprehensive and high-dimensional frequency modeling. The 3D convolutional layers capture fine-grained local spatial-spectral structures, while the Fourier-based global filtering modules efficiently model long-range dependencies and suppress noise. To further mitigate the severe class imbalance commonly observed in HSIC, HGFNet incorporates an Adaptive Focal Loss (AFL) that dynamically adjusts class-wise focusing and weighting, improving discrimination for underrepresented classes.
Authors: Joona Kareinen, Veikka Immonen, Tuomas Eerola, Lumi Haraguchi, Lasse Lensu, Kaisa Kraft, Sanna Suikkanen, Heikki K\"alvi\"ainen
Abstract: This paper considers self-supervised cross-modal coordination as a strategy enabling utilization of multiple modalities and large volumes of unlabeled plankton data to build models for plankton recognition. Automated imaging instruments facilitate the continuous collection of plankton image data on a large scale. Current methods for automatic plankton image recognition rely primarily on supervised approaches, which require labeled training sets that are labor-intensive to collect. On the other hand, some modern plankton imaging instruments complement image information with optical measurement data, such as scatter and fluorescence profiles, which currently are not widely utilized in plankton recognition. In this work, we explore the possibility of using such measurement data to guide the learning process without requiring manual labeling. Inspired by the concepts behind Contrastive Language-Image Pre-training, we train encoders for both modalities using only binary supervisory information indicating whether a given image and profile originate from the same particle or from different particles. For plankton recognition, we employ a small labeled gallery of known plankton species combined with a $k$-NN classifier. This approach yields a recognition model that is inherently multimodal, i.e., capable of utilizing information extracted from both image and profile data. We demonstrate that the proposed method achieves high recognition accuracy while requiring only a minimal number of labeled images. Furthermore, we show that the approach outperforms an image-only self-supervised baseline. Code available at https://github.com/Jookare/cross-modal-plankton.
Authors: Rasul Khanbayov, Mohamed Rayan Barhdadi, Erchin Serpedin, Hasan Kurban
Abstract: Unsupervised physical parameter estimation from video lacks a common benchmark: existing methods evaluate on non-overlapping synthetic data, the sole real-world dataset is restricted to single-body systems, and no established protocol addresses governing-equation identification. This work introduces IRIS, a high-fidelity benchmark comprising 220 real-world videos captured at 4K resolution and 60\,fps, spanning both single- and multi-body dynamics with independently measured ground-truth parameters and uncertainty estimates. Each dynamical system is recorded under controlled laboratory conditions and paired with its governing equations, enabling principled evaluation. A standardized evaluation protocol is defined encompassing parameter accuracy, identifiability, extrapolation, robustness, and governing-equation selection. Multiple baselines are evaluated, including a multi-step physics loss formulation and four complementary equation-identification strategies (VLM temporal reasoning, describe-then-classify prompting, CNN-based classification, and path-based labelling), establishing reference performance across all IRIS scenarios and exposing systematic failure modes that motivate future research. The dataset, annotations, evaluation toolkit, and all baseline implementations are publicly released.
Authors: Junseok Lee, Sungho Shin, Seongju Lee, Kyoobin Lee
Abstract: Single-domain generalization is essential for object detection, particularly when training models on a single source domain and evaluating them on unseen target domains. Domain shifts, such as changes in weather, lighting, or scene conditions, pose significant challenges to the generalization ability of existing models. To address this, we propose Cross-Domain Feature Knowledge Distillation (CD-FKD), which enhances the generalization capability of the student network by leveraging both global and instance-wise feature distillation. The proposed method uses diversified data through downscaling and corruption to train the student network, whereas the teacher network receives the original source domain data. The student network mimics the features of the teacher through both global and instance-wise distillation, enabling it to extract object-centric features effectively, even for objects that are difficult to detect owing to corruption. Extensive experiments on challenging scenes demonstrate that CD-FKD outperforms state-of-the-art methods in both target domain generalization and source domain performance, validating its effectiveness in improving object detection robustness to domain shifts. This approach is valuable in real-world applications, like autonomous driving and surveillance, where robust object detection in diverse environments is crucial.
Authors: Hunain Ahmed Jillani, Ahmed Tawfik Aboukhadra, Ahmed Elhayek, Jameel Malik, Nadia Robertini, Didier Stricker
Abstract: Fast and accurate 3D hand reconstruction is essential for real-time applications in VR/AR, human-computer interaction, robotics, and healthcare. Most state-of-the-art methods rely on heavy models, limiting their use on resource-constrained devices like headsets, smartphones, and embedded systems. In this paper, we investigate how the use of lightweight neural networks, combined with Knowledge Distillation, can accelerate complex 3D hand reconstruction models by making them faster and lighter, while maintaining comparable reconstruction accuracy. While our approach is suited for various hand reconstruction frameworks, we focus primarily on boosting the HaMeR model, currently the leading method in terms of reconstruction accuracy. We replace its original ViT-H backbone with lighter alternatives, including MobileNet, MobileViT, ConvNeXt, and ResNet, and evaluate three knowledge distillation strategies: output-level, feature-level, and a hybrid of both. Our experiments show that using lightweight backbones that are only 35% the size of the original achieves 1.5x faster inference speed while preserving similar performance quality with only a minimal accuracy difference of 0.4mm. More specifically, we show how output-level distillation notably improves student performance, while feature-level distillation proves more effective for higher-capacity students. Overall, the findings pave the way for efficient real-world applications on low-power devices. The code and models are publicly available under https://github.com/hunainahmedj/Fast-HaMeR.
Authors: Xingyu Liu, Zewei He, Yu Chen, Chunyu Zhu, Zixuan Chen, Xing Luo, Zhe-Ming Lu
Abstract: When capturing images through glass surfaces or windshields on rainy days, raindrops and reflections frequently co-occur to significantly reduce the visibility of captured images. This practical problem lacks attention and needs to be resolved urgently. Prior de-raindrop, de-reflection, and all-in-one models have failed to address this composite degradation. To this end, we first formally define the unified removal of raindrops and reflections (UR$^3$) task for the first time and construct a real-shot dataset, namely RainDrop and ReFlection (RDRF), which provides a new benchmark with substantial, high-quality, diverse image pairs. Then, we propose a novel diffusion-based framework (i.e., DiffUR$^3$) with several target designs to address this challenging task. By leveraging the powerful generative prior, DiffUR$^3$ successfully removes both types of degradations. Extensive experiments demonstrate that our method achieves state-of-the-art performance on our benchmark and on challenging in-the-wild images. The RDRF dataset and the codes will be made public upon acceptance.
Authors: Kaiwen Song, Jinkai Cui, Juyong Zhang
Abstract: In practical real-time XR and telepresence applications, network and computing resources fluctuate frequently. Therefore, a progressive 3D representation is needed. To this end, we propose ProgressiveAvatars, a progressive avatar representation built on a hierarchy of 3D Gaussians grown by adaptive implicit subdivision on a template mesh. 3D Gaussians are defined in face-local coordinates to remain animatable under varying expressions and head motion across multiple detail levels. The hierarchy expands when screen-space signals indicate a lack of detail, allocating resources to important areas. Leveraging importance ranking, ProgressiveAvatars supports incremental loading and rendering, adding new Gaussians as they arrive while preserving previous content, thus achieving smooth quality improvements across varying bandwidths. ProgressiveAvatars enables progressive delivery and progressive rendering under fluctuating network bandwidth and varying compute and memory resources.
Authors: Pietro Bonazzi, Rafael Sutter, Luigi Capogrosso, Mischa Buob, Michele Magno
Abstract: Anomaly detection plays a key role in industrial quality control, where defects must be identified despite the scarcity of labeled faulty samples. Recent self-supervised approaches, such as GLASS, learn normal visual patterns using only defect-free data and have shown strong performance on industrial benchmarks. However, their computational requirements limit deployment on resource-constrained edge platforms. This work introduces TinyGLASS, a lightweight adaptation of the GLASS framework designed for real-time in-sensor anomaly detection on the Sony IMX500 intelligent vision sensor. The proposed architecture replaces the original WideResNet-50 backbone with a compact ResNet-18 and introduces deployment-oriented modifications that enable static graph tracing and INT8 quantization using Sony's Model Compression Toolkit. In addition to evaluating performance on the MVTec-AD benchmark, we investigate robustness to contaminated training data and introduce a custom industrial dataset, named MMS Dataset, for cross-device evaluation. Experimental results show that TinyGLASS achieves 8.7x parameter compression while maintaining competitive detection performance, reaching 94.2% image-level AUROC on MVTec-AD and operating at 20 FPS within the 8 MB memory constraints of the IMX500 platform. System profiling demonstrates low power consumption (4.0 mJ per inference), real-time end-to-end latency (20 FPS), and high energy efficiency (470 GMAC/J). Furthermore, the model maintains stable performance under moderate levels of training data contamination.
Authors: Weiqing Li, Jinyue Guo, Yaqi Wang, Haiyang Xiao, Yuewei Zhang, Guohua Liu, Hao Henry Wang
Abstract: Visual-language models (VLMs) excel at data mappings, but real-world document heterogeneity and unstructuredness disrupt the consistency of cross-modal embeddings. Recent late-interaction methods enhance image-text alignment through multi-vector representations, yet traditional training with limited samples and static strategies cannot adapt to the model's dynamic evolution, causing cross-modal retrieval confusion. To overcome this, we introduce Evo-Retriever, a retrieval framework featuring an LLM-guided curriculum evolution built upon a novel Viewpoint-Pathway collaboration. First, we employ multi-view image alignment to enhance fine-grained matching via multi-scale and multi-directional perspectives. Then, a bidirectional contrastive learning strategy generates "hard queries" and establishes complementary learning paths for visual and textual disambiguation to rebalance supervision. Finally, the model-state summary from the above collaboration is fed into an LLM meta-controller, which adaptively adjusts the training curriculum using expert knowledge to promote the model's evolution. On ViDoRe V2 and MMEB (VisDoc), Evo-Retriever achieves state-of-the-art performance, with nDCG@5 scores of 65.2% and 77.1%.
Authors: Jiaxin Zhang, Junjun Jiang, Haijie Li, Youyu Chen, Kui Jiang, Dave Zhenyu Chen
Abstract: Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging implicit geometric priors from 3D reconstruction models, image-based methods still exhibit a notable performance gap compared to methods using explicit 3D data. We argue that this gap does not arise from insufficient geometric priors, but from a misalignment in the training paradigm: text-dominated fine-tuning fails to activate geometric representations within MLLMs. Existing approaches typically resort to naive feature concatenation and optimize directly for downstream tasks without geometry-specific supervision, leading to suboptimal structural utilization. To address this limitation, we propose GAP-MLLM, a Geometry-Aligned Pre-training paradigm that explicitly activates structural perception before downstream adaptation. Specifically, we introduce a visual-prompted joint task that compels the MLLMs to predict sparse pointmaps alongside semantic labels, thereby enforcing geometric awareness. Furthermore, we design a multi-level progressive fusion module with a token-level gating mechanism, enabling adaptive integration of geometric priors without suppressing semantic reasoning. Extensive experiments demonstrate that GAP-MLLM significantly enhances geometric feature fusion and consistently enhances performance across 3D visual grounding, 3D dense captioning, and 3D video object detection tasks.
Authors: Yicui Shi, Yuhan Chen, Xiangfei Huang, Zhenguo Wang, Wenxuan Yu, Ying Fang
Abstract: Low-light image enhancement aims to restore the visibility of images captured by visual sensors in dim environments by addressing their inherent signal degradations, such as luminance attenuation and structural corruption. Although numerous algorithms attempt to improve image quality, existing methods often cause a severe loss of intrinsic signal priors. To overcome these challenges, we propose a Dual-Stream Transformer Network (DST-Net) based on illumination-agnostic signal prior guidance and multi-scale spatial convolutions. First, to address the loss of critical signal features under low-light conditions, we design a feature extraction module. This module integrates Difference of Gaussians (DoG), LAB color space transformations, and VGG-16 for texture extraction, utilizing decoupled illumination-agnostic features as signal priors to continuously guide the enhancement process. Second, we construct a dual-stream interaction architecture. By employing a cross-modal attention mechanism, the network leverages the extracted priors to dynamically rectify the deteriorated signal representation of the enhanced image, ultimately achieving iterative enhancement through differentiable curve estimation. Furthermore, to overcome the inability of existing methods to preserve fine structures and textures, we propose a Multi-Scale Spatial Fusion Block (MSFB) featuring pseudo-3D and 3D gradient operator convolutions. This module integrates explicit gradient operators to recover high-frequency edges while capturing inter-channel spatial correlations via multi-scale spatial convolutions. Extensive evaluations and ablation studies demonstrate that DST-Net achieves superior performance in subjective visual quality and objective metrics. Specifically, our method achieves a PSNR of 25.64 dB on the LOL dataset. Subsequent validation on the LSRW dataset further confirms its robust cross-scene generalization.
Authors: Hyundo Choi, Junhyeong An, Jinseong Park, Jaewoong Choi
Abstract: Recent advances in one-step generative frameworks, such as flow map models, have significantly improved the efficiency of image generation by learning direct noise-to-data mappings in a single forward pass. However, machine unlearning for ensuring the safety of these powerful generators remains entirely unexplored. Existing diffusion unlearning methods are inherently incompatible with these one-step models, as they rely on a multi-step iterative denoising process. In this work, we propose UOT-Unlearn, a novel plug-and-play class unlearning framework for one-step generative models based on the Unbalanced Optimal Transport (UOT). Our method formulates unlearning as a principled trade-off between a forget cost, which suppresses the target class, and an $f$-divergence penalty, which preserves overall generation fidelity via relaxed marginal constraints. By leveraging UOT, our method enables the probability mass of the forgotten class to be smoothly redistributed to the remaining classes, rather than collapsing into low-quality or noise-like samples. Experimental results on CIFAR-10 and ImageNet-256 demonstrate that our framework achieves superior unlearning success (PUL) and retention quality (u-FID), significantly outperforming baselines.
Authors: Fucai Ke, Zhixi Cai, Boying Li, Long Chen, Beibei Lin, Weiqing Wang, Pari Delir Haghighi, Gholamreza Haffari, Hamid Rezatofighi
Abstract: Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints, yet existing research has largely focused on single-image or temporally dense video settings. In real-world scenarios, reasoning across views requires integrating partial observations without explicit guidance, while collecting large-scale multi-view data with accurate geometric and semantic annotations remains challenging. To address this gap, we leverage physically grounded simulation to construct diverse, high-fidelity 3D scenes with precise per-view metadata, enabling scalable data generation that remains transferable to real-world settings. Based on this engine, we introduce VIEW2SPACE, a multi-dimensional benchmark for sparse multi-view reasoning, together with a scalable, disjoint training split supporting millions of grounded question-answer pairs. Using this benchmark, a comprehensive evaluation of state-of-the-art vision-language and spatial models reveals that multi-view reasoning remains largely unsolved, with most models performing only marginally above random guessing. We further investigate whether training can bridge this gap. Our proposed Grounded Chain-of-Thought with Visual Evidence substantially improves performance under moderate difficulty, and generalizes to real-world data, outperforming existing approaches in cross-dataset evaluation. We further conduct difficulty-aware scaling analyses across model size, data scale, reasoning depth, and visibility constraints, indicating that while geometric perception can benefit from scaling under sufficient visibility, deep compositional reasoning across sparse views remains a fundamental challenge.
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 on generated data is shown with a prediction error 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: Mangyu Kong, Jaewon Lee, Seongwon Lee, Euntai Kim
Abstract: 3D Gaussian Splatting (3DGS) has recently emerged as a powerful scene representation and is increasingly used for visual localization and pose refinement. However, despite its high-quality differentiable rendering, the robustness of 3DGS-based pose refinement remains highly sensitive to both the initial camera pose and the reconstructed geometry. In this work, we take a closer look at these limitations and identify two major sources of uncertainty: (i) pose prior uncertainty, which often arises from regression or retrieval models that output a single deterministic estimate, and (ii) geometric uncertainty, caused by imperfections in the 3DGS reconstruction that propagate errors into PnP solvers. Such uncertainties can distort reprojection geometry and destabilize optimization, even when the rendered appearance still looks plausible. To address these uncertainties, we introduce a relocalization framework that combines Monte Carlo pose sampling with Fisher Information-based PnP optimization. Our method explicitly accounts for both pose and geometric uncertainty and requires no retraining or additional supervision. Across diverse indoor and outdoor benchmarks, our approach consistently improves localization accuracy and significantly increases stability under pose and depth noise.
Authors: Jilles S. van Hulst (Maurice), W. P. M. H. (Maurice), Heemels, Duarte J. Antunes
Abstract: Electron microscopy has enabled many scientific breakthroughs across multiple fields. A key challenge is the tuning of microscope parameters based on images to overcome optical aberrations that deteriorate image quality. This calibration problem is challenging due to the high-dimensional and noisy nature of the diagnostic images, and the fact that optimal parameters cannot be identified from a single image. We tackle the calibration problem for Scanning Transmission Electron Microscopes (STEM) by employing variational autoencoders (VAEs), trained on simulated data, to learn low-dimensional representations of images, whereas most existing methods extract only scalar values. We then simultaneously estimate the model that maps calibration parameters to encoded representations and the optimal calibration parameters using an expectation maximization (EM) approach. This joint estimation explicitly addresses the simulation-to-reality gap inherent in data-driven methods that train on simulated data from a digital twin. We leverage the known symmetry property of the optical system to establish global identifiability of the joint estimation problem, ensuring that a unique optimum exists. We demonstrate that our approach is substantially faster and more consistent than existing methods on a real STEM, achieving a 2x reduction in estimation error while requiring fewer observations. This represents a notable advance in automated STEM calibration and demonstrates the potential of VAEs for information compression in images. Beyond microscopy, the VAE-EM framework applies to inverse problems where simulated training data introduces a reality gap and where non-injective mappings would otherwise prevent unique solutions.
Authors: Mahmoud Ibrahim, Bart Elen, Chang Sun, Gokhan Ertaylan, Michel Dumontier
Abstract: Generative models are increasingly used to augment medical imaging datasets for fairer AI. Yet a key assumption often goes unexamined: that generators themselves produce equally high-quality images across demographic groups. Models trained on imbalanced data can inherit these imbalances, yielding degraded synthesis quality for rare subgroups and struggling with demographic intersections absent from training. We refer to this as the imbalanced generator problem. Existing remedies such as loss reweighting operate at the optimization level and provide limited benefit when training signal is scarce or absent for certain combinations. We propose CompDiff, a hierarchical compositional diffusion framework that addresses this problem at the representation level. A dedicated Hierarchical Conditioner Network (HCN) decomposes demographic conditioning, producing a demographic token concatenated with CLIP embeddings as cross-attention context. This structured factorization encourages parameter sharing across subgroups and supports compositional generalization to rare or unseen demographic intersections. Experiments on chest X-rays (MIMIC-CXR) and fundus images (FairGenMed) show that CompDiff compares favorably against both standard fine-tuning and FairDiffusion across image quality (FID: 64.3 vs. 75.1), subgroup equity (ES-FID), and zero-shot intersectional generalization (up to 21% FID improvement on held-out intersections). Downstream classifiers trained on CompDiff-generated data also show improved AUROC and reduced demographic bias, suggesting that architectural design of demographic conditioning is an important and underexplored factor in fair medical image generation. Code is available at https://anonymous.4open.science/r/CompDiff-6FE6.
Authors: Jiale Song, Jiaxin Luo, Xue-song Tang, Kuangrong Hao, Mingbo Zhao
Abstract: Large Vision-Language Models (LVLMs) achieve strong performance on many multimodal tasks, but object hallucinations severely undermine their reliability. Most existing studies focus on the text modality, attributing hallucinations to overly strong language priors and insufficient visual grounding. In contrast, we observe that abnormal attention patterns within the visual modality can also give rise to hallucinated objects. Building on this observation, we propose Segmentation-based Attention Entropy (SAE), which leverages semantic segmentation to quantify visual attention uncertainty in an object-level semantic space. Based on SAE, we further design a reliability score for hallucination detection and an SAE-guided attention adjustment method that modifies visual attention at inference time to mitigate hallucinations. We evaluate our approach on public benchmarks and in real embodied multimodal scenarios with quadruped robots. Experimental results show that SAE substantially reduces object hallucinations without any additional training cost, thereby enabling more trustworthy LVLM-driven perception and decision-making.
Authors: Florian B\"urger, Martim Dias Gomes, Adri\'an E. Granada, No\'emie Moreau, Katarzyna Bozek
Abstract: Understanding non-genetic determinants of cell fate is critical for developing and improving cancer therapies, as genetically identical cells can exhibit divergent outcomes under the same treatment conditions. In this work, we present a deep learning approach for cell fate prediction from raw long-term live-cell recordings of cancer cell populations under chemotherapeutic treatment. Our Transformer model is trained to predict cell fate directly from raw image sequences, without relying on predefined morphological or molecular features. Beyond classification, we introduce a comprehensive explainability framework for interpreting the temporal and morphological cues guiding the model's predictions. We demonstrate that prediction of cell outcomes is possible based on the video only, our model achieves balanced accuracy of 0.94 and an F1-score of 0.93. Attention and masking experiments further indicate that the signal predictive of the cell fate is not uniquely located in the final frames of a cell trajectory, as reliable predictions are possible up to 10 h before the event. Our analysis reveals distinct temporal distribution of predictive information in the mitotic and apoptotic sequences, as well as the role of cell morphology and p53 signaling in determining cell outcomes. Together, these findings demonstrate that attention-based temporal models enable accurate cell fate prediction while providing biologically interpretable insights into non-genetic determinants of cellular decision-making. The code is available at https://github.com/bozeklab/Cell-Fate-Prediction.
Authors: Jon Hasselgren, Zheng Zeng, Milos Hasan, Jacob Munkberg
Abstract: We present a method for generating physically-based materials for 3D shapes based on a video diffusion transformer architecture. Our method is conditioned on input geometry and a text description, and jointly models multiple material properties (base color, roughness, metallicity, height map) to form physically plausible materials. We further introduce a custom variational auto-encoder which encodes multiple material modalities into a compact latent space, which enables joint generation of multiple modalities without increasing the number of tokens. Our pipeline generates high-quality materials for 3D shapes given a text prompt, compatible with common content creation tools.
Authors: Amirhossein Kazerouni, Maitreya Suin, Tristan Aumentado-Armstrong, Sina Honari, Amanpreet Walia, Iqbal Mohomed, Konstantinos G. Derpanis, Babak Taati, Alex Levinshtein
Abstract: Recent advances in image restoration have enabled high-fidelity recovery of faces from degraded inputs using reference-based face restoration models (Ref-FR). However, such methods focus solely on facial regions, neglecting degradation across the full scene, including body and background, which limits practical usability. Meanwhile, full-scene restorers often ignore degradation cues entirely, leading to underdetermined predictions and visual artifacts. In this work, we propose Face2Scene, a two-stage restoration framework that leverages the face as a perceptual oracle to estimate degradation and guide the restoration of the entire image. Given a degraded image and one or more identity references, we first apply a Ref-FR model to reconstruct high-quality facial details. From the restored-degraded face pair, we extract a face-derived degradation code that captures degradation attributes (e.g., noise, blur, compression), which is then transformed into multi-scale degradation-aware tokens. These tokens condition a diffusion model to restore the full scene in a single step, including the body and background. Extensive experiments demonstrate the superior effectiveness of the proposed method compared to state-of-the-art methods.
Authors: Yong Zou, Haoran Li, Fanxiao Li, Shenyang Wei, Yunyun Dong, Li Tang, Wei Zhou, Renyang Liu
Abstract: Recent progress in image generation models (IGMs) enables high-fidelity content creation but also amplifies risks, including the reproduction of copyrighted content and the generation of offensive content. Image Generation Model Unlearning (IGMU) mitigates these risks by removing harmful concepts without full retraining. Despite growing attention, the robustness under adversarial inputs, particularly image-side threats in black-box settings, remains underexplored. To bridge this gap, we present REFORGE, a black-box red-teaming framework that evaluates IGMU robustness via adversarial image prompts. REFORGE initializes stroke-based images and optimizes perturbations with a cross-attention-guided masking strategy that allocates noise to concept-relevant regions, balancing attack efficacy and visual fidelity. Extensive experiments across representative unlearning tasks and defenses demonstrate that REFORGE significantly improves attack success rate while achieving stronger semantic alignment and higher efficiency than involved baselines. These results expose persistent vulnerabilities in current IGMU methods and highlight the need for robustness-aware unlearning against multi-modal adversarial attacks. Our code is at: https://github.com/Imfatnoily/REFORGE.
Authors: Frederik Beuth, Danny Kowerko
Abstract: Collinearity is a visual perception phenomenon in the human brain that amplifies spatially aligned edges arranged along a straight line. However, it is vague for which purpose humans might have this principle in the real-world, and its utilization in computer vision and engineering applications even is a largely unexplored field. In this work, our goal is to transfer the collinearity principle to computer vision, and we explore the potential usages of this novel principle for computer vision applications. We developed a prototype model to exemplify the principle, then tested it systematically, and benchmarked it in the context of four use cases. Our cases are selected to spawn a broad range of potential applications and scenarios: sketching the combination of collinearity with deep learning (case I and II), using collinearity with saliency models (case II), and as a feature detector (case I). In the first use case, we found that collinearity is able to improve the fault detection of wafers and obtain a performance increase by a factor 1.24 via collinearity (decrease of the error rate from 6.5% to 5.26%). In the second use case, we test the defect recognition in nanotechnology materials and achieve a performance increase by 3.2x via collinearity (deep learning, error from 21.65% to 6.64%), and also explore saliency models. As third experiment, we cover occlusions; while as fourth experiment, we test ImageNet and observe that it might not be very beneficial for ImageNet. Therefore, we can assemble a list of scenarios for which collinearity is beneficial (wafers, nanotechnology, occlusions), and for what is not beneficial (ImageNet). Hence, we infer collinearity might be suitable for industry applications as it helps if the image structures of interest are man-made because they often consist of lines. Our work provides another tool for CV, hope to capture the power of human processing.
Authors: Fangjing Li, Zhihai Wang, Xinxin Ding, Haiyang Liu, Ronghua Gao, Rong Wang, Yao Zhu, Ming Jin
Abstract: Mounting posture is an important visual indicator of estrus in dairy cattle. However, achieving reliable mounting pose estimation in real-world environments remains challenging due to cluttered backgrounds and frequent inter-animal occlusion. We present FSMC-Pose, a top-down framework that integrates a lightweight frequency-spatial fusion backbone, CattleMountNet, and a multiscale self-calibration head, SC2Head. Specifically, we design two algorithmic components for CattleMountNet: the Spatial Frequency Enhancement Block (SFEBlock) and the Receptive Aggregation Block (RABlock). SFEBlock separates cattle from cluttered backgrounds, while RABlock captures multiscale contextual information. The Spatial-Channel Self-Calibration Head (SC2Head) attends to spatial and channel dependencies and introduces a self-calibration branch to mitigate structural misalignment under inter-animal overlap. We construct a mounting dataset, MOUNT-Cattle, covering 1176 mounting instances, which follows the COCO format and supports drop-in training across pose estimation models. Using a comprehensive dataset that combines MOUNT-Cattle with the public NWAFU-Cattle dataset, FSMC-Pose achieves higher accuracy than strong baselines, with markedly lower computational and parameter costs, while maintaining real-time inference on commodity GPUs. Extensive experiments and qualitative analyses show that FSMC-Pose effectively captures and estimates cattle mounting pose in complex and cluttered environments. Dataset and code are available at https://github.com/elianafang/FSMC-Pose.
Authors: Weijie Qiu, Dai Guan, Junxin Wang, Zhihang Li, Yongbo Gai, Mengyu Zhou, Erchao Zhao, Xiaoxi Jiang, Guanjun Jiang
Abstract: Generative reward models (GRMs) for vision-language models (VLMs) often evaluate outputs via a three-stage pipeline: rubric generation, criterion-based scoring, and a final verdict. However, the intermediate rubric is rarely optimized directly. Prior work typically either treats rubrics as incidental or relies on expensive LLM-as-judge checks that provide no differentiable signal and limited training-time guidance. We propose Proxy-GRM, which introduces proxy-guided rubric verification into Reinforcement Learning (RL) to explicitly enhance rubric quality. Concretely, we train lightweight proxy agents (Proxy-SFT and Proxy-RL) that take a candidate rubric together with the original query and preference pair, and then predict the preference ordering using only the rubric as evidence. The proxy's prediction accuracy serves as a rubric-quality reward, incentivizing the model to produce rubrics that are internally consistent and transferable. With ~50k data samples, Proxy-GRM reaches state-of-the-art results on the VL-Reward Bench, Multimodal Reward Bench, and MM-RLHF-Reward Bench, outperforming the methods trained on four times the data. Ablations show Proxy-SFT is a stronger verifier than Proxy-RL, and implicit reward aggregation performs best. Crucially, the learned rubrics transfer to unseen evaluators, improving reward accuracy at test time without additional training. Our code is available at https://github.com/Qwen-Applications/Proxy-GRM.
Authors: Weiqin Jiao, Hao Cheng, George Vosselman, Claudio Persello
Abstract: We tackle the problem of generating a complete vector map representation from aerial imagery in a single run: producing polygons for all land-cover classes with shared boundaries and without gaps or overlaps. Existing polygonization methods are typically class-specific; extending them to multiple classes via per-class runs commonly leads to topological inconsistencies, such as duplicated edges, gaps, and overlaps. We formalize this new task as All-Class Polygonal Vectorization (ACPV) and release the first public benchmark, Deventer-512, with standardized metrics jointly evaluating semantic fidelity, geometric accuracy, vertex efficiency, per-class topological fidelity and global topological consistency. To realize ACPV, we propose ACPV-Net, a unified framework introducing a novel Semantically Supervised Conditioning (SSC) mechanism coupling semantic perception with geometric primitive generation, along with a topological reconstruction that enforces shared-edge consistency by design. While enforcing such strict topological constraints, ACPV-Net surpasses all class-specific baselines in polygon quality across classes on Deventer-512. It also applies to single-class polygonal vectorization without any architectural modification, achieving the best-reported results on WHU-Building. Data, code, and models will be released at: https://github.com/HeinzJiao/ACPV-Net.
Authors: Qiang He, Wentian Qu, Jiajia Dai, Changsong Lei, Shaofeng Wang, Feifei Zuo, Yajie Wang, Yaqian Liang, Xiaoming Deng, Cuixia Ma, Yong-Jin Liu, Hongan Wang
Abstract: Accurate semantic segmentation of 3D dental models is essential for digital dentistry applications such as orthodontics and dental implants. However, due to complex tooth arrangements and similarities in shape among adjacent teeth, existing methods struggle with accurate segmentation, because they often focus on local geometry while neglecting global contextual information. To address this, we propose TCATSeg, a novel framework that combines local geometric features with global semantic context. We introduce a set of sparse yet physically meaningful superpoints to capture global semantic relationships and enhance segmentation accuracy. Additionally, we present a new dataset of 400 dental models, including pre-orthodontic samples, to evaluate the generalization of our method. Extensive experiments demonstrate that TCATSeg outperforms state-of-the-art approaches.
Authors: Redwan Sony, Anil K Jain, Ross Arun
Abstract: Multimodal Large Language Models (MLLMs) have recently been proposed as a means to generate natural-language explanations for face recognition decisions. While such explanations facilitate human interpretability, their reliability on unconstrained face images remains underexplored. In this work, we systematically analyze MLLM-generated explanations for the unconstrained face verification task on the challenging IJB-S dataset, with a particular focus on extreme pose variation and surveillance imagery. Our results show that even when MLLMs produce correct verification decisions, the accompanying explanations frequently rely on non-verifiable or hallucinated facial attributes that are not supported by visual evidence. We further study the effect of incorporating information from traditional face recognition systems, viz., scores and decisions, alongside the input images. Although such information improves categorical verification performance, it does not consistently lead to faithful explanations. To evaluate the explanations beyond decision accuracy, we introduce a likelihood-ratio-based framework that measures the evidential strength of textual explanations. Our findings highlight fundamental limitations of current MLLMs for explainable face recognition and underscore the need for a principled evaluation of reliable and trustworthy explanations in biometric applications. Code is available at https://github.com/redwankarimsony/LR-MLLMFR-Explainability.
URLs: https://github.com/redwankarimsony/LR-MLLMFR-Explainability.
Authors: Zhenqi He, Lin Li, Long Chen
Abstract: Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by recombining primitives learned from seen pairs. Recent CZSL methods built on vision-language models (VLMs) typically adopt parameter-efficient fine-tuning (PEFT). They apply visual disentanglers for decomposition and manipulate token-level prompts or prefixes to encode compositions. However, such PEFT-based designs suffer from two fundamental limitations: (1) Implicit Composition Construction, where composition is realized only via token concatenation or branch-wise prompt tuning rather than an explicit operation in the embedding space; (2) Remained Feature Entanglement, where imperfect disentanglement leaves attribute, object, and composition features mutually contaminated. Together, these issues limit the generalization ability of current CZSL models. In this paper, we are the first to systematically study flow matching for CZSL and introduce FlowComposer, a model-agnostic framework that learns two primitive flows to transport visual features toward attribute and object text embeddings, and a learnable Composer that explicitly fuses their velocity fields into a composition flow. To exploit the inevitable residual entanglement, we further devise a leakage-guided augmentation scheme that reuses leaked features as auxiliary signals. We thoroughly evaluate FlowComposer on three public CZSL benchmarks by integrating it as a plug-and-play component into various baselines, consistently achieving significant improvements.
Authors: Melissa Schween, Mathis Kruse, Bodo Rosenhahn
Abstract: We propose Bijective Universal Scene-Specific Anomalous Relationship Detection (BUSSARD), a normalizing flow-based model for detecting anomalous relations in scene graphs, generated from images. Our work follows a multimodal approach, embedding object and relationship tokens from scene graphs with a language model to leverage semantic knowledge from the real world. A normalizing flow model is used to learn bijective transformations that map object-relation-object triplets from scene graphs to a simple base distribution (typically Gaussian), allowing anomaly detection through likelihood estimation. We evaluate our approach on the SARD dataset containing office and dining room scenes. Our method achieves around 10% better AUROC results compared to the current state-of-the-art model, while simultaneously being five times faster. Through ablation studies, we demonstrate superior robustness and universality, particularly regarding the use of synonyms, with our model maintaining stable performance while the baseline shows 17.5% deviation. This work demonstrates the strong potential of learning-based methods for relationship anomaly detection in scene graphs. Our code is available at https://github.com/mschween/BUSSARD .
Authors: Shihao Zhu, Ziheng Ouyang, Yijia Kang, Qilong Wang, Mi Zhou, Bo Li, Ming-Ming Cheng, Qibin Hou
Abstract: Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details.We introduce StyleExpert, a semantic-aware framework based on the Mixture of Experts (MoE). Our framework employs a unified style encoder, trained on our large-scale dataset of content-style-stylized triplets, to embed diverse styles into a consistent latent space. This embedding is then used to condition a similarity-aware gating mechanism, which dynamically routes styles to specialized experts within the MoE architecture. Leveraging this MoE architecture, our method adeptly handles diverse styles spanning multiple semantic levels, from shallow textures to deep semantics. Extensive experiments show that StyleExpert outperforms existing approaches in preserving semantics and material details, while generalizing to unseen styles. Our code and collected images are available at the project page: https://hh-lg.github.io/StyleExpert-Page/.
Authors: Chenchang Liu, Felix Fornoff, Annika Grasreiner, Patrick Maeder, Henri Greil, Marco Seeland
Abstract: Monitoring cavity-nesting wild bees and wasps is vital for biodiversity research and conservation. Layer trap nests (LTNs) are emerging as a valuable tool to study the abundance and species richness of these insects, offering insights into their nesting activities and ecological needs. However, manually evaluating LTNs to detect and classify brood cells is labor-intensive and time-consuming. To address this, we propose a deep learning based approach for efficient brood cell detection and classification in LTNs. LTNs present additional challenges due to densely packed brood cells, leading to a high labeling effort per image. Moreover, we observe a significant imbalance in class distribution, with common species having notably more occurrences than rare species. Comprehensive labeling of common species is time-consuming and exacerbates data imbalance, while partial labeling introduces data incompleteness which degrades model performance. To reduce labeling effort and mitigate the impact of unlabeled data, we introduce a novel Constrained False Positive Loss (CFPL) strategy. CFPL dynamically masks predictions from unlabeled data, preventing them from interfering with the classification loss during training. We evaluate our approach on a dataset of 712 LTN images collected over one season, covering 28 fine-grained classes describing the taxonomy and status of brood cells. To minimize labeling effort, we limit the training set to a maximum of 300 labels per class. Experimental results demonstrate that deep learning can be effectively used to detect brood cells in LTNs. Our CFPL method further improves performance and balances model accuracy and labeling effort while also mitigating class imbalance.
Authors: Md Jahidul Islam
Abstract: Adapting large-scale Vision-Language Models (VLMs) like CLIP to downstream tasks often suffers from a "one-size-fits-all" architectural approach, where visual and textual tokens are processed uniformly by wide, generic adapters. We argue that this homogeneity ignores the distinct structural nature of the modalities -- spatial locality in images versus semantic density in text. To address this, we propose HeBA (Heterogeneous Bottleneck Adapter), a unified architectural framework that introduces modality-specific structural inductive biases. HeBA departs from conventional designs through three key architectural innovations: (1) Heterogeneity: It processes visual tokens via 2D depthwise-separable convolutions to preserve spatial correlations, while distinctively processing text tokens via dense linear projections to capture semantic relationships; (2) Bottleneck Regularization: Unlike standard expanding adapters, HeBA employs a compression bottleneck (D -> D/4) that explicitly forces the model to learn compact, robust features and acts as a structural regularizer; and (3) Active Gradient Initialization: We challenge the restrictive zero-initialization paradigm, utilizing a Kaiming initialization strategy that ensures sufficient initial gradient flow to accelerate convergence without compromising the frozen backbone's pre-trained knowledge. Extensive experiments demonstrate that HeBA's architecturally specialized design achieves superior stability and accuracy, establishing a new state-of-the-art on 11 few-shot benchmarks. Code is available at https://github.com/Jahid12012021/VLM-HeBA.
Authors: Taiqin Chen, Yifeng Wang, Xiaochen Feng, Zhilin Zhu, Hao Sha, Yingjian Li, Yongbing Zhang
Abstract: While hyperspectral images (HSI) benefit from numerous spectral channels that provide rich information for classification, the increased dimensionality and sensor variability make them more sensitive to distributional discrepancies across domains, which in turn can affect classification performance. To tackle this issue, hyperspectral single-source domain generalization (SDG) typically employs data augmentation to simulate potential domain shifts and enhance model robustness under the condition of single-source domain training data availability. However, blind augmentation may produce samples misaligned with real-world scenarios, while excessive emphasis on realism can suppress diversity, highlighting a tradeoff between realism and diversity that limits generalization to target domains. To address this challenge, we propose a spectral property-driven data augmentation (SPDDA) that explicitly accounts for the inherent properties of HSI, namely the device-dependent variation in the number of spectral channels and the mixing of adjacent channels. Specifically, SPDDA employs a spectral diversity module that resamples data from the source domain along the spectral dimension to generate samples with varying spectral channels, and constructs a channel-wise adaptive spectral mixer by modeling inter-channel similarity, thereby avoiding fixed augmentation patterns. To further enhance the realism of the augmented samples, we propose a spatial-spectral co-optimization mechanism, which jointly optimizes a spatial fidelity constraint and a spectral continuity self-constraint. Moreover, the weight of the spectral self-constraint is adaptively adjusted based on the spatial counterpart, thus preventing over-smoothing in the spectral dimension and preserving spatial structure. Extensive experiments conducted on three remote sensing benchmarks demonstrate that SPDDA outperforms state-of-the-art methods.
Authors: Jiawei Mao, Hardy Chen, Haoqin Tu, Yuhan Wang, Letian Zhang, Zeyu Zheng, Huaxiu Yao, Zirui Wang, Cihang Xie, Yuyin Zhou
Abstract: Large vision-language models (LVLMs) have become increasingly strong but remain prone to hallucinations in multimodal tasks, which significantly narrows their deployment. As training these LVLMs to avoid hallucinations becomes prohibitively expensive for larger models, training-free methods offer a cheap and flexible solution to this problem, yet existing approaches based on decoding or tool use often bring limited gains and/or weak interpretability. We propose Kestrel, a training-free framework for LVLM hallucination mitigation that combines an explicit visual-grounding agent with evidence-verified self-refinement mechanism. In detail, Kestrel first collects explicit visual evidence and converts tool outputs into reusable and structured textual evidence. Second, to take full advantage of these evidence, Kestrel verifies them via an LVLM judge for evidence checking, then iteratively self-refine answers based on verified evidence to reduce the risk of over-correction. Extensive experiments show that Kestrel improves performance over strong baselines across hallucination benchmarks (e.g., average +3.31% on POPE and +28.34 on MME-Hallucination with Qwen3-VL), while providing transparent verification traces for hallucination diagnosis and analysis -- e.g., both the integrated self-refinement module and grounding agent contributing an average +2.0% gain on POPE.
Authors: Tianyuan Yuan, Zibin Dong, Yicheng Liu, Hang Zhao
Abstract: World Action Models (WAMs) have emerged as a promising alternative to Vision-Language-Action (VLA) models for embodied control because they explicitly model how visual observations may evolve under action. Most existing WAMs follow an imagine-then-execute paradigm, incurring substantial test-time latency from iterative video denoising, yet it remains unclear whether explicit future imagination is actually necessary for strong action performance. In this paper, we ask whether WAMs need explicit future imagination at test time, or whether their benefit comes primarily from video modeling during training. We disentangle the role of video modeling during training from explicit future generation during inference by proposing \textbf{Fast-WAM}, a WAM architecture that retains video co-training during training but skips future prediction at test time. We further instantiate several Fast-WAM variants to enable a controlled comparison of these two factors. Across these variants, we find that Fast-WAM remains competitive with imagine-then-execute variants, while removing video co-training causes a much larger performance drop. Empirically, Fast-WAM achieves competitive results with state-of-the-art methods both on simulation benchmarks (LIBERO and RoboTwin) and real-world tasks, without embodied pretraining. It runs in real time with 190ms latency, over 4$\times$ faster than existing imagine-then-execute WAMs. These results suggest that the main value of video prediction in WAMs may lie in improving world representations during training rather than generating future observations at test time. Project page: https://yuantianyuan01.github.io/FastWAM/
Authors: Ruishan Guo, Ciyu Ruan, Haoyang Wang, Zihang Gong, Jingao Xu, Xinlei Chen
Abstract: Estimating dense 2D optical flow and 3D scene flow is essential for dynamic scene understanding. Recent work combines images, LiDAR, and event data to jointly predict 2D and 3D motion, yet most approaches operate in separate heterogeneous feature spaces. Without a shared latent space that all modalities can align to, these systems rely on multiple modality-specific blocks, leaving cross-sensor mismatches unresolved and making fusion unnecessarily complex.Event cameras naturally provide a spatiotemporal edge signal, which we can treat as an intrinsic edge field to anchor a unified latent representation, termed the Event Edge Space. Building on this idea, we introduce $x^2$-Fusion, which reframes multimodal fusion as representation unification: event-derived spatiotemporal edges define an edge-centric homogeneous space, and image and LiDAR features are explicitly aligned in this shared representation.Within this space, we perform reliability-aware adaptive fusion to estimate modality reliability and emphasize stable cues under degradation. We further employ cross-dimension contrast learning to tightly couple 2D optical flow with 3D scene flow. Extensive experiments on both synthetic and real benchmarks show that $x^2$-Fusion achieves state-of-the-art accuracy under standard conditions and delivers substantial improvements in challenging scenarios.
Authors: Aojie Yuan
Abstract: Medical image retrieval (MIR) is a critical component of computer-aided diagnosis, yet existing systems suffer from three persistent limitations: uniform feature encoding that fails to account for the varying clinical importance of anatomical structures, ambiguous similarity metrics based on coarse classification labels, and an exclusive focus on global image similarity that cannot meet the clinical demand for fine-grained region-specific retrieval. We propose HMAR (Hierarchical Modality-Aware Expert and Dynamic Routing), an adaptive retrieval framework built on a Mixture-of-Experts (MoE) architecture. HMAR employs a dual-expert mechanism: Expert0 extracts global features for holistic similarity matching, while Expert1 learns position-invariant local representations for precise lesion-region retrieval. A two-stage contrastive learning strategy eliminates the need for expensive bounding-box annotations, and a sliding-window matching algorithm enables dense local comparison at inference time. Hash codes are generated via Kolmogorov-Arnold Network (KAN) layers for efficient Hamming-distance search. Experiments on the RadioImageNet-CT dataset (16 clinical patterns, 29,903 images) show that HMAR achieves mean Average Precision (mAP) of 0.711 and 0.724 for 64-bit and 128-bit hash codes, improving over the state-of-the-art ACIR method by 0.7% and 1.1%, respectively.
Authors: Sainan Liu, Tz-Ying Wu, Hector A Valdez, Subarna Tripathi
Abstract: We present Search2Motion, a training-free framework for object-level motion editing in image-to-video generation. Unlike prior methods requiring trajectories, bounding boxes, masks, or motion fields, Search2Motion adopts target-frame-based control, leveraging first-last-frame motion priors to realize object relocation while preserving scene stability without fine-tuning. Reliable target-frame construction is achieved through semantic-guided object insertion and robust background inpainting. We further show that early-step self-attention maps predict object and camera dynamics, offering interpretable user feedback and motivating ACE-Seed (Attention Consensus for Early-step Seed selection), a lightweight search strategy that improves motion fidelity without look-ahead sampling or external evaluators. Noting that existing benchmarks conflate object and camera motion, we introduce S2M-DAVIS and S2M-OMB for stable-camera, object-only evaluation, alongside FLF2V-obj metrics that isolate object artifacts without requiring ground-truth trajectories. Search2Motion consistently outperforms baselines on FLF2V-obj and VBench.
Authors: Hai Nguyen, Hieu Dao, Hung Nguyen, Nam Vu, Cong Tran
Abstract: This study presents high-throughput, real-time multi-agent affective computing framework designed to enhance classroom learning through emotional state monitoring. As large classroom sizes and limited teacher student interaction increasingly challenge educators, there is a growing need for scalable, data-driven tools capable of capturing students' emotional and engagement patterns in real time. The system was evaluated using the Classroom Emotion Dataset, consisting of 1,500 labeled images and 300 classroom detection videos. Tailored for IoT devices, the system addresses load balancing and latency challenges through efficient real-time processing. Field testing was conducted across three educational institutions in a large metropolitan area: a primary school (hereafter school A), a secondary school (school B), and a high school (school C). The system demonstrated robust performance, detecting up to 50 faces at 25 FPS and achieving 88% overall accuracy in classifying classroom engagement states. Implementation results showed positive outcomes, with favorable feedback from students, teachers, and parents regarding improved classroom interaction and teaching adaptation. Key contributions of this research include establishing a practical, IoT-based framework for emotion-aware learning environments and introducing the 'Classroom Emotion Dataset' to facilitate further validation and research.
Authors: Lukas H\"ollein, Matthias Nie{\ss}ner
Abstract: Video diffusion models generate high-quality and diverse worlds; however, individual frames often lack 3D consistency across the output sequence, which makes the reconstruction of 3D worlds difficult. To this end, we propose a new method that handles these inconsistencies by non-rigidly aligning the video frames into a globally-consistent coordinate frame that produces sharp and detailed pointcloud reconstructions. First, a geometric foundation model lifts each frame into a pixel-wise 3D pointcloud, which contains unaligned surfaces due to these inconsistencies. We then propose a tailored non-rigid iterative frame-to-model ICP to obtain an initial alignment across all frames, followed by a global optimization that further sharpens the pointcloud. Finally, we leverage this pointcloud as initialization for 3D reconstruction and propose a novel inverse deformation rendering loss to create high quality and explorable 3D environments from inconsistent views. We demonstrate that our 3D scenes achieve higher quality than baselines, effectively turning video models into 3D-consistent world generators.
Authors: Guangzhi Xiong, Sanchit Sinha, Zhenghao He, Aidong Zhang
Abstract: Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal reasoning tasks, but they often struggle to disentangle fine-grained visual attributes and reason about underlying causal relationships. In-context learning (ICL) offers a promising avenue for VLMs to adapt to new tasks, but its effectiveness critically depends on the selection of demonstration examples. Existing retrieval-augmented approaches typically rely on passive similarity-based retrieval, which tends to select correlated but non-causal examples, amplifying spurious associations and limiting model robustness. We introduce CIRCLES (Composed Image Retrieval for Causal Learning Example Selection), a novel framework that actively constructs demonstration sets by retrieving counterfactual-style examples through targeted, attribute-guided composed image retrieval. By incorporating counterfactual-style examples, CIRCLES enables VLMs to implicitly reason about the causal relations between attributes and outcomes, moving beyond superficial correlations and fostering more robust and grounded reasoning. Comprehensive experiments on four diverse datasets demonstrate that CIRCLES consistently outperforms existing methods across multiple architectures, especially on small-scale models, with pronounced gains under information scarcity. Furthermore, CIRCLES retrieves more diverse and causally informative examples, providing qualitative insights into how models leverage in-context demonstrations for improved reasoning. Our code is available at https://github.com/gzxiong/CIRCLES.
Authors: Zhen Xu, Jinsu Yoo, Cristian Bautista, Zanming Huang, Tai-Yu Pan, Zhenzhen Liu, Katie Z Luo, Mark Campbell, Bharath Hariharan, Wei-Lun Chao
Abstract: Building robust 3D perception for self-driving still relies heavily on large-scale data collection and manual annotation, yet this paradigm becomes impractical as deployment expands across diverse cities and regions. Meanwhile, modern cities are increasingly instrumented with roadside units (RSUs), static sensors deployed along roads and at intersections to monitor traffic. This raises a natural question: can the city itself help train the vehicle? We propose infrastructure-taught, label-free 3D perception, a paradigm in which RSUs act as stationary, unsupervised teachers for ego vehicles. Leveraging their fixed viewpoints and repeated observations, RSUs learn local 3D detectors from unlabeled data and broadcast predictions to passing vehicles, which are aggregated as pseudo-label supervision for training a standalone ego detector. The resulting model requires no infrastructure or communication at test time. We instantiate this idea as a fully label-free three-stage pipeline and conduct a concept-and-feasibility study in a CARLA-based multi-agent environment. With CenterPoint, our pipeline achieves 82.3% AP for detecting vehicles, compared to a fully supervised ego upper bound of 94.4%. We further systematically analyze each stage, evaluate its scalability, and demonstrate complementarity with existing ego-centric label-free methods. Together, these results suggest that city infrastructure itself can potentially provide a scalable supervisory signal for autonomous vehicles, positioning infrastructure-taught learning as a promising orthogonal paradigm for reducing annotation cost in 3D perception.
Authors: Chenggong Hu, Yi Wang, Mengqi Xue, Haofei Zhang, Jie Song, Li Sun
Abstract: Textile pattern generation (TPG) aims to synthesize fine-grained textile pattern images based on given clothing images. Although previous studies have not explicitly investigated TPG, existing image-to-image models appear to be natural candidates for this task. However, when applied directly, these methods often produce unfaithful results, failing to preserve fine-grained details due to feature confusion between complex textile patterns and the inherent non-rigid texture distortions in clothing images. In this paper, we propose a novel method, SLDDM-TPG, for faithful and high-fidelity TPG. Our method consists of two stages: (1) a latent disentangled network (LDN) that resolves feature confusion in clothing representations and constructs a multi-dimensional, independent clothing feature space; and (2) a semi-supervised latent diffusion model (S-LDM), which receives guidance signals from LDN and generates faithful results through semi-supervised diffusion training, combined with our designed fine-grained alignment strategy. Extensive evaluations show that SLDDM-TPG reduces FID by 4.1 and improves SSIM by up to 0.116 on our CTP-HD dataset, and also demonstrate good generalization on the VITON-HD dataset.
Authors: Sreekar Chigurupati, Eleftherios Garyfallidis
Abstract: We present SuCor, a method for correcting susceptibility induced geometric distortions in echo planar imaging (EPI) using optimal transport (OT) along the phase encoding direction. Given a pair of reversed phase encoding EPI volumes, we model each column of the distortion field as a Wasserstein-2 barycentric displacement between the opposing-polarity intensity profiles. Regularization is performed in the spectral domain using a bending-energy penalty whose strength is selected automatically via the Morozov discrepancy principle, requiring no manual tuning. On a human connectome project (HCP) dataset with left-right/right-left b0 EPI pairs and a co-registered T1 structural reference, SuCor achieves a mean volumetric mutual information of 0.341 with the T1 image, compared to 0.317 for FSL TOPUP, while running in approximately 12 seconds on a single CPU core.
Authors: Jinsheng Wei, Xiguang Zhang, Zheng Shi, Guanming Lu
Abstract: Recongnizing true emotions from masked expressions is extremely challenging due to deliberate concealment. Existing paradigms recognize true emotions from masked-expression clips that contain onsetframes just starting to disguise. However, this paradigm may not reflect the actual disguised state, as the onsetframe leaks the true emotional information without reaching a stable disguise state. Thus, this paper introduces a novel apexframe-based paradigm that classifies true emotions from the apexframe with a stable disguised state. Furthermore, this paper proposes a novel dual stream independence decoupling framework that decouples true and disguised emotion features, avoiding the interference of disguised emotions on true emotions. For efficient decoupling, we design a decoupling loss group, comprising two classification losses that learn true emotion and disguised expression features, respectively, and a Hilbert-Schmidt Independence loss that enhances the independence of two features. Experiments demonstrate that the apexframe-based paradigm is challenging, and the proposed decouple framework improves recogntion performances.
Authors: Qiaosi Yi, Shuai Li, Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang, Lei Zhang
Abstract: Recently, reinforcement learning (RL) has been employed for improving generative image super-resolution (ISR) performance. However, the current efforts are focused on multi-step generative ISR, while one-step generative ISR remains underexplored due to its limited stochasticity. In addition, RL methods such as Direct Preference Optimization (DPO) require the generation of positive and negative sample pairs offline, leading to a limited number of samples, while Group Relative Policy Optimization (GRPO) only calculates the likelihood of the entire image, ignoring local details that are crucial for ISR. In this paper, we propose Group Direct Preference Optimization (GDPO), a novel approach to integrate RL into one-step generative ISR model training. First, we introduce a noise-aware one-step diffusion model that can generate diverse ISR outputs. To prevent performance degradation caused by noise injection, we introduce an unequal-timestep strategy to decouple the timestep of noise addition from that of diffusion. We then present the GDPO strategy, which integrates the principle of GRPO into DPO, to calculate the group-relative advantage of each online generated sample for model optimization. Meanwhile, an attribute-aware reward function is designed to dynamically evaluate the score of each sample based on its statistics of smooth and texture areas. Experiments demonstrate the effectiveness of GDPO in enhancing the performance of one-step generative ISR models. Code: https://github.com/Joyies/GDPO.
Authors: Huimin Xiong, Zijie Meng, Tianxiang Hu, Chenyi Zhou, Yang Feng, Zuozhu Liu
Abstract: 3D intraoral scans (IOS) are increasingly adopted in routine dentistry due to abundant geometric evidence, and unified multi-disease diagnosis is desirable for clinical documentation and communication. While recent works introduce dental vision-language models (VLMs) to enable unified diagnosis and report generation on 2D images or multi-view images rendered from IOS, they do not fully leverage native 3D geometry. Such work is necessary and also challenging, due to: (i) heterogeneous scan forms and the complex IOS topology, (ii) multi-disease co-occurrence with class imbalance and fine-grained morphological ambiguity, (iii) limited paired 3D IOS-text data. Thus, we present IOSVLM, an end-to-end 3D VLM that represents scans as point clouds and follows a 3D encoder-projector-LLM design for unified diagnosis and generative visual question-answering (VQA), together with IOSVQA, a large-scale multi-source IOS diagnosis VQA dataset comprising 19,002 cases and 249,055 VQA pairs over 23 oral diseases and heterogeneous scan types. To address the distribution gap between color-free IOS data and color-dependent 3D pre-training, we propose a geometry-to-chromatic proxy that stabilizes fine-grained geometric perception and cross-modal alignment. A two-stage curriculum training strategy further enhances robustness. IOSVLM consistently outperforms strong baselines, achieving gains of at least +9.58% macro accuracy and +1.46% macro F1, indicating the effectiveness of direct 3D geometry modeling for IOS-based diagnosis.
Authors: Han Lin, Xichen Pan, Zun Wang, Yue Zhang, Chu Wang, Jaemin Cho, Mohit Bansal
Abstract: Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained autoencoders. However, standard pixel-space diffusion models receive relatively weak semantic supervision and are not explicitly designed to capture high-level visual structure. Recent representation-alignment methods (e.g., REPA) suggest that pretrained visual features can substantially improve diffusion training, and visual co-denoising has emerged as a promising direction for incorporating such features into the generative process. However, existing co-denoising approaches often entangle multiple design choices, making it unclear which design choices are truly essential. Therefore, we present V-Co, a systematic study of visual co-denoising in a unified JiT-based framework. This controlled setting allows us to isolate the ingredients that make visual co-denoising effective. Our study reveals four key ingredients for effective visual co-denoising. First, preserving feature-specific computation while enabling flexible cross-stream interaction motivates a fully dual-stream architecture. Second, effective classifier-free guidance (CFG) requires a structurally defined unconditional prediction. Third, stronger semantic supervision is best provided by a perceptual-drifting hybrid loss. Fourth, stable co-denoising further requires proper cross-stream calibration, which we realize through RMS-based feature rescaling. Together, these findings yield a simple recipe for visual co-denoising. Experiments on ImageNet-256 show that, at comparable model sizes, V-Co outperforms the underlying pixel-space diffusion baseline and strong prior pixel-diffusion methods while using fewer training epochs, offering practical guidance for future representation-aligned generative models.
Authors: Muhammad Aamir, Naoya Muramatsu, Sangyun Shin, Matthew Wijers, Jiaxing Jhong, Xinyu Hou, Amir Patel, Andrew Markham
Abstract: Depth estimation and 3D reconstruction have been extensively studied as core topics in computer vision. Starting from rigid objects with relatively simple geometric shapes, such as vehicles, the research has expanded to address general objects, including challenging deformable objects, such as humans and animals. However, for the animal, in particular, the majority of existing models are trained based on datasets without metric scale, which can help validate image-only models. To address this limitation, we present WildDepth, a multimodal dataset and benchmark suite for depth estimation, behavior detection, and 3D reconstruction from diverse categories of animals ranging from domestic to wild environments with synchronized RGB and LiDAR. Experimental results show that the use of multi-modal data improves depth reliability by up to 10% RMSE, while RGB-LiDAR fusion enhances 3D reconstruction fidelity by 12% in Chamfer distance. By releasing WildDepth and its benchmarks, we aim to foster robust multimodal perception systems that generalize across domains.
Authors: Sourya Saha (City University of New York), Saptarshi Debroy (City University of New York)
Abstract: Immersive extended reality (XR) applications introduce latency-critical workloads that must satisfy stringent real-time responsiveness while operating on energy- and battery-constrained devices, making execution placement between end devices and nearby edge servers a fundamental systems challenge. Existing approaches to adaptive execution and computation offloading typically optimize average performance metrics and do not fully capture the sustained interaction between real-time latency requirements and device battery lifetime in closed-loop XR workloads. In this paper, we present a battery-aware execution management framework for edge-assisted XR systems that jointly considers execution placement, workload quality, latency requirements, and battery dynamics. We design an online decision mechanism based on a lightweight deep reinforcement learning policy that continuously adapts execution decisions under dynamic network conditions while maintaining high motion-to-photon latency compliance. Experimental results show that the proposed approach extends the projected device battery lifetime by up to 163% compared to latency-optimal local execution while maintaining over 90% motion-to-photon latency compliance under stable network conditions. Such compliance does not fall below 80% even under significantly limited network bandwidth availability, thereby demonstrating the effectiveness of explicitly managing latency-energy trade-offs in immersive XR systems.
Authors: Felix Kr\"ober, Genc Hoxha, Ribana Roscher
Abstract: Label noise in the sense of incorrect labels is present in many real-world data sets and is known to severely limit the generalizability of deep learning models. In the field of remote sensing, however, automated treatment of label noise in data sets has received little attention to date. In particular, there is a lack of systematic analysis of the performance of data-centric methods that not only cope with label noise but also explicitly identify and isolate noisy labels. In this paper, we examine three such methods and evaluate their behavior under different label noise assumptions. To do this, we inject different types of label noise with noise levels ranging from 10 to 70% into two benchmark data sets, followed by an analysis of how well the selected methods filter the label noise and how this affects task performances. With our analyses, we clearly prove the value of data-centric methods for both parts - label noise identification and task performance improvements. Our analyses provide insights into which method is the best choice depending on the setting and objective. Finally, we show in which areas there is still a need for research in the transfer of data-centric label noise methods to remote sensing data. As such, our work is a step forward in bridging the methodological establishment of data-centric label noise methods and their usage in practical settings in the remote sensing domain.
Authors: Moritz Pawlowsky, Antonis Vamvakeros, Alexander Weiss, Anja Bielefeld, Samuel J. Cooper, Ronan Docherty
Abstract: Vision transformers (ViTs) - especially feature foundation models like DINOv2 - learn rich representations useful for many downstream tasks. However, architectural choices (such as positional encoding) can lead to these models displaying positional biases and artefacts independent of semantic content. This makes zero-shot adaption difficult in fields like material science, where images are often cross-sections of homogeneous microstructure (i.e. having no preferred direction). In this work, we investigate the positional bias in ViTs via linear probing, finding it present across a range of objectives and positional encodings, and subsequently reduce it by finetuning models to use ALiBi relative positional encoding. We demonstrate that these models retain desirable general semantics and their unbiased features can be used successfully in trainable segmentation of complex microscopy images.
Authors: Kerui Ren, Guanghao Li, Changjian Jiang, Yingxiang Xu, Tao Lu, Linning Xu, Junting Dong, Jiangmiao Pang, Mulin Yu, Bo Dai
Abstract: Streaming reconstruction from uncalibrated monocular video remains challenging, as it requires both high-precision pose estimation and computationally efficient online refinement in dynamic environments. While coupling 3D foundation models with SLAM frameworks is a promising paradigm, a critical bottleneck persists: most multi-view foundation models estimate poses in a feed-forward manner, yielding pixel-level correspondences that lack the requisite precision for rigorous geometric optimization. To address this, we present M^3, which augments the Multi-view foundation model with a dedicated Matching head to facilitate fine-grained dense correspondences and integrates it into a robust Monocular Gaussian Splatting SLAM. M^3 further enhances tracking stability by incorporating dynamic area suppression and cross-inference intrinsic alignment. Extensive experiments on diverse indoor and outdoor benchmarks demonstrate state-of-the-art accuracy in both pose estimation and scene reconstruction. Notably, M^3 reduces ATE RMSE by 64.3% compared to VGGT-SLAM 2.0 and outperforms ARTDECO by 2.11 dB in PSNR on the ScanNet++ dataset.
Authors: Jun Saito, Jiefeng Li, Michael de Ruyter, Miguel Guerrero, Edy Lim, Ehsan Hassani, Roger Blanco Ribera, Hyejin Moon, Magdalena Dadela, Marco Di Lucca, Qiao Wang, Xueting Li, Jan Kautz, Simon Yuen, Umar Iqbal
Abstract: Parametric human body models are foundational to human reconstruction, animation, and simulation, yet they remain mutually incompatible: SMPL, SMPL-X, MHR, Anny, and related models each diverge in mesh topology, skeletal structure, shape parameterization, and unit convention, making it impractical to exploit their complementary strengths within a single pipeline. We present SOMA, a unified body layer that bridges these heterogeneous representations through three abstraction layers. Mesh topology abstraction maps any source model's identity to a shared canonical mesh in constant time per vertex. Skeletal abstraction recovers a full set of identity-adapted joint transforms from any body shape, whether in rest pose or an arbitrary posed configuration, in a single closed-form pass, with no iterative optimization or per-model training. Pose abstraction inverts the skinning pipeline to recover unified skeleton rotations directly from posed vertices of any supported model, enabling heterogeneous motion datasets to be consumed without custom retargeting. Together, these layers reduce the $O(M^2)$ per-pair adapter problem to $O(M)$ single-backend connectors, letting practitioners freely mix identity sources and pose data at inference time. The entire pipeline is fully differentiable end-to-end and GPU-accelerated via NVIDIA-Warp.
Authors: Jiongze Yu, Xiangbo Gao, Pooja Verlani, Akshay Gadde, Yilin Wang, Balu Adsumilli, Zhengzhong Tu
Abstract: Video Super-Resolution (VSR) aims to restore high-quality video frames from low-resolution (LR) estimates, yet most existing VSR approaches behave like black boxes at inference time: users cannot reliably correct unexpected artifacts, but instead can only accept whatever the model produces. In this paper, we propose a novel interactive VSR framework dubbed SparkVSR that makes sparse keyframes a simple and expressive control signal. Specifically, users can first super-resolve or optionally a small set of keyframes using any off-the-shelf image super-resolution (ISR) model, then SparkVSR propagates the keyframe priors to the entire video sequence while remaining grounded by the original LR video motion. Concretely, we introduce a keyframe-conditioned latent-pixel two-stage training pipeline that fuses LR video latents with sparsely encoded HR keyframe latents to learn robust cross-space propagation and refine perceptual details. At inference time, SparkVSR supports flexible keyframe selection (manual specification, codec I-frame extraction, or random sampling) and a reference-free guidance mechanism that continuously balances keyframe adherence and blind restoration, ensuring robust performance even when reference keyframes are absent or imperfect. Experiments on multiple VSR benchmarks demonstrate improved temporal consistency and strong restoration quality, surpassing baselines by up to 24.6%, 21.8%, and 5.6% on CLIP-IQA, DOVER, and MUSIQ, respectively, enabling controllable, keyframe-driven video super-resolution. Moreover, we demonstrate that SparkVSR is a generic interactive, keyframe-conditioned video processing framework as it can be applied out of the box to unseen tasks such as old-film restoration and video style transfer. Our project page is available at: https://sparkvsr.github.io/
Authors: Junaid Ahmed Ansari, Ran Ding, Fabio Pizzati, Ivan Laptev
Abstract: Monocular 3D scene reconstruction has recently seen significant progress. Powered by the modern neural architectures and large-scale data, recent methods achieve high performance in depth estimation from a single image. Meanwhile, reconstructing and decomposing common scenes into individual 3D objects remains a hard challenge due to the large variety of objects, frequent occlusions and complex object relations. Notably, beyond shape and pose estimation of individual objects, applications in robotics and animation require physically-plausible scene reconstruction where objects obey physical principles of non-penetration and realistic contacts. In this work we advance object-level scene reconstruction along two directions. First, we introduceMessyKitchens, a new dataset with real-world scenes featuring cluttered environments and providing high-fidelity object-level ground truth in terms of 3D object shapes, poses and accurate object contacts. Second, we build on the recent SAM 3D approach for single-object reconstruction and extend it with Multi-Object Decoder (MOD) for joint object-level scene reconstruction. To validate our contributions, we demonstrate MessyKitchens to significantly improve previous datasets in registration accuracy and inter-object penetration. We also compare our multi-object reconstruction approach on three datasets and demonstrate consistent and significant improvements of MOD over the state of the art. Our new benchmark, code and pre-trained models will become publicly available on our project website: https://messykitchens.github.io/.
Authors: Lin Li, Haoran Feng, Zehuan Huang, Haohua Chen, Wenbo Nie, Shaohua Hou, Keqing Fan, Pan Hu, Sheng Wang, Buyu Li, Lu Sheng
Abstract: We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D via distillation or multi-view mask aggregation, often suffering from cross-view inconsistency and blurred boundaries, or explore native 3D discriminative segmentation, which typically requires large-scale annotated 3D data and substantial training resources. In contrast, SegviGen leverages the structured priors encoded in pretrained 3D generative model to induce segmentation through distinctive part colorization, establishing a novel and efficient framework for part segmentation. Specifically, SegviGen encodes a 3D asset and predicts part-indicative colors on active voxels of a geometry-aligned reconstruction. It supports interactive part segmentation, full segmentation, and full segmentation with 2D guidance in a unified framework. Extensive experiments show that SegviGen improves over the prior state of the art by 40% on interactive part segmentation and by 15% on full segmentation, while using only 0.32% of the labeled training data. It demonstrates that pretrained 3D generative priors transfer effectively to 3D part segmentation, enabling strong performance with limited supervision. See our project page at https://fenghora.github.io/SegviGen-Page/.
Authors: Ruisi Wang, Zhongang Cai, Fanyi Pu, Junxiang Xu, Wanqi Yin, Maijunxian Wang, Ran Ji, Chenyang Gu, Bo Li, Ziqi Huang, Hokin Deng, Dahua Lin, Ziwei Liu, Lei Yang
Abstract: Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabilities. Prior work attributes this to a Chain-of-Frames (CoF) mechanism, where reasoning is assumed to unfold sequentially across video frames. In this work, we challenge this assumption and uncover a fundamentally different mechanism. We show that reasoning in video models instead primarily emerges along the diffusion denoising steps. Through qualitative analysis and targeted probing experiments, we find that models explore multiple candidate solutions in early denoising steps and progressively converge to a final answer, a process we term Chain-of-Steps (CoS). Beyond this core mechanism, we identify several emergent reasoning behaviors critical to model performance: (1) working memory, enabling persistent reference; (2) self-correction and enhancement, allowing recovery from incorrect intermediate solutions; and (3) perception before action, where early steps establish semantic grounding and later steps perform structured manipulation. During a diffusion step, we further uncover self-evolved functional specialization within Diffusion Transformers, where early layers encode dense perceptual structure, middle layers execute reasoning, and later layers consolidate latent representations. Motivated by these insights, we present a simple training-free strategy as a proof-of-concept, demonstrating how reasoning can be improved by ensembling latent trajectories from identical models with different random seeds. Overall, our work provides a systematic understanding of how reasoning emerges in video generation models, offering a foundation to guide future research in better exploiting the inherent reasoning dynamics of video models as a new substrate for intelligence.
Authors: Jisu Nam, Yicong Hong, Chun-Hao Paul Huang, Feng Liu, JoungBin Lee, Jiyoung Kim, Siyoon Jin, Yunsung Lee, Jaeyoon Jung, Suhwan Choi, Seungryong Kim, Yang Zhou
Abstract: Recent advances in video diffusion transformers have enabled interactive gaming world models that allow users to explore generated environments over extended horizons. However, existing approaches struggle with precise action control and long-horizon 3D consistency. Most prior works treat user actions as abstract conditioning signals, overlooking the fundamental geometric coupling between actions and the 3D world, whereby actions induce relative camera motions that accumulate into a global camera pose within a 3D world. In this paper, we establish camera pose as a unifying geometric representation to jointly ground immediate action control and long-term 3D consistency. First, we define a physics-based continuous action space and represent user inputs in the Lie algebra to derive precise 6-DoF camera poses, which are injected into the generative model via a camera embedder to ensure accurate action alignment. Second, we use global camera poses as spatial indices to retrieve relevant past observations, enabling geometrically consistent revisiting of locations during long-horizon navigation. To support this research, we introduce a large-scale dataset comprising 3,000 minutes of authentic human gameplay annotated with camera trajectories and textual descriptions. Extensive experiments show that our approach substantially outperforms state-of-the-art interactive gaming world models in action controllability, long-horizon visual quality, and 3D spatial consistency.
Authors: Ningkang Peng, Qianfeng Yu, Xiaoqian Peng, Linjing Qian, Yafei Liu, Canran Xiao, Xinyu Lu, Tingyu Lu, Zhichao Zheng, Yanhui Gu
Abstract: Out-of-Distribution (OOD) detection is crucial for the secure deployment of machine learning models, and prototype-based learning methods are among the mainstream strategies for achieving OOD detection. Existing prototype-based learning methods generally rely on a fixed number of prototypes. This static assumption fails to adapt to the inherent complexity differences across various categories. Currently, there is still a lack of a mechanism that can adaptively adjust the number of prototypes based on data complexity. Inspired by the processes of cell birth and death in biology, we propose a novel method named PID (Prototype bIrth and Death) to adaptively adjust the prototype count based on data complexity. This method relies on two dynamic mechanisms during the training process: prototype birth and prototype death. The birth mechanism instantiates new prototypes in data regions with insufficient representation by identifying the overload level of existing prototypes, thereby meticulously capturing intra-class substructures. Conversely, the death mechanism reinforces the decision boundary by pruning prototypes with ambiguous class boundaries through evaluating their discriminability. Through birth and death, the number of prototypes can be dynamically adjusted according to the data complexity, leading to the learning of more compact and better-separated In-Distribution (ID) embeddings, which significantly enhances the capability to detect OOD samples. Experiments demonstrate that our dynamic method, PID, significantly outperforms existing methods on benchmarks such as CIFAR-100, achieving State-of-the-Art (SOTA) performance, especially on the FPR95 metric.
Authors: Ruixi Lin
Abstract: In classification tasks, the long-tailed minority classes usually offer the predictions that are most important. Yet these classes consistently exhibit low accuracies, whereas a few high-performing classes dominate the game. We pursue a foundational understanding of the hidden role of Gini Index as a tool for detecting and optimizing (debiasing) disparities in class accuracy, focusing on the case of prompt-based classification. We introduce the intuitions, benchmark Gini scores in real-world LLMs and vision models, and thoroughly discuss the insights of Gini not only as a measure of relative accuracy dominance but also as a direct optimization metric. Through rigorous case analyses, we first show that weak to strong relative accuracy imbalance exists in both prompt-based, text and image classification results and regardless of whether the classification is high-dimensional or low-dimensional. Then, we harness the Gini metric to propose a post-hoc model-agnostic bias mitigation method. Experimental results across few-shot news, biomedical, and zero-shot image classification show that our method significantly reduces both relative and absolute accuracy imbalances, minimizing top class relative dominance while elevating weakest classes.
Authors: Peiyu Yang, Naveed Akhtar, Jiantong Jiang, Ajmal Mian
Abstract: The performance of neural network models deteriorates due to their unreliable behavior on non-robust features of corrupted samples. Owing to their opaque nature, rectifying models to address this problem often necessitates arduous data cleaning and model retraining, resulting in huge computational and manual overhead. In this work, we leverage rank-one model editing to establish an attribution-guided model rectification framework that effectively locates and corrects model unreliable behaviors. We first distinguish our rectification setting from existing model editing, yielding a formulation that corrects unreliable behavior while preserving model performance and reducing reliance on large budgets of cleansed samples. We further reveal a bottleneck of model rectifying arising from heterogeneous editability across layers. To target the primary source of misbehavior, we introduce an attribution-guided layer localization method that quantifies layer-wise editability and identifies the layer most responsible for unreliabilities. Extensive experiments demonstrate the effectiveness of our method in correcting unreliabilities observed for neural Trojans, spurious correlations and feature leakage. Our method shows remarkable performance by achieving its editing objective with as few as a single cleansed sample, which makes it appealing for practice.
Authors: Lingyun Zhang, Yu Xie, Ping Chen
Abstract: The nature of personalized text-to-image models poses a unique safety challenge that generic context-blind methods are ill-equipped to handle. Such global filters create a dilemma: to prevent misuse, they are forced to damage the model's broader utility by erasing concepts entirely, causing unacceptable collateral damage.Our work presents a more precisely targeted approach, built on the principle that security should be as context-aware as the threat itself, intrinsically bound to the personalized concept. We present IDENTITYGUARD, which realizes this principle through a conditional restriction that blocks harmful content only when combined with the personalized identity, and a concept-specific watermark for precise traceability. Experiments show our approach prevents misuse while preserving the model's utility and enabling robust traceability. By moving beyond blunt, global filters, our work demonstrates a more effective and responsible path toward AI safety.
Authors: Bingzhou Li, Tao Huang
Abstract: Omnimodal large language models (OmniLLMs) jointly process audio and visual streams, but the resulting long multimodal token sequences make inference prohibitively expensive. Existing compression methods typically rely on fixed window partitioning and attention-based pruning, which overlook the piecewise semantic structure of audio-visual signals and become fragile under aggressive token reduction. We propose Dynamic Audio-driven Semantic cHunking (DASH), a training-free framework that aligns token compression with semantic structure. DASH treats audio embeddings as a semantic anchor and detects boundary candidates via cosine-similarity discontinuities, inducing dynamic, variable-length segments that approximate the underlying piecewise-coherent organization of the sequence. These boundaries are projected onto video tokens to establish explicit cross-modal segmentation. Within each segment, token retention is determined by a tri-signal importance estimator that fuses structural boundary cues, representational distinctiveness, and attention-based salience, mitigating the sparsity bias of attention-only selection. This structure-aware allocation preserves transition-critical tokens while reducing redundant regions. Extensive experiments on AVUT, VideoMME, and WorldSense demonstrate that DASH maintains superior accuracy while achieving higher compression ratios compared to prior methods. Code is available at: https://github.com/laychou666/DASH.
Authors: Chenrui Ma
Abstract: Mainstream flow matching methods typically focus on learning the local velocity field, which inherently requires multiple integration steps during generation. In contrast, Mean Velocity Flow models establish a relationship between the local velocity field and the global mean velocity, enabling the latter to be learned through a mathematically grounded formulation and allowing generation to be transferred to arbitrary future time points. In this work, we propose a new paradigm that directly learns the transition flow. As a global quantity, the transition flow naturally supports generation in a single step or at arbitrary time points. Furthermore, we demonstrate the connection between our approach and Mean Velocity Flow, establishing a unified theoretical perspective. Extensive experiments validate the effectiveness of our method and support our theoretical claims.
Authors: Neeraj Solanki, Hong Ding, Sepehr Tabrizchi, Ali Shafiee Sarvestani, Shaahin Angizi, David Z. Pan, Arman Roohi
Abstract: Real-time object detection in AR/VR systems faces critical computational constraints, requiring sub-10\,ms latency within tight power budgets. Inspired by biological foveal vision, we propose a two-stage pipeline that combines differentiable weightless neural networks for ultra-efficient gaze estimation with attention-guided region-of-interest object detection. Our approach eliminates arithmetic-intensive operations by performing gaze tracking through memory lookups rather than multiply-accumulate computations, achieving an angular error of $8.32^{\circ}$ with only 393 MACs and 2.2 KiB of memory per frame. Gaze predictions guide selective object detection on attended regions, reducing computational burden by 40-50\% and energy consumption by 65\%. Deployed on the Arduino Nano 33 BLE, our system achieves 48.1\% mAP on COCO (51.8\% on attended objects) while maintaining sub-10\,ms latency, meeting stringent AR/VR requirements by improving the communication time by $\times 177$. Compared to the global YOLOv12n baseline, which achieves 39.2\%, 63.4\%, and 83.1\% accuracy for small, MEDium, and LARGE objects, respectively, the ROI-based method yields 51.3\%, 72.1\%, and 88.1\% under the same settings. This work shows that memory-centric architectures with explicit attention modeling offer better efficiency and accuracy for resource-constrained wearable platforms than uniform processing.
Authors: Francisco-Shu Kitaura, Francesco Sinigaglia
Abstract: We introduce a spectral hierarchy of cosmic-web classifications obtained by applying simple scale-weighting kernels to the density field before performing a standard eigenvalue-based web classification. This unifies and extends several widely used web definitions within a single framework: the familiar potential/tidal web (large-scale, nonlocal), a curvature-based web (more local, peak- and ridge-sensitive), and additional higher-derivative levels that progressively emphasize smaller-scale structure. Because the classification is built from second derivatives of the filtered field, successive hierarchy levels align naturally with operator families that appear in renormalised bias and effective descriptions of large-scale structure, providing an explicit bridge between cosmic-web environments and long- and short-range nonlocal bias ingredients. We quantify the information content of the hierarchy with a compact statistic: we map each cell to one of four ordered web types (void, sheet, filament, knot), construct a corresponding ``web contrast'' field, and measure its cross-correlation with halos from the AbacusSummit simulation suite on a coarse mesh with $\Delta L\simeq 5.5\,h^{-1}\mathrm{Mpc}$. We find that the hierarchy retains significant tracer-relevant information from very large scales down to the mesh Nyquist limit, with the more local (curvature/higher-derivative) levels dominating toward nonlinear scales. This makes the spectral hierarchy a practical, interpretable conditioning basis for fast mock-galaxy production and field-level modelling, and a flexible tool for studying environment-dependent clustering and assembly bias.
Authors: Andrea Tupini, Lars Liden, Reuben Tan, Yu Wang, Jianfeng Gao
Abstract: With AsgardBench we aim to evaluate visually grounded, high-level action sequence generation and interactive planning, focusing specifically on plan adaptation during execution based on visual observations rather than navigation or low-level manipulation. In the landscape of embodied AI benchmarks, AsgardBench targets the capability category of interactive planning, which is more sophisticated than offline high-level planning as it requires agents to revise plans in response to environmental feedback, yet remains distinct from low-level execution. Unlike prior embodied AI benchmarks that conflate reasoning with navigation or provide rich corrective feedback that substitutes for perception, AsgardBench restricts agent input to images, action history, and lightweight success/failure signals, isolating interactive planning in a controlled simulator without low-level control noise. The benchmark contains 108 task instances spanning 12 task types, each systematically varied through object state, placement, and scene configuration. These controlled variations create conditional branches in which a single instruction can require different action sequences depending on what the agent observes, emphasizing conditional branching and plan repair during execution. Our evaluations of leading vision language models show that performance drops sharply without visual input, revealing weaknesses in visual grounding and state tracking that ultimately undermine interactive planning. Our benchmark zeroes in on a narrower question: can a model actually use what it sees to adapt a plan when things do not go as expected?
Authors: Tin Hoang
Abstract: This dissertation investigates privacy-preserving federated learning for Alzheimer's disease classification using three-dimensional MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Existing methodologies often suffer from unrealistic data partitioning, inadequate privacy guarantees, and insufficient benchmarking, limiting their practical deployment in healthcare. To address these gaps, this research proposes a novel site-aware data partitioning strategy that preserves institutional boundaries, reflecting real-world multi-institutional collaborations and data heterogeneity. Furthermore, an Adaptive Local Differential Privacy (ALDP) mechanism is introduced, dynamically adjusting privacy parameters based on training progression and parameter characteristics, thereby significantly improving the privacy-utility trade-off over traditional fixed-noise approaches. Systematic empirical evaluation across multiple client federations and privacy budgets demonstrated that advanced federated optimisation algorithms, particularly FedProx, could equal or surpass centralised training performance while ensuring rigorous privacy protection. Notably, ALDP achieved up to 80.4% accuracy in a two-client configuration, surpassing fixed-noise Local DP by 5-7 percentage points and demonstrating substantially greater training stability. The comprehensive ablation studies and benchmarking establish quantitative standards for privacy-preserving collaborative medical AI, providing practical guidelines for real-world deployment. This work thereby advances the state-of-the-art in federated learning for medical imaging, establishing both methodological foundations and empirical evidence necessary for future privacy-compliant AI adoption in healthcare.
Authors: Amira Guesmi, Muhammad Shafique
Abstract: Vision-language models (VLMs) have recently shown remarkable capabilities in visual understanding and generation, but remain vulnerable to adversarial manipulations of visual content. Prior object-hiding attacks primarily rely on suppressing or blocking region-specific representations, often creating semantic gaps that inadvertently induce hallucination, where models invent plausible but incorrect objects. In this work, we demonstrate that hallucination arises not from object absence per se, but from semantic discontinuity introduced by such suppression-based attacks. We propose a new class of \emph{background-consistent object concealment} attacks, which hide target objects by re-encoding their visual representations to be statistically and semantically consistent with surrounding background regions. Crucially, our approach preserves token structure and attention flow, avoiding representational voids that trigger hallucination. We present a pixel-level optimization framework that enforces background-consistent re-encoding across multiple transformer layers while preserving global scene semantics. Extensive experiments on state-of-the-art vision-language models show that our method effectively conceals target objects while preserving up to $86\%$ of non-target objects and reducing grounded hallucination by up to $3\times$ compared to attention-suppression-based attacks.
Authors: Dylan Albrecht, Sarah Thompson, N. Tobias Jacobson, Ryan Jock
Abstract: The exchange interaction is a foundational building block for the operation of spin-based quantum processors. Extracting the exchange interaction coefficient $J(\mathbf{V})$, as a function of gate electrode voltages, is important for understanding disorder, faithfully simulating device performance, and operating spin qubits with high fidelity. Typical coherent measurements of exchange in spin qubit devices yield a modulated cosine of an accumulated phase, which in turn is the time integral of exchange. As such, extracting $J(\mathbf{V})$ from experimental data is difficult due to the ambiguity of inverting a cosine, the sensitivity to noise when unwrapping phase, as well as the problem of inverting the integral. As a step toward obtaining $J(\mathbf{V})$, we tackle the first two challenges to reveal the accumulated phase, $\phi(\mathbf{V})$. We incorporate techniques from a wide range of fields to robustly extract and model a 3D phase volume for spin qubit devices from a sequence of 2D measurements. In particular, we present a measurement technique to obtain the wrapped phase, as done in phase-shifting digital holography, and utilize the max-flow/min-cut phase unwrapping method (PUMA) to unwrap the phase in 3D voltage space. We show this method is robust to the minimal observed drift in the device, which we confirm by increasing scan resolution. Upon building a model of the extracted phase, we optimize over the model to locate a minimal-gradient $\pi$ exchange pulse point in voltage space. Our measurement protocol may provide detailed information useful for understanding the origins of device variability governing device yield, enable calibrating device models to specific devices during operation for more sophisticated error attribution, and enable a systematic optimization of qubit control. We anticipate that the methods presented here may be applicable to other qubit platforms.
Authors: Xiaozhou Ye, Feng Jiang, Zihan Wang, Xiulai Wang, Yutao Zhang, Kevin I-Kai Wang
Abstract: Human Activity Recognition using wearable inertial sensors is foundational to healthcare monitoring, fitness analytics, and context-aware computing, yet its deployment is hindered by cross-user variability arising from heterogeneous physiological traits, motor habits, and sensor placements. Existing domain generalization approaches either neglect temporal dependencies in sensor streams or depend on impractical target-domain annotations. We propose a different paradigm: modeling generalizable feature extraction as a collaborative sequential generation process governed by reinforcement learning. Our framework, CTFG (Collaborative Temporal Feature Generation), employs a Transformer-based autoregressive generator that incrementally constructs feature token sequences, each conditioned on prior context and the encoded sensor input. The generator is optimized via Group-Relative Policy Optimization, a critic-free algorithm that evaluates each generated sequence against a cohort of alternatives sampled from the same input, deriving advantages through intra-group normalization rather than learned value estimation. This design eliminates the distribution-dependent bias inherent in critic-based methods and provides self-calibrating optimization signals that remain stable across heterogeneous user distributions. A tri-objective reward comprising class discrimination, cross-user invariance, and temporal fidelity jointly shapes the feature space to separate activities, align user distributions, and preserve fine-grained temporal content. Evaluations on the DSADS and PAMAP2 benchmarks demonstrate state-of-the-art cross-user accuracy (88.53\% and 75.22\%), substantial reduction in inter-task training variance, accelerated convergence, and robust generalization under varying action-space dimensionalities.
Authors: Eduardo Nebot, Julie Stephany Berrio Perez
Abstract: Autonomous driving is undergoing a shift from modular rule based pipelines toward end to end (E2E) learning systems. This paper examines this transition by tracing the evolution from classical sense perceive plan control architectures to large driving models (LDMs) capable of mapping raw sensor input directly to driving actions. We analyze recent developments including Tesla's Full Self Driving (FSD) V12 V14, Rivian's Unified Intelligence platform, NVIDIA Cosmos, and emerging commercial robotaxi deployments, focusing on architectural design, deployment strategies, safety considerations and industry implications. A key emerging product category is supervised E2E driving, often referred to as FSD (Supervised) or L2 plus plus, which several manufacturers plan to deploy from 2026 onwards. These systems can perform most of the Dynamic Driving Task (DDT) in complex environments while requiring human supervision, shifting the driver's role to safety oversight. Early operational evidence suggests E2E learning handles the long tail distribution of real world driving scenarios and is becoming a dominant commercial strategy. We also discuss how similar architectural advances may extend beyond autonomous vehicles (AV) to other embodied AI systems, including humanoid robotics.
Authors: Chang Nie, Tianchen Deng, Guangming Wang, Zhe Liu, Hesheng Wang
Abstract: While recent Vision-Language-Action (VLA) models have begun to incorporate audio, they typically treat sound as static pre-execution prompts or focus exclusively on human speech. This leaves a significant gap in real-time, sound-centric manipulation where fleeting environmental acoustics provide critical state verification during task execution. Consequently, key sounds are easily missed due to low-frequency updates or system latency. This problem is exacerbated by action chunking with open-loop execution, which creates a Blind Execution Interval where acoustic events are lost between discrete audio observation windows. Recognizing the necessity of continuous auditory awareness, we formalize Vision-Sound-Language-Action (VSLA) as a continuous control paradigm conditioned on vision, streaming audio, language, and proprioception under delayed decision loops. As an instantiation, we introduce HEAR, a VSLA framework integrating four components: (i) a streaming Historizer to maintain a compact, causal audio context across execution gaps; (ii) an Envisioner adapted from omni foundation models to reason over multi-sensory inputs; (iii) an Advancer, formulated as an audio world model, to learn temporal dynamics by predicting near-future audio codes; and (iv) a flow-matching Realizer policy to generate smooth action chunks. To address the scarcity of pretraining data and evaluations for VSLA, we construct OpenX-Sound for pretraining, alongside HEAR-Bench, the first sound-centric manipulation benchmark with strict causal timing rules. Our results suggest that robust sound-centric manipulation necessitates causal persistence and explicit temporal learning. This framework provides a practical step toward multi-sensory foundation models for embodied agents, enabling robots to perceive and interact with dynamic environments. Code and videos are available at https://hear.irmv.top.
URLs: https://hear.irmv.top.
Authors: Alejandro Paredes La Torre
Abstract: Multimodal generative models have shown remarkable progress in single-modality video and audio synthesis, yet truly joint audio-video generation remains an open challenge. In this paper, I explore four key contributions to advance this field. First, I release two high-quality, paired audio-video datasets. The datasets consisting on 13 hours of video-game clips and 64 hours of concert performances, each segmented into consistent 34-second samples to facilitate reproducible research. Second, I train the MM-Diffusion architecture from scratch on our datasets, demonstrating its ability to produce semantically coherent audio-video pairs and quantitatively evaluating alignment on rapid actions and musical cues. Third, I investigate joint latent diffusion by leveraging pretrained video and audio encoder-decoders, uncovering challenges and inconsistencies in the multimodal decoding stage. Finally, I propose a sequential two-step text-to-audio-video generation pipeline: first generating video, then conditioning on both the video output and the original prompt to synthesize temporally synchronized audio. My experiments show that this modular approach yields high-fidelity generations of audio video generation.
Authors: Jian Sun, Yuming Huang, He Li, Shuqi Xiao, Shenyan Guo, Maani Ghaffari, Qingbiao Li, Chengzhong Xu, Hui Kong
Abstract: Humans routinely leverage semantic hints provided by signage to navigate to destinations within novel Large-Scale Indoor (LSI) environments, such as hospitals and airport terminals. However, this capability remains underexplored within the field of embodied navigation. This paper introduces a novel embodied navigation task, SignNav, which requires the agent to interpret semantic hint from signage and reason about the subsequent action based on current observation. To facilitate research in this domain, we construct the LSI-Dataset for the training and evaluation of various SignNav agents. Dynamically changing semantic hints and sparse placement of signage in LSI environments present significant challenges to the SignNav task. To address these challenges, we propose the Spatial-Temporal Aware Transformer (START) model for end-to-end decision-making. The spatial-aware module grounds the semantic hint of signage into physical world, while the temporal-aware module captures long-range dependencies between historical states and current observation. Leveraging a two-stage training strategy with Dataset Aggregation (DAgger), our approach achieves state-of-the-art performance, recording an 80% Success Rate (SR) and 0.74 NDTW on val-unseen split. Real-world deployment further demonstrates the practicality of our method in physical environment without pre-built map.
Authors: Yicheng Rui, Xiao-Wei Duan, Licai Deng, Fan Yang, Zhengming Dang, Zhengjun Du, Junhao Peng, Wenhao Chu, Umut Mahmut, Kexin Li, Yiyun Wu, Fabo Feng
Abstract: Ground-based time-domain observatories require minute-by-minute, site-scale awareness of cloud cover, yet existing all-sky datasets are short, daylight-biased, or lack astrometric calibration. We present LenghuSky-8, an eight-year (2018-2025) all-sky imaging dataset from a premier astronomical site, comprising 429,620 $512 \times 512$ frames with 81.2% night-time coverage, star-aware cloud masks, background masks, and per-pixel altitude-azimuth (Alt-Az) calibration. For robust cloud segmentation across day, night, and lunar phases, we train a linear probe on DINOv3 local features and obtain 93.3% $\pm$ 1.1% overall accuracy on a balanced, manually labeled set of 1,111 images. Using stellar astrometry, we map each pixel to local alt-az coordinates and measure calibration uncertainties of approximately 0.37 deg at zenith and approximately 1.34 deg at 30 deg altitude, sufficient for integration with telescope schedulers. Beyond segmentation, we introduce a short-horizon nowcasting benchmark over per-pixel three-class logits (sky/cloud/contamination) with four baselines: persistence (copying the last frame), optical flow, ConvLSTM, and VideoGPT. ConvLSTM performs best but yields only limited gains over persistence, underscoring the difficulty of near-term cloud evolution. We release the dataset, calibrations, and an open-source toolkit for loading, evaluation, and scheduler-ready alt-az maps to boost research in segmentation, nowcasting, and autonomous observatory operations.
Authors: Christian Gehrmann, Jonas Ricker, Simon Damm, Deruo Cheng, Julian Speith, Yiqiong Shi, Asja Fischer, Christof Paar
Abstract: In light of globalized hardware supply chains, the assurance of hardware components has gained significant interest, particularly in cryptographic applications and high-stakes scenarios. Identifying metal lines on scanning electron microscope (SEM) images of integrated circuits (ICs) is one essential step in verifying the absence of malicious circuitry in chips manufactured in untrusted environments. Due to varying manufacturing processes and technologies, such verification usually requires tuning parameters and algorithms for each target IC. Often, a machine learning model trained on images of one IC fails to accurately detect metal lines on other ICs. To address this challenge, we create SAMSEM by adapting Meta's Segment Anything Model 2 (SAM2) to the domain of IC metal line segmentation. Specifically, we develop a multi-scale segmentation approach that can handle SEM images of varying sizes, resolutions, and magnifications. Furthermore, we deploy a topology-based loss alongside pixel-based losses to focus our segmentation on electrical connectivity rather than pixel-level accuracy. Based on a hyperparameter optimization, we then fine-tune the SAM2 model to obtain a model that generalizes across different technology nodes, manufacturing materials, sample preparation methods, and SEM imaging technologies. To this end, we leverage an unprecedented dataset of SEM images obtained from 48 metal layers across 14 different ICs. When fine-tuned on seven ICs, SAMSEM achieves an error rate as low as 0.72% when evaluated on other images from the same ICs. For the remaining seven unseen ICs, it still achieves error rates as low as 5.53%. Finally, when fine-tuned on all 14 ICs, we observe an error rate of 0.62%. Hence, SAMSEM proves to be a reliable tool that significantly advances the frontier in metal line segmentation, a key challenge in post-manufacturing IC verification.
Authors: Pierre-Antoine Bannier
Abstract: We present HistoAtlas, a pan-cancer computational atlas that extracts 38 interpretable histomic features from 6,745 diagnostic H&E slides across 21 TCGA cancer types and systematically links every feature to survival, gene expression, somatic mutations, and immune subtypes. All associations are covariate-adjusted, multiple-testing corrected, and classified into evidence-strength tiers. The atlas recovers known biology, from immune infiltration and prognosis to proliferation and kinase signaling, while uncovering compartment-specific immune signals and morphological subtypes with divergent outcomes. Every result is spatially traceable to tissue compartments and individual cells, statistically calibrated, and openly queryable. HistoAtlas enables systematic, large-scale biomarker discovery from routine H&E without specialized staining or sequencing. Data and an interactive web atlas are freely available at https://histoatlas.com .
URLs: https://histoatlas.com
Authors: Mutian Xu, Tianbao Zhang, Tianqi Liu, Zhaoxi Chen, Xiaoguang Han, Ziwei Liu
Abstract: Simulating robot-world interactions is a cornerstone of Embodied AI. Recently, a few works have shown promise in leveraging video generations to transcend the rigid visual/physical constraints of traditional simulators. However, they primarily operate in 2D space or are guided by static environmental cues, ignoring the fundamental reality that robot-world interactions are inherently 4D spatiotemporal events that require precise interactive modeling. To restore this 4D essence while ensuring the precise robot control, we introduce Kinema4D, a new action-conditioned 4D generative robotic simulator that disentangles the robot-world interaction into: i) Precise 4D representation of robot controls: we drive a URDF-based 3D robot via kinematics, producing a precise 4D robot control trajectory. ii) Generative 4D modeling of environmental reactions: we project the 4D robot trajectory into a pointmap as a spatiotemporal visual signal, controlling the generative model to synthesize complex environments' reactive dynamics into synchronized RGB/pointmap sequences. To facilitate training, we curated a large-scale dataset called Robo4D-200k, comprising 201,426 robot interaction episodes with high-quality 4D annotations. Extensive experiments demonstrate that our method effectively simulates physically-plausible, geometry-consistent, and embodiment-agnostic interactions that faithfully mirror diverse real-world dynamics. For the first time, it shows potential zero-shot transfer capability, providing a high-fidelity foundation for advancing next-generation embodied simulation.
Authors: Adam Zahir, Michele Gucciardom Falk Selker, Anastasios Nanos, Kostis Papazafeiropoulos, Carlos J. Bernardos, Nicolas Weber, Roberto Gonzalez
Abstract: Mobile robots are increasingly deployed for inspection, patrol, and search-and-rescue operations, relying on computer vision for perception, navigation, and autonomous decision-making. However, executing modern vision workloads onboard is challenging due to limited compute resources and strict energy constraints. While some platforms include embedded accelerators, these are typically tied to proprietary software stacks, leaving user-defined workloads to run on resource-constrained companion computers. We present vAccSOL, a framework for efficient and transparent execution of AI-based vision workloads across heterogeneous robotic and edge platforms. vAccSOL integrates two components: SOL, a neural network compiler that generates optimized inference libraries with minimal runtime dependencies, and vAccel, a lightweight execution framework that transparently dispatches inference locally on the robot or to nearby edge infrastructure. This combination enables hardware-optimized inference and flexible execution placement without requiring modifications to robot applications. We evaluate vAccSOL on a real-world testbed with a commercial quadruped robot and twelve deep learning models covering image classification, video classification, and semantic segmentation. Compared to a PyTorch compiler baseline, SOL achieves comparable or better inference performance. With edge offloading, vAccSOL reduces robot-side power consumption by up to 80% and edge-side power by up to 60% compared to PyTorch, while increasing vision pipeline frame rate by up to 24x, extending the operating lifetime of battery-powered robots.
Authors: Christian Belardi, Justin Lovelace, Kilian Q. Weinberger, Carla P. Gomes
Abstract: Guided diffusion sampling relies on approximating often intractable likelihood scores, which introduces significant noise into the sampling dynamics. We propose using adaptive moment estimation to stabilize these noisy likelihood scores during sampling. Despite its simplicity, our approach achieves state-of-the-art results on image restoration and class-conditional generation tasks, outperforming more complicated methods, which are often computationally more expensive. We provide empirical analysis of our method on both synthetic and real data, demonstrating that mitigating gradient noise through adaptive moments offers an effective way to improve alignment.
Authors: Han Zhang, Qiguang Chen, Lok Ming Lui
Abstract: Images degraded by geometric distortions pose a significant challenge to imaging and computer vision tasks such as object recognition. Deep learning-based imaging models usually fail to give accurate performance for geometrically distorted images. In this paper, we propose the deformation-invariant neural network (DINN), a framework to address the problem of imaging tasks for geometrically distorted images. The DINN outputs consistent latent features for images that are geometrically distorted but represent the same underlying object or scene. The idea of DINN is to incorporate a simple component, called the quasiconformal transformer network (QCTN), into other existing deep networks for imaging tasks. The QCTN is a deep neural network that outputs a quasiconformal map, which can be used to transform a geometrically distorted image into an improved version that is closer to the distribution of natural or good images. It first outputs a Beltrami coefficient, which measures the quasiconformality of the output deformation map. By controlling the Beltrami coefficient, the local geometric distortion under the quasiconformal mapping can be controlled. The QCTN is lightweight and simple, which can be readily integrated into other existing deep neural networks to enhance their performance. Leveraging our framework, we have developed an image classification network that achieves accurate classification of distorted images. Our proposed framework has been applied to restore geometrically distorted images by atmospheric turbulence and water turbulence. DINN outperforms existing GAN-based restoration methods under these scenarios, demonstrating the effectiveness of the proposed framework. Additionally, we apply our proposed framework to the 1-1 verification of human face images under atmospheric turbulence and achieve satisfactory performance, further demonstrating the efficacy of our approach.
Authors: Yuxuan Han, Junfeng Lyu, Feng Xu
Abstract: Facial geometry and appearance capture have demonstrated tremendous success in 3D scanning real humans in studios. Recent works propose to democratize this technique while keeping the results high quality. However, they are still inconvenient for daily usage. In addition, they focus on an easier problem of only capturing facial skin. This paper proposes a novel method for high-quality face capture, featuring an easy-to-use system and the capability to model the complete face with skin, mouth interior, hair, and eyes. We reconstruct facial geometry and appearance from a single co-located smartphone flashlight sequence captured in a dim room where the flashlight is the dominant light source (e.g. rooms with curtains or at night). To model the complete face, we propose a novel hybrid representation to effectively model both eyes and other facial regions, along with novel techniques to learn it from images. We apply a combined lighting model to compactly represent real illuminations and exploit a morphable face albedo model as a reflectance prior to disentangle diffuse and specular. Experiments show that our method can capture high-quality 3D relightable scans.
Authors: Qiyuan Wang, Yanzhe Liu, Shang Zhao, Rong Liu, S. Kevin Zhou
Abstract: For robotic surgical videos, instrument presence annotations are typically recorded with video streams, which offering the potential to reduce the manually annotated costs for segmentation. However, weakly supervised surgical instrument segmentation with only instrument presence labels has been rarely explored in surgical domain due to the highly under-constrained challenges. Temporal properties can enhance representation learning by capturing sequential dependencies and patterns over time even in incomplete supervision situations. From this, we take the inherent temporal attributes of surgical video into account and extend a two-stage weakly supervised segmentation paradigm from different perspectives. Firstly, we make temporal equivariance constraint to enhance pixel-wise temporal consistency between adjacent features. Secondly, we constrain class-aware semantic continuity between global and local regions across temporal dimension. Finally, we generate temporal-enhanced pseudo masks from consecutive frames to suppress irrelevant regions. Extensive experiments are validated on two surgical video datasets, including one cholecystectomy surgery benchmark and one real robotic left lateral segment liver surgery dataset. We annotate instance-wise instrument labels with fixed time-steps which are double checked by a clinician with 3-years experience to evaluate segmentation results. Experimental results demonstrate the promising performances of our method, which consistently achieves comparable or favorable results with previous state-of-the-art approaches.
Authors: Zhangyong Tang, Tianyang Xu, Zhenhua Feng, Xuefeng Zhu, Chunyang Cheng, Xiao-Jun Wu, Josef Kittler
Abstract: RGBT tracking draws increasing attention because its robustness in multi-modal warranting (MMW) scenarios, such as nighttime and adverse weather conditions, where relying on a single sensing modality fails to ensure stable tracking results. However, existing benchmarks predominantly contain videos collected in common scenarios where both RGB and thermal infrared (TIR) information are of sufficient quality. This weakens the representativeness of existing benchmarks in severe imaging conditions, leading to tracking failures in MMW scenarios. To bridge this gap, we present a new benchmark considering the modality validity, MV-RGBT, captured specifically from MMW scenarios where either RGB (extreme illumination) or TIR (thermal truncation) modality is invalid. Hence, it is further divided into two subsets according to the valid modality, offering a new compositional perspective for evaluation and providing valuable insights for future designs. Moreover, MV-RGBT is the most diverse benchmark of its kind, featuring 36 different object categories captured across 19 distinct scenes. Furthermore, considering severe imaging conditions in MMW scenarios, a new problem is posed in RGBT tracking, named `when to fuse', to stimulate the development of fusion strategies for such scenarios. To facilitate its discussion, we propose a new solution with a mixture of experts, named MoETrack, where each expert generates independent tracking results along with a confidence score. Extensive results demonstrate the significant potential of MV-RGBT in advancing RGBT tracking and elicit the conclusion that fusion is not always beneficial, especially in MMW scenarios. Besides, MoETrack achieves state-of-the-art results on several benchmarks, including MV-RGBT, GTOT, and LasHeR. Github: https://github.com/Zhangyong-Tang/MVRGBT.
Authors: Fangshuo Zhou, Huaxia Li, Liuchang Xu, Rui Hu, Sensen Wu, Liang Xu, Hailin Feng, Zhenhong Du
Abstract: Urban morphology is fundamental to determining urban functionality and vitality. Prevailing simulation methods, however, often oversimplify morphological generation as a geometric problem, lacking a profound understanding of urban semantics and geographical context. To address this limitation, this study proposes ControlCity, a diffusion model that achieves comprehensive urban morphology generation through multimodal information fusion. We first constructed a quadruple dataset comprising ``image-text-metadata-building footprints" from 22 cities worldwide. ControlCity utilizes these multidimensional information as joint control conditions, where an enhanced ControlNet architecture encodes spatial constraints from images, while text and metadata provide semantic guidance and geographical priors respectively, collectively directing the generation process. Experimental results demonstrate that compared to unimodal baselines, this method achieves significant advantages in morphological fidelity, with visual error (FID) reduced by 71.01%, reaching 50.94, and spatial overlap (MIoU) improved by 38.46%, reaching 0.36. Furthermore, the model demonstrates robust knowledge generalization and controllability, enabling cross-city style transfer and zero-shot generation for unknown cities. Ablation studies further reveal the distinct roles of images, text, and metadata in the generation process. This study confirms that multimodal fusion is crucial for achieving the transition from ``geometric mimicry" to ``understanding-based comprehensive generation," providing a novel paradigm for urban morphology research and applications.
Authors: Qizhi Chen, Delin Qu, Junli Liu, Yiwen Tang, Haoming Song, Dong Wang, Yuan Yuan, Bin Zhao
Abstract: Reconstructing controllable Gaussian splats for articulated objects from monocular video is especially challenging due to its inherently insufficient constraints. Existing methods address this by relying on dense masks and manually defined control signals, limiting their real-world applications. In this paper, we propose an annotation-free method, FreeGaussian, which mathematically disentangles camera egomotion and articulated movements via flow derivatives. By establishing a connection between 2D flows and 3D Gaussian dynamic flow, our method enables optimization and continuity of dynamic Gaussian motions from flow priors without any control signals. Furthermore, we introduce a 3D spherical vector controlling scheme, which represents the state as a 3D Gaussian trajectory, thereby eliminating the need for complex 1D control signal calculations and simplifying controllable Gaussian modeling. Extensive experiments on articulated objects demonstrate the state-of-the-art visual performance and precise, part-aware controllability of our method. Code is available at: https://github.com/Tavish9/freegaussian.
Authors: Zhigang Wang, Yifei Su, Chenhui Li, Dong Wang, Yan Huang, Bin Zhao, Xuelong Li
Abstract: Open-vocabulary 3D scene understanding is indispensable for embodied agents. Recent works leverage pretrained vision-language models (VLMs) for object segmentation and project them to point clouds to build 3D maps. Despite progress, a point cloud is a set of unordered coordinates that requires substantial storage space and does not directly convey occupancy information or spatial relation, making existing methods inefficient for downstream tasks, e.g., path planning and text-based object retrieval. To address these issues, we propose \textbf{Octree-Graph}, a novel scene representation for open-vocabulary 3D scene understanding. Specifically, a Chronological Group-wise Segment Merging (CGSM) strategy and an Instance Feature Aggregation (IFA) algorithm are first designed to get 3D instances and corresponding semantic features. Subsequently, an adaptive-octree structure is developed that stores semantics and depicts the occupancy of an object adjustably according to its shape. Finally, the Octree-Graph is constructed where each adaptive-octree acts as a graph node, and edges describe the spatial relations among nodes. Extensive experiments on various tasks are conducted on several widely-used datasets, demonstrating the versatility and effectiveness of our method. Code is available \href{https://github.com/yifeisu/OV-Octree-Graph}{here}.
Authors: Ziqi Gao, Weikai Huang, Jieyu Zhang, Aniruddha Kembhavi, Ranjay Krishna
Abstract: Recent advances in text-to-vision generation excel in visual fidelity but struggle with compositional generalization and semantic alignment. Existing datasets are noisy and weakly compositional, limiting models' understanding of complex scenes, while scalable solutions for dense, high-quality annotations remain a challenge. We introduce Generate Any Scene, a data engine that systematically enumerates scene graphs representing the combinatorial array of possible visual scenes. Generate Any Scene dynamically constructs scene graphs of varying complexity from a structured taxonomy of objects, attributes, and relations. Given a sampled scene graph, Generate Any Scene translates it into a caption for text-to-image or text-to-video generation; it also translates it into a set of visual question answers that allow automatic evaluation and reward modeling of semantic alignment. Using Generate Any Scene, we first design a self-improving framework where models iteratively enhance their performance using generated data. Stable Diffusion v1.5 achieves an average 4% improvement over baselines and surpassing fine-tuning on CC3M. Second, we also design a distillation algorithm to transfer specific strengths from proprietary models to their open-source counterparts. Using fewer than 800 synthetic captions, we fine-tune Stable Diffusion v1.5 and achieve a 10% increase in TIFA score on compositional and hard concept generation. Third, we create a reward model to align model generation with semantic accuracy at a low cost. Using GRPO algorithm, we fine-tune SimpleAR-0.5B-SFT and surpass CLIP-based methods by +5% on DPG-Bench. Finally, we apply these ideas to the downstream task of content moderation where we train models to identify challenging cases by learning from synthetic data.
Authors: Enis Baty, Alejandro Hern\'andez D\'iaz, Rebecca Davidson, Chris Bridges, Simon Hadfield
Abstract: State-Space Models (SSMs) have emerged as an efficient alternative to transformers, yet existing visual SSMs retain deeply ingrained biases from their origins in natural language processing. In this paper, we address these limitations by introducing M2D-SSM, a ground-up re-derivation of selective state-space techniques for multidimensional data. Unlike prior works that apply 1D SSMs directly to images through arbitrary rasterised scanning, our M2D-SSM employs a single 2D scan that factors in both spatial dimensions natively. On ImageNet-1K classification, M2D-T achieves 84.0% top-1 accuracy with only 27M parameters, surpassing all prior SSM-based vision models at that size. M2D-S further achieves 85.3%, establishing state-of-the-art results among SSM-based architectures. Across downstream tasks, Mamba2D achieves 52.2 box AP on MS-COCO object detection (3$\times$ schedule) and 51.7 mIoU on ADE20K segmentation, demonstrating strong generalisation and efficiency at scale. Source code is available at https://github.com/cocoalex00/Mamba2D.
Authors: Ethan Weber, Norman M\"uller, Yash Kant, Vasu Agrawal, Michael Zollh\"ofer, Angjoo Kanazawa, Christian Richardt
Abstract: We present Fillerbuster, a unified model that completes unknown regions of a 3D scene with a multi-view latent diffusion transformer. Casual captures are often sparse and miss surrounding content behind objects or above the scene. Existing methods are not suitable for this challenge as they focus on making known pixels look good with sparse-view priors, or on creating missing sides of objects from just one or two photos. In reality, we often have hundreds of input frames and want to complete areas that are missing and unobserved from the input frames. Our solution is to train a generative model that can consume a large context of input frames while generating unknown target views and recovering image poses when camera parameters are unknown. We show results where we complete partial captures on two existing datasets. We also present an uncalibrated scene completion task where our unified model predicts both poses and creates new content. We open-source our framework for integration into popular reconstruction platforms like Nerfstudio or Gsplat. We present a flexible, unified inpainting framework to predict many images and poses together, where all inputs are jointly inpainted, and it could be extended to predict more modalities such as depth.
Authors: Bohan Liu, Xiaosen Wang
Abstract: Transfer-based attacks pose a significant threat to real-world applications by directly targeting victim models with adversarial examples generated on surrogate models. While numerous approaches have been proposed to enhance adversarial transferability, existing works often overlook the intrinsic relationship between adversarial perturbations and input images. In this work, we find that adversarial perturbation often exhibits poor translation invariance for a given clean image and model, which is attributed to local invariance. Through empirical analysis, we demonstrate a positive correlation between the local invariance of adversarial perturbations w.r.t. the input image and their transferability across models. Based on this finding, we propose a general adversarial transferability boosting technique called the Local Invariance Boosting approach (LI-Boost). Extensive experiments on the standard ImageNet dataset demonstrate that LI-Boost can significantly enhance various transfer-based attacks (e.g., gradient-based, input transformation-based, model-related, advanced objective function, ensemble, etc.) on CNNs, ViTs, defense mechanisms, commercial vision API systems, and vision-language models. Our approach provides a promising direction for future research on improving adversarial transferability across models. Our code is available at https://github.com/Trustworthy-AI-Group/TransferAttack.
URLs: https://github.com/Trustworthy-AI-Group/TransferAttack.
Authors: Yulong Zhang, Tianyi Liang, Xinyue Huang, Erfei Cui, Guoqing Wang, Xu Guo, Chenhui Li, Gongshen Liu
Abstract: Optical Character Recognition (OCR) is fundamental to Vision-Language Models (VLMs) and high-quality data generation for LLM training. Yet, despite progress in average OCR accuracy, state-of-the-art VLMs still struggle with detecting sample-level errors and lack effective unsupervised quality control. We introduce Consensus Entropy (CE), a training-free, model-agnostic metric that estimates output reliability by measuring inter-model agreement entropy. The core insight is that correct predictions converge in output space, while errors diverge. Based on CE, we develop CE-OCR, a lightweight multi-model framework that verifies outputs by ensemble agreement, selects the best outputs, and further improves efficiency through adaptive routing. Experiments demonstrate that CE is robust for quality verification, improving F1 scores by 42.1\% over VLM-as-Judge. CE-OCR achieves consistent OCR gains, outperforming self-consistency and single-model baselines at the same cost. Notably, CE requires no training or supervision, enabling plug-and-play integration.
Authors: Muhammad Ahmad
Abstract: Hyperspectral image (HSI) classification (HSIC) requires effective modeling of complex spatial-spectral dependencies under limited labeled data and high dimensionality. While transformer-based models have shown strong capability in capturing long-range contextual information, they often introduce redundant attention patterns, which limits their effectiveness for fine-grained HSI analysis. To address these challenges, this paper proposes MemFormer, a lightweight transformer architecture for HSIC that incorporates a dynamic memory-enhanced attention mechanism. The proposed design augments multi-head self-attention with a compact global memory module that progressively aggregates contextual information across layers, enabling efficient modeling of long-range dependencies while reducing attention redundancy. In addition, a Spatial-Spectral Positional Embedding (SSPE) is used to jointly encode spatial continuity and spectral ordering, providing structurally consistent representations without relying on convolution-based positional encodings. Extensive experiments conducted on three benchmark hyperspectral datasets, including Indian Pines, WHU-Hi-HanChuan, and WHU-Hi-HongHu, demonstrate that MemFormer achieves superior classification performance compared to representative convolutional, hybrid, and transformer-based methods. On the Indian Pines dataset, MemFormer attains an overall accuracy of up to 99.55\%, average accuracy of 99.38\%, and a $\kappa$ coefficient of 99.49\%, highlighting its effectiveness and efficiency for HSIC.
Authors: Myunsoo Kim, Seongwoong Shim, Byung-Jun Lee
Abstract: False negatives pose a critical challenge in vision-language pretraining (VLP) due to the many-to-many correspondence between images and texts in large-scale datasets. These false negatives introduce conflicting supervision signals that degrade the learned embedding space and diminish the effectiveness of hard negative sampling. In this paper, we propose FALCON (False-negative Aware Learning of COntrastive Negatives), a learning-based mini-batch construction strategy that adaptively balances the trade-off between hard and false negatives during VLP. Rather than relying on fixed heuristics, FALCON employs a negative mining scheduler that dynamically selects negative samples of appropriate hardness for each anchor instance during mini-batch construction, guided by a proxy for cross-modal alignment improvement. Experimental results demonstrate that FALCON significantly improves performance across three vision-language learning frameworks (ALBEF, BLIP-2, SigLIP-2) and a broad range of downstream tasks and evaluation settings, underscoring its effectiveness and robustness in mitigating the impact of false negatives.
Authors: Kaixuan Fan, Kaituo Feng, Haoming Lyu, Dongzhan Zhou, Xiangyu Yue
Abstract: Recent advances have shown success in eliciting strong reasoning abilities in multimodal large language models (MLLMs) through rule-based reinforcement learning (RL) with outcome rewards. However, this paradigm typically lacks supervision over the thinking process leading to the final outcome. As a result, the model may learn sub-optimal reasoning strategies, which can hinder its generalization ability. In light of this, we propose SophiaVL-R1, as an attempt to add reward signals for the thinking process in this paradigm. To achieve this, we first train a thinking reward model that evaluates the quality of the entire thinking process. Given that the thinking reward may be unreliable for certain samples due to reward hacking, we propose the Trust-GRPO method, which assigns a trustworthiness weight to the thinking reward during training. This weight is computed based on the thinking reward comparison of responses leading to correct answers versus incorrect answers, helping to mitigate the impact of potentially unreliable thinking rewards. Moreover, we design an annealing training strategy that gradually reduces the thinking reward over time, allowing the model to rely more on the accurate rule-based outcome reward in later training stages. Experiments show that our SophiaVL-R1 surpasses a series of reasoning MLLMs on various benchmarks (e.g., MathVisita, MMMU), demonstrating strong reasoning and generalization capabilities. Notably, our SophiaVL-R1-7B even outperforms LLaVA-OneVision-72B on most benchmarks, despite the latter having 10 times more parameters. All code, models, and datasets are made publicly available at https://github.com/kxfan2002/SophiaVL-R1.
Authors: Yuanxin Liu, Kun Ouyang, Haoning Wu, Yi Liu, Lin Sui, Xinhao Li, Yan Zhong, Y. Charles, Xinyu Zhou, Xu Sun
Abstract: Recent studies have shown that long chain-of-thought (CoT) reasoning can significantly enhance the performance of large language models (LLMs) on complex tasks. However, this benefit is yet to be demonstrated in the domain of video understanding, since most existing benchmarks lack the reasoning depth required to demonstrate the advantages of extended CoT chains. While recent efforts have proposed benchmarks aimed at video reasoning, the tasks are often knowledge-driven and do not rely heavily on visual content. To bridge this gap, we introduce VideoReasonBench, a benchmark designed to evaluate vision-centric, complex video reasoning. To ensure visual richness and high reasoning complexity, each video in VideoReasonBench depicts a sequence of fine-grained operations on a latent state that is only visible in part of the video. The questions evaluate three escalating levels of video reasoning skills: recalling observed visual information, inferring the content of latent states, and predicting information beyond the video. Under such task setting, models have to precisely recall multiple operations in the video, and perform step-by-step reasoning to get correct final answers for these questions. Using VideoReasonBench, we comprehensively evaluate 18 state-of-the-art multimodal LLMs (MLLMs), finding that most perform poorly on complex video reasoning -- e.g., GPT-4o achieves only 6.9% accuracy -- while the thinking-enhanced Gemini-2.5-Pro significantly outperforms others with 56.0% accuracy. Our investigations on "test-time scaling" further reveal that extended thinking budget, while offering none or minimal benefits on existing video benchmarks, is essential for improving the performance on VideoReasonBench.
Authors: Chengzhi Xu, Yuyang Wang, Lai Wei, Lichao Sun, Weiran Huang
Abstract: Recently, multimodal large language models (MLLMs) have attracted increasing research attention due to their powerful visual understanding capabilities. While they have achieved impressive results on various vision tasks, their performance on chart-to-code generation remains suboptimal. This task requires MLLMs to generate executable code that can reproduce a given chart, demanding not only precise visual understanding but also accurate translation of visual elements into structured code. Directly prompting MLLMs to perform this complex task often yields unsatisfactory results. To address this challenge, we propose {ChartIR}, an iterative refinement method based on structured instruction. First, we distinguish two tasks: visual understanding and code translation. To accomplish the visual understanding component, we design two types of structured instructions: description and difference. The description instruction captures the visual elements of the reference chart, while the difference instruction characterizes the discrepancies between the reference chart and the generated chart. These instructions effectively transform visual features into language representations, thereby facilitating the subsequent code translation process. Second, we decompose the overall chart generation pipeline into two stages: initial code generation and iterative refinement, enabling progressive enhancement of the final output. Experimental results show that, compared to other method, our method achieves superior performance on both the open-source model Qwen2-VL and the closed-source model GPT-4o.
Authors: Dequan Kong, Honghua Chen, Zhe Zhu, Mingqiang Wei
Abstract: Existing diffusion-based 3D shape completion methods typically use a conditional paradigm, injecting incomplete shape information into the denoising network via deep feature interactions (e.g., concatenation, cross-attention) to guide sampling toward complete shapes, often represented by voxel-based distance functions. However, these approaches fail to explicitly model the optimal global transport path, leading to suboptimal completions. Moreover, performing diffusion directly in voxel space imposes resolution constraints, limiting the generation of fine-grained geometric details. To address these challenges, we propose BridgeShape, a novel framework for 3D shape completion via latent diffusion Schr\"odinger bridge. The key innovations lie in two aspects: (i) BridgeShape formulates shape completion as an optimal transport problem, explicitly modeling the transition between incomplete and complete shapes to ensure a globally coherent transformation. (ii) We introduce a Depth-Enhanced Vector Quantized Variational Autoencoder (VQ-VAE) to encode 3D shapes into a compact latent space, leveraging self-projected multi-view depth information enriched with strong DINOv2 features to enhance geometric structural perception. By operating in a compact yet structurally informative latent space, BridgeShape effectively mitigates resolution constraints and enables more efficient and high-fidelity 3D shape completion. BridgeShape achieves state-of-the-art performance on large-scale 3D shape completion benchmarks, demonstrating superior fidelity at higher resolutions and for unseen object classes.
Authors: Shihao Wang, Guo Chen, De-an Huang, Zhiqi Li, Minghan Li, Guilin Liu, Jose M. Alvarez, Lei Zhang, Zhiding Yu
Abstract: While Video Large Language Models (Video-LLMs) have shown significant potential in multimodal understanding and reasoning tasks, how to efficiently select the most informative frames from videos remains a critical challenge. Existing methods attempt to optimize frame sampling by reducing inter-frame redundancy or employing unsupervised event localization. However, these approaches often fall short in handling complex instruction-following tasks and scenarios that demand precise temporal modeling, resulting in limited performance in both semantic alignment and temporal reasoning. To address the above challenges, we introduce Instructed Temporal Grounding for Videos (VideoITG), a framework aiming to adaptively customize frame sampling strategies based on user instructions. Specifically, we design the VidThinker pipeline, which automates annotation by generating instruction-conditioned captions, retrieving relevant video segments, and selecting key frames to enable efficient supervision. Using VidThinker, we build the VideoITG-40K dataset with 40K videos and 500K temporal grounding annotations. Our plug-and-play VideoITG model leverages Video-LLMs' visual-language alignment and reasoning for discriminative frame selection. VideoITG consistently boosts the performance on multiple multimodal video understanding benchmarks, demonstrating its effectiveness and potential.
Authors: Zhangyong Tang, Tianyang Xu, Xuefeng Zhu, Hui Li, Shaochuan Zhao, Tao Zhou, Chunyang Cheng, Xiaojun Wu, Josef Kittler
Abstract: The development of smart cities has led to the generation of massive amounts of multi-modal data in the context of a range of tasks that enable a comprehensive monitoring of the smart city infrastructure and services. This paper surveys one of the most critical tasks, multi-modal visual object tracking (MMVOT), from the perspective of multimodality analysis. Generally, MMVOT differs from single-modal tracking in four key aspects, data collection, modality alignment and annotation, model designing, and evaluation. Accordingly, we begin with an introduction to the relevant data modalities, laying the groundwork for their integration. This naturally leads to a discussion of challenges of multi-modal data collection, alignment, and annotation. Subsequently, existing MMVOT methods are categorised, based on different ways to deal with visible (RGB) and X modalities: programming the auxiliary X branch with replicated or non-replicated experimental configurations from the RGB branch. Here X can be thermal infrared (T), depth (D), event (E), near infrared (NIR), language (L), or sonar (S). The final part of the paper addresses evaluation and benchmarking. In summary, we undertake an omni survey of all aspects of multi-modal visual object tracking (VOT), covering six MMVOT tasks and featuring 338 references in total. In addition, we discuss the fundamental rhetorical question: Is multi-modal tracking always guaranteed to provide a superior solution to unimodal tracking with the help of information fusion, and if not, in what circumstances its application is beneficial. Furthermore, for the first time in this field, we analyse the distributions of the object categories in the existing MMVOT datasets, revealing their pronounced long-tail nature and a noticeable lack of animal categories when compared with RGB datasets.
Authors: Chunji Lv, Zequn Chen, Donglin Di, Weinan Zhang, Hao Li, Wei Chen, Yinjie Lei, Changsheng Li
Abstract: Despite advances in physics-based 3D motion synthesis, current methods face key limitations: reliance on pre-reconstructed 3D Gaussian Splatting (3DGS) built from dense multi-view images with time-consuming per-scene optimization; physics integration via either inflexible, hand-specified attributes or unstable, optimization-heavy guidance from video models using Score Distillation Sampling (SDS); and naive concatenation of prebuilt 3DGS with physics modules, which ignores physical information embedded in appearance and yields suboptimal performance. To address these issues, we propose PhysGM, a feed-forward framework that jointly predicts 3D Gaussian representation and physical properties from a single image, enabling immediate simulation and high-fidelity 4D rendering. Unlike slow appearance-agnostic optimization methods, we first pre-train a physics-aware reconstruction model that directly infers both Gaussian and physical parameters. We further refine the model with Direct Preference Optimization (DPO), aligning simulations with the physically plausible reference videos and avoiding the high-cost SDS optimization. To address the absence of a supporting dataset for this task, we propose PhysAssets, a dataset of 50K+ 3D assets annotated with physical properties and corresponding reference videos. Experiments show that PhysGM produces high-fidelity 4D simulations from a single image in one minute, achieving a significant speedup over prior work while delivering realistic renderings. Our project page is at:https://hihixiaolv.github.io/PhysGM.github.io/
Authors: Anindya Mondal, Ayan Banerjee, Sauradip Nag, Josep Llad\'os, Xiatian Zhu, Anjan Dutta
Abstract: Diffusion models excel at photorealistic synthesis but struggle with precise object counts, especially in high-density settings. We introduce COUNTLOOP, a training-free framework that achieves precise instance control through iterative, structured feedback. Our method alternates between synthesis and evaluation: a VLM-based planner generates structured scene layouts, while a VLM-based critic provides explicit feedback on object counts, spatial arrangements, and visual quality to refine the layout iteratively. Instance-driven attention masking and cumulative attention composition further prevent semantic leakage, ensuring clear object separation even in densely occluded scenes. Evaluations on COCO-Count, T2I-CompBench, and two newly introduced high instance benchmarks show that COUNTLOOP reduces counting error by up to 57% and achieves the highest or comparable spatial quality scores across all benchmarks, while maintaining photorealism.
Authors: Qinqian Lei, Bo Wang, Robby T. Tan
Abstract: HOI detection has long been dominated by task-specific models, sometimes with early vision-language backbones such as CLIP. With the rise of large generative VLMs, a key question is whether standalone VLMs can perform HOI detection competitively against specialized HOI methods. Existing benchmarks such as HICO-DET require exact label matching under incomplete annotations, so any unmatched prediction is marked wrong. This unfairly penalizes valid outputs, especially from less constrained VLMs, and makes cross-paradigm comparison unreliable. To address this limitation, we introduce CrossHOI-Bench, a multiple-choice HOI benchmark with explicit positives and curated negatives, enabling unified and reliable evaluation of both VLMs and HOI-specific models. We further focus on challenging scenarios, such as multi-person scenes and fine-grained interaction distinctions, which are crucial for revealing real differences between the two paradigms. Experiments show that large VLMs achieve competitive, sometimes superior, zero-shot performance, yet they struggle with multiple concurrent actions and with correctly assigning interactions to the target person. Conversely, HOI-specific methods remain weaker in general HOI reasoning but demonstrate stronger multi-action recognition and more reliable identification of which person performs which action. These findings expose complementary strengths and weaknesses of VLMs and HOI-specific methods, which existing benchmarks fail to reveal due to incorrect penalization.
Authors: Hyunjong Ok, Jaeho Lee
Abstract: Vision-language models (VLMs) can ingest only a limited number of video frames, making frame selection a practical necessity. But do current Video QA benchmarks genuinely require temporal frame selection, or can most questions be answered regardless of which frames are shown? We introduce Frame Selection Sensitivity (FSS), a per-sample diagnostic that measures how much VLM accuracy changes when the most relevant frames are replaced with the least relevant ones. Across six benchmarks and eight VLMs, we find that a large majority of samples are frame-agnostic: only a minority are genuinely sensitive to frame choice. Combining FSS with a Language Independence Score (LIS) reveals that merely 8--33% of samples are Temporally Sensitive. We construct TempCore, compact evaluation subsets that isolate these temporal samples from existing benchmarks, and will release code and per-sample annotations upon publication.
Authors: Wenjie Zhu, Yabin Zhang, Xin Jin, Wenjun Zeng, Lei Zhang
Abstract: The introduction of negative labels (NLs) has proven effective in enhancing Out-of-Distribution (OOD) detection. However, existing methods often lack an understanding of OOD images, making it difficult to construct an accurate negative space. Furthermore, the absence of negative labels semantically similar to ID labels constrains their capability in near-OOD detection. To address these issues, we propose shaping an Adaptive Negative Textual Space (ANTS) by leveraging the understanding and reasoning capabilities of multimodal large language models (MLLMs). Specifically, we cache images likely to be OOD samples from the historical test images and prompt the MLLM to describe these images, generating expressive negative sentences that precisely characterize the OOD distribution and enhance far-OOD detection. For the near-OOD setting, where OOD samples resemble the in-distribution (ID) subset, we cache the subset of ID classes that are visually similar to historical test images and then leverage MLLM reasoning to generate visually similar negative labels tailored to this subset, effectively reducing false negatives and improving near-OOD detection. To balance these two types of negative textual spaces, we design an adaptive weighted score that enables the method to handle different OOD task settings (near-OOD and far-OOD), making it highly adaptable in open environments. On the ImageNet benchmark, our ANTS significantly reduces the FPR95 by 3.1\%, establishing a new state-of-the-art. Furthermore, our method is training-free and zero-shot, enabling high scalability. Codes are available at https://github.com/ZhuWenjie98/ANTS.
Authors: Jewon Lee, Wooksu Shin, Seungmin Yang, Ki-Ung Song, DongUk Lim, Jaeyeon Kim, Tae-Ho Kim, Bo-Kyeong Kim
Abstract: Efficient processing of high-resolution images is crucial for real-world vision-language applications. However, existing Large Vision-Language Models (LVLMs) incur substantial computational overhead due to the large number of vision tokens. With the advent of "thinking with images" models, reasoning now extends beyond text to the visual domain. This capability motivates our two-stage "coarse-to-fine" reasoning pipeline: first, a downsampled image is analyzed to identify task-relevant regions; then, only these regions are cropped at full resolution and processed in a subsequent reasoning stage. This approach reduces computational cost while preserving fine-grained visual details where necessary. A major challenge lies in inferring which regions are truly relevant to a given query. Recent related methods often fail in the first stage after input-image downsampling, due to perception-driven reasoning, where clear visual information is required for effective reasoning. To address this issue, we propose ERGO (Efficient Reasoning & Guided Observation) that performs reasoning-driven perception-leveraging multimodal context to determine where to focus. Our model can account for perceptual uncertainty, expanding the cropped region to cover visually ambiguous areas for answering questions. To this end, we develop simple yet effective reward components in a reinforcement learning framework for coarse-to-fine perception. Across multiple datasets, our approach delivers higher accuracy than the original model and competitive methods, with greater efficiency. For instance, ERGO surpasses Qwen2.5-VL-7B on the V* benchmark by 4.7 points while using only 23% of the vision tokens, achieving a 3x inference speedup. The code and models can be found at: https://github.com/nota-github/ERGO.
Authors: Atif Belal, Heitor R. Medeiros, Marco Pedersoli, Eric Granger
Abstract: Vision-language object detectors (VLODs) such as YOLO-World and Grounding DINO exhibit strong zero-shot generalization, but their performance degrades under distribution shift. Test-time adaptation (TTA) offers a practical way to adapt models online using only unlabeled target data. However, despite substantial progress in TTA for vision-language classification, TTA for VLODs remains largely unexplored. The only prior method relies on a mean-teacher framework that introduces significant latency and memory overhead. To this end, we introduce \textsc{VLOD-TTA}, a TTA method that leverages dense proposal overlap and image-conditioned prompts to adapt VLODs with low additional overhead. \textsc{VLOD-TTA} combines (i) an IoU-weighted entropy objective that emphasizes spatially coherent proposal clusters and mitigates confirmation bias from isolated boxes, and (ii) image-conditioned prompt selection that ranks prompts by image-level compatibility and aggregates the most informative prompt scores for detection. Our experiments across diverse distribution shifts, including artistic domains, adverse driving conditions, low-light imagery, and common corruptions, indicate that \textsc{VLOD-TTA} consistently outperforms standard TTA baselines and the prior state-of-the-art method using YOLO-World and Grounding DINO. Code : https://github.com/imatif17/VLOD-TTA
Authors: Yu Kiu (Idan), Lau, Chao Chen, Ge Jin, Chen Feng
Abstract: Sequential Visual Place Recognition (Seq-VPR) leverages transformers to capture spatio-temporal features effectively. In practice, a transformer-based Seq-VPR model should be flexible to the number of frames per sequence (seq- length), deliver fast inference, and have low memory usage to meet real-time constraints. However, existing approaches prioritize performance at the expense of flexibility and effi- ciency. To address this gap, we propose Adapt-STformer, a Seq-VPR method built around our novel Recurrent Deformable Transformer Encoder (Recurrent-DTE), which uses an iterative recurrent mechanism to fuse information from multiple sequen- tial frames. This design naturally supports variable seq-lengths, fast inference, and low memory usage. Experiments on the Nordland, Oxford, and NuScenes datasets show that Adapt- STformer boosts recall by up to 17% while reducing sequence extraction time by 36% and lowering memory usage by 35% relative to our best comparable baseline. Our code is released at https://ai4ce.github.io/Adapt-STFormer/.
Authors: Yu Huang, Zelin Peng, Changsong Wen, Xiaokang Yang, Wei Shen
Abstract: Affordance segmentation aims to decompose 3D objects into parts that serve distinct functional roles, enabling models to reason about object interactions rather than mere recognition. Existing methods, mostly following the paradigm of 3D semantic segmentation or prompt-based frameworks, struggle when geometric cues are weak or ambiguous, as sparse point clouds provide limited functional information. To overcome this limitation, we leverage the rich semantic knowledge embedded in large-scale 2D Vision Foundation Models (VFMs) to guide 3D representation learning through a cross-modal alignment mechanism. Specifically, we propose Cross-Modal Affinity Transfer (CMAT), a pretraining strategy that compels the 3D encoder to align with the semantic structures induced by lifted 2D features. CMAT is driven by a core affinity alignment objective, supported by two auxiliary losses, geometric reconstruction and feature diversity, which together encourage structured and discriminative feature learning. Built upon the CMAT-pretrained backbone, we employ a lightweight affordance segmentor that injects text or visual prompts into the learned 3D space through an efficient cross-attention interface, enabling dense and prompt-aware affordance prediction while preserving the semantic organization established during pretraining. Extensive experiments demonstrate consistent improvements over previous state-of-the-art methods in both accuracy and efficiency.
Authors: Zeqing Wang, Xinyu Wei, Bairui Li, Zhen Guo, Jinrui Zhang, Hongyang Wei, Keze Wang, Lei Zhang
Abstract: The recent rapid advancement of Text-to-Video (T2V) generation technologies are engaging the trained models with more world model ability, making the existing benchmarks increasingly insufficient to evaluate state-of-the-art T2V models. First, current evaluation dimensions, such as per-frame aesthetic quality and temporal consistency, are no longer able to differentiate state-of-the-art T2V models. Second, event-level temporal causality-an essential property that differentiates videos from other modalities-remains largely unexplored. Third, existing benchmarks lack a systematic assessment of world knowledge, which are essential capabilities for building world models. To address these issues, we introduce VideoVerse, a comprehensive benchmark focusing on evaluating whether the current T2V model could understand complex temporal causality and world knowledge to synthesize videos. We collect representative videos across diverse domains and extract their event-level descriptions with inherent temporal causality, which are then rewritten into text-to-video prompts by independent annotators. For each prompt, we design ten evaluation dimensions covering dynamic and static properties, resulting in 300 prompts, 815 events, and 793 evaluation questions. Consequently, a human preference-aligned QA-based evaluation pipeline is developed by using modern vision-language models to systematically benchmark leading open- and closed-source T2V systems, revealing the current gap between T2V models and desired world modeling abilities.
Authors: Minkwan Kim, Seungmin Lee, Junho Kim, Young Min Kim
Abstract: Recent advances in novel-view synthesis can create the photo-realistic visualization of real-world environments from conventional camera captures. However, the everyday environment experiences frequent scene changes, which require dense observations, both spatially and temporally, that an ordinary setup cannot cover. We propose long-term Gaussian scene chronology from sparse-view updates, coined LTGS, an efficient scene representation that can embrace everyday changes from highly under-constrained casual captures. Given an incomplete and unstructured 3D Gaussian Splatting (3DGS) representation obtained from an initial set of input images, we robustly model the long-term chronology of the scene despite abrupt movements and subtle environmental variations. We construct objects as template Gaussians, which serve as structural, reusable priors for shared object tracks. Then, the object templates undergo a further refinement pipeline that modulates the priors to adapt to temporally varying environments given few-shot observations. Once trained, our framework is generalizable across multiple time steps through simple transformations, significantly enhancing the scalability for a temporal evolution of 3D environments. As existing datasets do not explicitly represent the long-term real-world changes with a sparse capture setup, we collect real-world datasets to evaluate the practicality of our pipeline. Experiments demonstrate that our framework achieves superior reconstruction quality compared to other baselines while enabling fast and light-weight updates.
Authors: Bingyu Li, Feiyu Wang, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li
Abstract: Most existing underwater instance segmentation approaches are constrained by close-vocabulary prediction, limiting their ability to recognize novel marine categories. To support evaluation, we introduce \textbf{MARIS} (\underline{Mar}ine Open-Vocabulary \underline{I}nstance \underline{S}egmentation), the first large-scale fine-grained benchmark for underwater Open-Vocabulary (OV) segmentation, featuring a limited set of seen categories and diverse unseen categories. Although OV segmentation has shown promise on natural images, our analysis reveals that transfer to underwater scenes suffers from severe visual degradation (e.g., color attenuation) and semantic misalignment caused by lack underwater class definitions. To address these issues, we propose a unified framework with two complementary components. The Geometric Prior Enhancement Module (\textbf{GPEM}) leverages stable part-level and structural cues to maintain object consistency under degraded visual conditions. The Semantic Alignment Injection Mechanism (\textbf{SAIM}) enriches language embeddings with domain-specific priors, mitigating semantic ambiguity and improving recognition of unseen categories. Experiments show that our framework consistently outperforms existing OV baselines both In-Domain and Cross-Domain setting on MARIS, establishing a strong foundation for future underwater perception research.
Authors: Xinhao Cai, Liulei Li, Gensheng Pei, Tao Chen, Jinshan Pan, Yazhou Yao, Wenguan Wang
Abstract: This paper presents a generation-based debiasing framework for object detection. Prior debiasing methods are often limited by the representation diversity of samples, while naive generative augmentation often preserves the biases it aims to solve. Moreover, our analysis reveals that simply generating more data for rare classes is suboptimal due to two core issues: i) instance frequency is an incomplete proxy for the true data needs of a model, and ii) current layout-to-image synthesis lacks the fidelity and control to generate high-quality, complex scenes. To overcome this, we introduce the representation score (RS) to diagnose representational gaps beyond mere frequency, guiding the creation of new, unbiased layouts. To ensure high-quality synthesis, we replace ambiguous text prompts with a precise visual blueprint and employ a generative alignment strategy, which fosters communication between the detector and generator. Our method significantly narrows the performance gap for underrepresented object groups, \eg, improving large/rare instances by 4.4/3.6 mAP over the baseline, and surpassing prior L2I synthesis models by 15.9 mAP for layout accuracy in generated images.
Authors: Huichan Seo, Sieun Choi, Minki Hong, Yi Zhou, Junseo Kim, Lukman Ismaila, Naome Etori, Mehul Agarwal, Zhixuan Liu, Jihie Kim, Jean Oh
Abstract: Generative image models produce striking visuals yet often misrepresent culture. Prior work has examined cultural bias mainly in text-to-image (T2I) systems, leaving image-to-image (I2I) editors underexplored. We bridge this gap with a unified evaluation across six countries, an 8-category/36-subcategory schema, and era-aware prompts, auditing both T2I generation and I2I editing under a standardized protocol that yields comparable diagnostics. Using open models with fixed settings, we derive cross-country, cross-era, and cross-category evaluations. Our framework combines standard automatic metrics, a culture-aware retrieval-augmented VQA, and expert human judgments collected from native reviewers. To enable reproducibility, we release the complete image corpus, prompts, and configurations. Our study reveals three findings: (1) under country-agnostic prompts, models default to Global-North, modern-leaning depictions that flatten cross-country distinctions; (2) iterative I2I editing erodes cultural fidelity even when conventional metrics remain flat or improve; and (3) I2I models apply superficial cues (palette shifts, generic props) rather than era-consistent, context-aware changes, often retaining source identity for Global-South targets. These results highlight that culture-sensitive edits remain unreliable in current systems. By releasing standardized data, prompts, and human evaluation protocols, we provide a reproducible, culture-centered benchmark for diagnosing and tracking cultural bias in generative image models. Project page: https://seochan99.github.io/ECB
Authors: Daichi Nagai, Ryugo Morita, Shunsuke Kitada, Hitoshi Iyatomi
Abstract: Despite the remarkable success of text-to-image diffusion models, their output of a single, flattened image remains a critical bottleneck for professional applications requiring layer-wise control. Existing solutions either rely on fine-tuning with large, inaccessible datasets or are training-free yet limited to generating isolated foreground elements, failing to produce a complete and coherent scene. To address this, we introduce the Training-free Noise Transplantation and Cultivation Diffusion Model (TAUE), a novel framework for layer-wise image generation that requires neither fine-tuning nor additional data. TAUE embeds global structural information from intermediate denoising latents into the initial noise to preserve spatial coherence, and integrates semantic cues through cross-layer attention sharing to maintain contextual and visual consistency across layers. Extensive experiments demonstrate that TAUE achieves state-of-the-art performance among training-free methods, delivering image quality comparable to fine-tuned models while improving inter-layer consistency. Moreover, it enables new applications, such as layout-aware editing, multi-object composition, and background replacement, indicating potential for interactive, layer-separated generation systems in real-world creative workflows.
Authors: Bingyu Li, Tao Huo, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li
Abstract: Accurate segmentation of marine organisms is vital for biodiversity monitoring and ecological assessment, yet existing datasets and models remain largely limited to terrestrial scenes. To bridge this gap, we introduce \textbf{AquaOV255}, the first large-scale and fine-grained underwater segmentation dataset containing 255 categories and over 20K images, covering diverse categories for open-vocabulary (OV) evaluation. Furthermore, we establish the first underwater OV segmentation benchmark, \textbf{UOVSBench}, by integrating AquaOV255 with five additional underwater datasets to enable comprehensive evaluation. Alongside, we present \textbf{Earth2Ocean}, a training-free OV segmentation framework that transfers terrestrial vision--language models (VLMs) to underwater domains without any additional underwater training. Earth2Ocean consists of two core components: a Geometric-guided Visual Mask Generator (\textbf{GMG}) that refines visual features via self-similarity geometric priors for local structure perception, and a Category-visual Semantic Alignment (\textbf{CSA}) module that enhances text embeddings through multimodal large language model reasoning and scene-aware template construction. Extensive experiments on the UOVSBench benchmark demonstrate that Earth2Ocean achieves significant performance improvement on average while maintaining efficient inference.
Authors: Xuan Yu, Tianyang Xu
Abstract: Grassmannian manifold offers a powerful carrier for geometric representation learning by modelling high-dimensional data as low-dimensional subspaces. However, existing approaches predominantly rely on static single-subspace representations, neglecting the dynamic interplay between multiple subspaces critical for capturing complex geometric structures. To address this limitation, we propose a topology-driven multi-subspace fusion framework that enables adaptive subspace collaboration on the Grassmannian. Our solution introduces two key innovations: (1) Inspired by the Kolmogorov-Arnold representation theorem, an adaptive multi-subspace modelling mechanism is proposed that dynamically selects and weights task-relevant subspaces via topological convergence analysis, and (2) a multi-subspace interaction block that fuses heterogeneous geometric representations through Fr\'echet mean optimisation on the manifold. Theoretically, we establish the convergence guarantees of adaptive subspaces under a projection metric topology, ensuring stable gradient-based optimisation. Practically, we integrate Riemannian batch normalisation and mutual information regularisation to enhance discriminability and robustness. Extensive experiments on 3D action recognition (HDM05, FPHA), EEG classification (MAMEM-SSVEPII), and graph tasks demonstrate state-of-the-art performance. Our work not only advances geometric deep learning but also successfully adapts the proven multi-channel interaction philosophy of Euclidean networks to non-Euclidean domains, achieving superior discriminability and interpretability.
Authors: Rui-Yang Ju, Kohei Yamashita, Hirotaka Kameko, Shinsuke Mori
Abstract: Kuzushiji, a pre-modern Japanese cursive script, can currently be read and understood by only a few thousand trained experts in Japan. With the rapid development of deep learning, researchers have begun applying Optical Character Recognition (OCR) techniques to transcribe Kuzushiji into modern Japanese. Although existing OCR methods perform well on clean pre-modern Japanese documents written in Kuzushiji, they often fail to consider various types of noise, such as document degradation and seals, which significantly affect recognition accuracy. To the best of our knowledge, no existing dataset specifically addresses these challenges. To address this gap, we introduce the Degraded Kuzushiji Documents with Seals (DKDS) dataset as a new benchmark for related tasks. We describe the dataset construction process, which involves the assistance of a trained Kuzushiji expert, and define two benchmark tracks: (1) Kuzushiji character and seal detection and (2) document binarization. For the Kuzushiji character and seal detection track, we provide baseline results using several recent versions of YOLO to detect Kuzushiji characters and seals. For the document binarization track, we present baseline results from traditional binarization algorithms, traditional algorithms combined with K-means clustering, two state-of-the-art (SOTA) generative adversarial network (GAN) methods, and our improved conditional GAN (cGAN)-based method. The DKDS dataset and the implementation code for baseline methods are available at https://ruiyangju.github.io/DKDS.
Authors: Xun Huang, Shijia Zhao, Yunxiang Wang, Xin Lu, Wanfa Zhang, Rongsheng Qu, Weixin Li, Yunhong Wang, Chenglu Wen
Abstract: Embodied navigation is a fundamental capability for robotic agents operating. Real-world deployment requires open vocabulary generalization and low training overhead, motivating zero-shot methods rather than task-specific RL training. However, existing zero-shot methods that build explicit 3D scene graphs often compress rich visual observations into text-only relations, leading to high construction cost, irreversible loss of visual evidence, and constrained vocabularies. To address these limitations, we introduce the Multi-modal 3D Scene Graph (M3DSG), which preserves visual cues by replacing textual relational edges with dynamically assigned images. Built on M3DSG, we propose MSGNav, a zero-shot navigation system that includes a Key Subgraph Selection module for efficient reasoning, an Adaptive Vocabulary Update module for open vocabulary support, and a Closed-Loop Reasoning module for accurate exploration reasoning. Additionally, we further identify the last mile problem in zero-shot navigation determining the feasible target location with a suitable final viewpoint, and propose a Visibility-based Viewpoint Decision module to explicitly resolve it. Comprehensive experimental results demonstrate that MSGNav achieves state-of-the-art performance on the challenging GOAT-Bench and HM3D-ObjNav benchmark. The code will be publicly available at https://github.com/ylwhxht/MSGNav.
Authors: Junpeng Jing, Weixun Luo, Ye Mao, Krystian Mikolajczyk
Abstract: Recent advances in stereo matching have focused on accuracy, often at the cost of significantly increased model size. Traditionally, the community has regarded efficient models as incapable of zero-shot ability due to their limited capacity. In this paper, we introduce Lite Any Stereo, a stereo depth estimation framework that achieves strong zero-shot generalization while remaining highly efficient. To this end, we design a compact yet expressive backbone to ensure scalability, along with a carefully crafted hybrid cost aggregation module. We further propose a three-stage training strategy on million-scale data to effectively bridge the sim-to-real gap. Together, these components demonstrate that an ultra-light model can deliver strong generalization, ranking 1st across four widely used real-world benchmarks. Remarkably, our model attains accuracy comparable to or exceeding state-of-the-art non-prior-based accurate methods while requiring less than 1% computational cost, setting a new standard for efficient stereo matching.
Authors: Runxun Zhang, Yizhou Liu, Li Dongrui, Bo XU, Jingwei Wei
Abstract: Deformable image registration (DIR) remains a fundamental yet challenging problem in medical image analysis, largely due to the prohibitively high-dimensional deformation space of dense displacement fields and the scarcity of voxel-level supervision. Existing reinforcement learning frameworks often project this space into coarse, low-dimensional representations, limiting their ability to capture spatially variant deformations. We propose MorphSeek, a fine-grained representation-level policy optimization paradigm that reformulates DIR as a spatially continuous optimization process in the latent feature space. MorphSeek introduces a stochastic Gaussian policy head atop the encoder to model a distribution over latent features, facilitating efficient exploration and coarse-to-fine refinement. The framework integrates unsupervised warm-up with weakly supervised fine-tuning through Group Relative Policy Optimization, where multi-trajectory sampling stabilizes training and improves label efficiency. Across three 3D registration benchmarks (OASIS brain MRI, LiTS liver CT, and Abdomen MR-CT), MorphSeek achieves consistent Dice improvements over competitive baselines while maintaining high label efficiency with minimal parameter cost and low step-level latency overhead. Beyond optimizer specifics, MorphSeek advances a representation-level policy learning paradigm that achieves spatially coherent and data-efficient deformation optimization, offering a principled, backbone-agnostic, and optimizer-agnostic solution for scalable visual alignment in high-dimensional settings.
Authors: Tianyang Xu, Jinjie Gu, Xuefeng Zhu, XiaoJun Wu, Josef Kittler
Abstract: With the proliferation of low altitude unmanned aerial vehicles (UAVs), visual multi-object tracking is becoming a critical security technology, demanding significant robustness even in complex environmental conditions. However, tracking UAVs using a single visual modality often fails in challenging scenarios, such as low illumination, cluttered backgrounds, and rapid motion. Although multi-modal multi-object UAV tracking is more resilient, the development of effective solutions has been hindered by the absence of dedicated public datasets. To bridge this gap, we release MM-UAV, the first large-scale benchmark for Multi-Modal UAV Tracking, integrating three key sensing modalities, e.g. RGB, infrared (IR), and event signals. The dataset spans over 30 challenging scenarios, with 1,321 synchronised multi-modal sequences, and more than 2.8 million annotated frames. Accompanying the dataset, we provide a novel multi-modal multi-UAV tracking framework, designed specifically for UAV tracking applications and serving as a baseline for future research. Our framework incorporates two key technical innovations, e.g. an offset-guided adaptive alignment module to resolve spatio mismatches across sensors, and an adaptive dynamic fusion module to balance complementary information conveyed by different modalities. Furthermore, to overcome the limitations of conventional appearance modelling in multi-object tracking, we introduce an event-enhanced association mechanism that leverages motion cues from the event modality for more reliable identity maintenance. Comprehensive experiments demonstrate that the proposed framework consistently outperforms state-of-the-art methods. To foster further research in multi-modal UAV tracking, both the dataset and source code will be made publicly available at https://xuefeng-zhu5.github.io/MM-UAV/.
Authors: Arpit Garg, Hemanth Saratchandran, Simon Lucey
Abstract: Multimodal Large Language Models (MLLMs) increasingly need to forget specific knowledge such as unsafe or private information without requiring full retraining. However, existing unlearning methods often disrupt vision language alignment, causing models to reject both harmful and benign queries. We trace this failure to the projector network during unlearning, its Jacobian becomes severely illconditioned, leading to unstable optimization and drift in cross modal embeddings. We introduce SineProject, a simple method that augments the frozen projector with sinusoidally modulated trainable parameters, improving the Jacobian's spectral conditioning and stabilizing alignment throughout unlearning. Across standard safety and privacy unlearning benchmarks using LLaVA v1.5 7B and 13B, SineProject reduces benign query refusals while achieving complete forgetting of targeted information, yielding state of the art forget retain trade offs with negligible computational overhead.
Authors: Minchong Chen, Xiaoyun Yuan, Junzhe Wan, Jianing Zhang, Jun Zhang
Abstract: The miniaturization of thermal sensors for mobile platforms inherently limits their spatial resolution and textural fidelity, leading to blurry and less informative images. Existing thermal super-resolution (SR) methods can be grouped into single-image and RGB-guided approaches: the former struggles to recover fine structures from limited information, while the latter relies on accurate and laborious cross-camera calibration, which hinders practical deployment and robustness. Here, we propose 3M-TI, a calibration-free Multi-camera cross-Modality diffusion framework for Mobile Thermal Imaging. At its core, 3M-TI integrates a cross-modal self-attention module (CSM) into the diffusion UNet, replacing the original self-attention layers to adaptively align thermal and RGB features throughout the denoising process, without requiring explicit camera calibration. This design enables the diffusion network to leverage its generative prior to enhance spatial resolution, structural fidelity, and texture detail in the super-resolved thermal images. Extensive evaluations on real-world mobile thermal cameras and public benchmarks validate our superior performance, achieving state-of-the-art results in both visual quality and quantitative metrics. More importantly, the thermal images enhanced by 3M-TI lead to substantial gains in critical downstream tasks like object detection and segmentation, underscoring its practical value for robust mobile thermal perception systems. More materials: https://github.com/work-submit/3MTI.
Authors: Rui Li, Yuanzhi Liang, Ziqi Ni, Haibing Huang, Chi Zhang, Xuelong Li
Abstract: Group Relative Policy Optimization (GRPO) enables stable and preference-oriented updates via group-wise comparisons for post-training video generation. However, GRPO directly optimizes reward-induced advantages. Under sustained optimization, the reward score can lose fidelity as a proxy for true video quality, consistent with the phenomenon described by Goodhart's Law. This leads to two recurring issues: (i) shortcut-driven optimization under composite objectives and (ii) reward saturation within prompt groups. To address these issues, we introduce TaRoS, a Target-Robust Reward Signaling framework for Video generation GRPO. TaRoS leverages component level performance assessment together with intra-group sparsity to organize multi-aspect rewards towards optimization objectives. In addition, it adaptively downweights components that exhibit saturation, thereby preserving effective optimization directions and mitigating redundancy. This maintains meaningful optimization directions and preserves within-group ranking separation, thereby preventing reward hacking and leading to more reliable policy updates. Extensive experiments show consistent improvements in visual fidelity, motion coherence, and text-video alignment over strong baselines.
Authors: Dian Zheng, Manyuan Zhang, Hongyu Li, Kai Zou, Hongbo Liu, Ziyu Guo, Kaituo Feng, Yexin Liu, Ying Luo, Hongsheng Li
Abstract: Unified multimodal models for image generation and understanding represent a significant step toward AGI and have attracted widespread attention from researchers. The main challenge of this task lies in the difficulty in establishing an optimal training paradigm due to inherent conflicting targets in understanding and generation tasks. To alleviate these conflicts and pursue higher performance, many researchers adopt varying degrees of architecture decoupling (e.g., Double image encoders, MOE/MOT architecture, or frozen MLLM). However, excessive model decoupling can lead to the loss of interleave generation ability, undermining the original intent of unified models. In this work, we aim to explore how to mitigate task conflicts without resorting to model decoupling. Firstly, we analyze why decoupling boosts performance by studying the cross-modal attention behavior of models. We observe that architecture decoupling does not solve task conflicts, but essentially drives models toward cross-modal interaction patterns of task-specific models, as seen in Qwen3-VL and HunyuanImage-3.0, and that the more thorough the decoupling, the more consistent the behavior becomes. Motivated by this observation, we propose Attention Interaction Alignment (AIA) loss, which explicitly learns task-specific multimodal interaction patterns during training. To demonstrate the generalizability of our AIA loss, we apply it to Emu3 and Janus-Pro during SFT and post-training stage respectively. Without bells and whistles, AIA not only refines cross-modal attention patterns, but also boosts both generation and understanding performance.
Authors: Zixuan Song, Jing Zhang, Di Wang, Zidie Zhou, Wenbin Liu, Haonan Guo, En Wang, Bo Du
Abstract: Cross-view geo-localization infers a location by retrieving geo-tagged reference images that visually correspond to a query image. However, the traditional satellite-centric paradigm limits robustness when high-resolution or up-to-date satellite imagery is unavailable. It further underexploits complementary cues across views (\eg, drone, satellite, and street) and modalities (\eg, language and image). To address these challenges, we propose GeoBridge, a novel model that performs bidirectional matching across views and supports language-to-image retrieval. Going beyond traditional satellite-centric formulations, GeoBridge builds on a novel semantic-anchor mechanism that bridges multi-view features through textual descriptions for robust, flexible localization. In support of this task, we construct GeoLoc, the first large-scale, cross-modal, and multi-view aligned dataset comprising over 50,000 pairs of drone, street-view panorama, and satellite images as well as their textual descriptions, collected from 36 countries, ensuring both geographic and semantic alignment. We performed broad evaluations across multiple tasks. Experiments confirm that GeoLoc pre-training markedly improves geo-location accuracy for GeoBridge while promoting cross-domain generalization and cross-modal knowledge transfer. Code, dataset, and pretrained models will be released at https://github.com/MiliLab/GeoBridge.
Authors: Yizi Chen, Sidi Wu, Tianyi Xiao, Nina Wiedemann, Loic Landrieu
Abstract: VR sketching lets users explore and iterate on ideas directly in 3D, offering a faster and more intuitive alternative to conventional CAD tools. However, existing sketch-to-shape models ignore the temporal ordering of strokes, discarding crucial cues about structure and design intent. We introduce VRSketch2Shape, the first framework and multi-category dataset for generating 3D shapes from sequential VR sketches. Our contributions are threefold: (i) an automated pipeline that generates sequential VR sketches from arbitrary shapes, (ii) a dataset of over 20k synthetic and 900 hand-drawn sketch-shape pairs across four categories, and (iii) an order-aware sketch encoder coupled with a diffusion-based 3D generator. Our approach yields higher geometric fidelity than prior work, generalizes effectively from synthetic to real sketches with minimal supervision, and performs well even on partial sketches. All data and models will be released open-source at https://chenyizi086.github.io/VRSketch2Shape_website.
Authors: Johannes Meier, Jonathan Michel, Oussema Dhaouadi, Yung-Hsu Yang, Christoph Reich, Zuria Bauer, Stefan Roth, Marc Pollefeys, Jacques Kaiser, Daniel Cremers
Abstract: Real-time monocular 3D object detection remains challenging due to severe depth ambiguity, viewpoint shifts, and the high computational cost of 3D reasoning. Existing approaches either rely on LiDAR or geometric priors to compensate for missing depth or sacrifice efficiency to achieve competitive accuracy. We introduce LeAD-M3D, a monocular 3D detector that achieves state-of-the-art accuracy and real-time inference without extra modalities. Our method is enabled by three key components. Asymmetric Augmentation Denoising Distillation (A2D2) transfers geometric knowledge from a clean-image teacher to a MixUp-noised student via a quality- and importance-weighted depth-feature loss, enabling stronger depth reasoning without LiDAR. 3D-aware Consistent Matching (CM$_{\text{3D}}$) improves prediction-to-ground truth assignment by integrating 3D MGIoU into the matching score, yielding stable and precise supervision. Finally, Confidence-Gated 3D Inference (CGI$_{\text{3D}}$) accelerates inference by restricting expensive 3D regression to confident regions. Together, these contributions set a new Pareto frontier for monocular 3D detection: LeAD-M3D achieves state-of-the-art accuracy on KITTI and Waymo, and the best reported car AP on Rope3D, while running up to 3.6$\,\times$ faster than prior high-accuracy models (e.g., MonoDiff). LeAD-M3D demonstrates that high fidelity and real-time monocular 3D detection is simultaneously attainable, without LiDAR, stereo, or strong geometric assumptions.
Authors: Haoyu Zhang, Junhan Luo, Yugang Cao, Jie Huang, Liangjian-Deng
Abstract: Pansharpening fuses a high-resolution panchromatic (PAN) image with a low-resolution multispectral (LRMS) image to produce a high-resolution multispectral (HRMS) image. A key difficulty is that jointly processing PAN and MS features often entangles spatial detail enhancement with spectral fidelity. To address this feature entanglement, we propose S2WMamba, a framework that explicitly disentangles modality-specific frequency information for highly controlled crossmodal interaction. Concretely, unlike global frequency transforms, a localized 2D Haar DWT is applied to the PAN image to precisely isolate spatial edges and textures. Concurrently, a novel channel-wise 1D Haar DWT treats each pixel's spectrum as a 1D signal, isolating the shared spectral base from band-specific variations to strictly limit spectral distortion. The resulting Spectral branch injects wavelet-extracted spatial details into MS features, while the Spatial branch refines PAN features using spectra from the DWT1D process. To overcome inadequate frequency fusion, the two branches exchange information via Mambabased cross-modulation, which explicitly models long-range dependencies across these decoupled sub-bands with linear complexity. On WV3, GF2, and QB datasets, S2WMamba matches or surpasses recent strong baselines (FusionMamba, CANNet, U2Net, PanNet), improving PSNR by up to 0.23 dB and reaching an HQNR of 0.956 on full-resolution WV3. Extensive ablations justify the modality-specific DWT placement and the parallel dual-branch architecture.
Authors: Jaeyoon Lee, Hojoon Jung, Sungtae Hwang, Jihyong Oh, Jongwon Choi
Abstract: We present COREA, the first unified three-tasks framework that couples an SDF and relightable 3D Gaussians (3DGS) to jointly support SH-based novel-view synthesis (NVS), surface reconstruction, and inverse physically-based rendering (inverse PBR). While recent relightable 3DGS methods have progressed, inverse PBR remains bottlenecked by normal estimation, as the discrete nature of 3DGS often yields oversmoothed and unstable normals. To address this limitation, COREA couples the complementary geometric properties of an SDF and relightable 3DGS on a shared underlying surface, where geometry-constrained relightable 3DGS provides reliable depth signals to anchor SDF geometry and the continuous SDF normal field provides spatially consistent supervision for Gaussian normal learning. We couple these signals through depth-guided alignment and normal supervision with normal-aware densification, and introduce Dual-Density Control to regulate densification by balancing photometric and geometric gradients for stable, memory-efficient training. Experiments on standard benchmarks show that COREA is the only framework that supports all three tasks, achieving competitive performance overall, with particularly superior results in inverse PBR.
Authors: Chen Ziwen, Hao Tan, Peng Wang, Zexiang Xu, Li Fuxin
Abstract: Recent advances in generalizable Gaussian splatting (GS) have enabled feed-forward reconstruction of scenes from tens of input views. Long-LRM notably scales this paradigm to 32 input images at $950\times540$ resolution, achieving 360{\deg} scene-level reconstruction in a single forward pass. However, directly predicting millions of Gaussian parameters at once remains highly error-sensitive: small inaccuracies in positions or other attributes lead to noticeable blurring, particularly in fine structures such as text. In parallel, implicit representation methods such as LVSM and LaCT have demonstrated significantly higher rendering fidelity by compressing scene information into model weights rather than explicit Gaussians, and decoding RGB frames using the full transformer or TTT backbone. However, this computationally intensive decompression process for every rendered frame makes real-time rendering infeasible. These observations raise key questions: Is the deep, sequential "decompression" process necessary? Can we retain the benefits of implicit representations while enabling real-time performance? We address these questions with Long-LRM++, a model that adopts a semi-explicit scene representation combined with a lightweight decoder. Long-LRM++ matches the rendering quality of LaCT on DL3DV while achieving real-time 14 FPS rendering on an A100 GPU, overcoming the speed limitations of prior implicit methods. Our design also scales to 64 input views at the $950\times540$ resolution, demonstrating strong generalization to increased input lengths. Additionally, Long-LRM++ delivers superior novel-view depth prediction on ScanNetv2 compared to direct depth rendering from Gaussians. Extensive ablation studies validate the effectiveness of each component in the proposed framework.
Authors: Nazanin Mahjourian, Vinh Nguyen
Abstract: Many manufacturing environments operate in low-light conditions or within enclosed machines where conventional vision systems struggle. Infrared cameras provide complementary advantages in such environments. Simultaneously, supervised AI systems require large labeled datasets, which makes zero-shot learning frameworks more practical for applications including infrared cameras. Recent advances in vision-language foundation models (VLMs) offer a new path in zero-shot predictions from paired image-text representations. However, current VLMs cannot understand infrared camera data since they are trained on RGB data. This work introduces VLM-IRIS (Vision-Language Models for InfraRed Industrial Sensing), a zero-shot framework that adapts VLMs to infrared data by preprocessing infrared images captured by a FLIR Boson sensor into RGB-compatible inputs suitable for CLIP-based encoders. We demonstrate zero-shot workpiece presence detection on a 3D printer bed where temperature differences between the build plate and workpieces make the task well-suited for thermal imaging. VLM-IRIS converts the infrared images to magma representation and applies centroid prompt ensembling with a CLIP ViT-B/32 encoder to achieve high accuracy on infrared images without any model retraining. These findings demonstrate that the proposed improvements to VLMs can be effectively extended to thermal applications for label-free monitoring.
Authors: Bowen Wen, Shaurya Dewan, Stan Birchfield
Abstract: Stereo foundation models achieve strong zero-shot generalization but remain computationally prohibitive for real-time applications. Efficient stereo architectures, on the other hand, sacrifice robustness for speed and require costly per-domain fine-tuning. To bridge this gap, we present Fast-FoundationStereo, a family of architectures that achieve, for the first time, strong zero-shot generalization at real-time frame rate. We employ a divide-and-conquer acceleration strategy with three components: (1) knowledge distillation to compress the hybrid backbone into a single efficient student; (2) blockwise neural architecture search for automatically discovering optimal cost filtering designs under latency budgets, reducing search complexity exponentially; and (3) structured pruning for eliminating redundancy in the iterative refinement module. Furthermore, we introduce an automatic pseudo-labeling pipeline used to curate 1.4M in-the-wild stereo pairs to supplement synthetic training data and facilitate knowledge distillation. The resulting model can run over 10x faster than FoundationStereo while closely matching its zero-shot accuracy, thus establishing a new state-of-the-art among real-time methods. Project page: https://nvlabs.github.io/Fast-FoundationStereo/
Authors: Yiwei Lyu, Chenhui Zhao, Soumyanil Banerjee, Shixuan Liu, Akshay Rao, Akhil Kondepudi, Honglak Lee, Todd C. Hollon
Abstract: Training vision models with language supervision enables general and transferable representations. However, many visual domains, especially non-object-centric domains such as medical imaging and remote sensing, contain itemized text annotations: multiple text items describing distinct and semantically independent findings within a single image. Such supervision differs from standard multi-caption supervision, where captions are redundant or highly overlapping. Here, we introduce ItemizedCLIP, a framework for learning complete and explainable visual representations from itemized text supervision. ItemizedCLIP employs a cross-attention module to produce text item-conditioned visual embeddings and a set of tailored objectives that jointly enforce item independence (distinct regions for distinct items) and representation completeness (coverage of all items). Across four domains with naturally itemized text supervision (brain MRI, head CT, chest CT, remote sensing) and one additional synthetically itemized dataset, ItemizedCLIP achieves substantial improvements in zero-shot performance and fine-grained interpretability over baselines. The resulting ItemizedCLIP representations are semantically grounded, item-differentiable, complete, and visually interpretable. Our code is available at https://github.com/MLNeurosurg/ItemizedCLIP.
Authors: Yuxuan Han, Xin Ming, Tianxiao Li, Zhuofan Shen, Qixuan Zhang, Lan Xu, Feng Xu
Abstract: Existing methods achieve high-quality facial albedo capture under controllable lighting, which increases capture cost and limits usability. We propose WildCap, a novel method for high-quality facial albedo capture from a smartphone video recorded in the wild. To disentangle high-quality albedo from complex lighting effects in in-the-wild captures, we propose a novel hybrid inverse rendering framework. We first apply a data-driven method, i.e., SwitchLight, to convert the captured images into more constrained conditions and then adopt model-based inverse rendering. However, unavoidable local artifacts in network predictions, such as shadow-baking, are non-physical and thus hinder accurate inverse rendering of lighting and material. To address this, we propose a novel texel grid lighting model to explain non-physical effects as clean albedo illuminated by local physical lighting. During optimization, we jointly sample a diffusion prior for the albedo map and optimize the lighting, effectively resolving scale ambiguity between local lights and albedo. Other reflectance maps are then predicted from the albedo. Our method achieves significantly better results than prior arts in the same capture setup, closing the quality gap between in-the-wild and controllable recordings by a large margin.
Authors: Jelena Bratuli\'c, Sudhanshu Mittal, Thomas Brox, Christian Rupprecht
Abstract: Feed-forward 3D reconstruction models such as DUSt3R, VGGT, and Depth Anything 3 (DA3) are transformer-based foundation models that infer camera geometry and dense scene structure in a single forward pass. Trained at scale in a supervised fashion, they raise a central question: do these models build upon geometric principles akin to traditional multi-view pipelines, or do they primarily rely on learned priors arising from the large-scale training setup? We find that epipolar geometry emerges within the intermediate layers of all three models and is causally linked to correspondence patterns in attention heads. To study this, we perform a systematic analysis of their internal representations across three real-world datasets and a controlled synthetic dataset. We quantify geometric understanding by probing intermediate features, analyzing attention patterns to identify correspondence matching patterns, and performing targeted interventions at the attention level. Further, we assess the role of learned priors by applying challenging input-level perturbations, such as occlusions, scene ambiguities, and varying camera configurations, and compare them against classical multi-stage reconstruction pipelines.
Authors: Dashti A. Ali, Aras T. Asaad, Jacob J. Peoples, Ahmad Bashir Barekzai, Camila Vilela, Hala Khasawneh, Jayasree Chakraborty, Jo\~ao Miranda, Mohammad Hamghalam, Natalie Gangai, Natally Horvat, Richard K. G. Do, Alice C. Wei, Amber L. Simpson
Abstract: The development of machine learning (ML) models based on computed tomography (CT) imaging has been a major focus due to the promise that imaging holds for diagnosis, staging, and prognostication. These models often rely on the extraction of hand-crafted features, incorporating robust feature engineering improves the performance of these models. Topological data analysis (TDA), based on the mathematical field of algebraic topology, focuses on data from a topological perspective, extracting deeper insight and higher dimensional structures. Persistent homology (PH), a fundamental tool in TDA, extracts topological features such as connected components, cycles, and voids. A popular approach to construct PH from 3D CT images is to utilize the 3D cubical complex filtration, a method adapted for grid-structured data. However, this approach is subject to poor performance and high computational cost with higher resolution CT images. This study introduces a novel patch-based PH construction approach tailored for volumetric CT imaging data that improves performance and reduces computational time. This study conducts a series of systematic experiments to comprehensively analyze the performance of the proposed method with various parameters and benchmarks against the 3D cubical complex algorithm and radiomic features. Our results highlight the dominance of the patch-based TDA approach in terms of both classification performance and computational time. The proposed approach outperformed the cubical complex method and radiomic features, achieving average improvement of 7.2%, 3.6%, 2.7%, 8.0%, and 7.2% in accuracy, AUC, sensitivity, specificity, and F1 score, respectively, across all datasets. Finally, we provide a convenient python package, Patch-TDA, to facilitate the utilization of the proposed approach.
Authors: Zhou Tao, Shida Wang, Yongxiang Hua, Haoyu Cao, Linli Xu
Abstract: Multimodal Large Language Models have achieved impressive performance on a variety of vision-language tasks, yet their fine-grained visual perception and precise spatial reasoning remain limited. In this work, we introduce DiG (Differential Grounding), a novel proxy task framework where MLLMs learn fine-grained perception by identifying and localizing all differences between similar image pairs without prior knowledge of their number. To support scalable training, we develop an automated 3D rendering-based data generation pipeline that produces high-quality paired images with fully controllable discrepancies. To address the sparsity of difference signals, we further employ curriculum learning that progressively increases complexity from single to multiple differences, enabling stable optimization. Extensive experiments demonstrate that DiG significantly improves model performance across a variety of visual perception benchmarks and that the learned fine-grained perception skills transfer effectively to standard downstream tasks, including RefCOCO, RefCOCO+, RefCOCOg, and general multimodal perception benchmarks. Our results highlight differential grounding as a scalable and robust approach for advancing fine-grained visual reasoning in MLLMs.
Authors: Danxu Liu, Di Wang, Hebaixu Wang, Haoyang Chen, Wentao Jiang, Yilin Cheng, Haonan Guo, Wei Cui, Jing Zhang
Abstract: Synthetic Aperture Radar (SAR) imagery plays a critical role in all-weather, day-and-night remote sensing applications. However, existing SAR-oriented deep learning is constrained by data scarcity, while the physically grounded speckle noise in SAR imagery further hampers fine-grained semantic representation learning. To address these challenges, we propose SARMAE, a Noise-Aware Masked Autoencoder for self-supervised SAR representation learning. Specifically, we construct SAR-1M, the first million-scale SAR dataset, with additional paired optical images, to enable large-scale pre-training. Building upon this, we design Speckle-Aware Representation Enhancement (SARE), which injects SAR-specific speckle noise into masked autoencoders to facilitate noise-aware and robust representation learning. Furthermore, we introduce Semantic Anchor Representation Constraint (SARC), which leverages paired optical priors to align SAR features and ensure semantic consistency. Extensive experiments across multiple SAR datasets demonstrate that SARMAE achieves state-of-the-art performance on classification, detection, and segmentation tasks. Code and models will be available at https://github.com/MiliLab/SARMAE.
Authors: Lin Xi, Yingliang Ma, Xiahai Zhuang
Abstract: We introduce a novel FSVOS model that employs a local matching strategy to restrict the search space to the most relevant neighboring pixels. Rather than relying on inefficient standard im2col-like implementations (e.g., spatial convolutions, depthwise convolutions and feature-shifting mechanisms) or hardware-specific CUDA kernels (e.g., deformable and neighborhood attention), which often suffer from limited portability across non-CUDA devices, we reorganize the local sampling process through a direction-based sampling perspective. Specifically, we implement a non-parametric sampling mechanism that enables dynamically varying sampling regions. This approach provides the flexibility to adapt to diverse spatial structures without the computational costs of parametric layers and the need for model retraining. To further enhance feature coherence across frames, we design a supervised spatio-temporal contrastive learning scheme that enforces consistency in feature representations. In addition, we introduce a publicly available benchmark dataset for multi-object segmentation in X-ray angiography videos (MOSXAV), featuring detailed, manually labeled segmentation ground truth. Extensive experiments on the CADICA, XACV, and MOSXAV datasets show that our proposed FSVOS method outperforms current state-of-the-art video segmentation methods in terms of segmentation accuracy and generalization capability (i.e., seen and unseen categories). This work offers enhanced flexibility and potential for a wide range of clinical applications. Code is available at https://github.com/xilin-x/XRAVOS
Authors: Yifan Wang, Yanyu Li, Gordon Guocheng Qian, Sergey Tulyakov, Yun Fu, Anil Kag
Abstract: Video diffusion alignment has been heavily relied on scalar rewards. These rewards are typically derived from learned reward models in human preference datasets, requiring additional training and extensive collection. Moreover, scalar rewards provide coarse, global supervision, offering limited prompt-generation mismatch credit assignment and making models prone to reward exploitation and unstable optimization. We propose Diffusion-DRF, a free, rich, and differentiable reward framework for video diffusion fine-tuning. Diffusion-DRF employs a frozen, off-the-shelf Vision-Language Model (VLM) as the critic, eliminating the need for reward model training. Instead of relying on a single scalar reward, it decomposes each user prompt into multi-dimensional questions with freeform dense VQA explanation queries, yielding information-rich feedback. By direct differentiable optimization over this rich feedback, Diffusion-DRF achieves stable reward-based tuning without preference datasets collection. Diffusion-DRF achieves significant gains both quantitatively and qualitatively, outperforming state-of-the-art Flow-GRPO by 4.74% in overall performance on unseen VBench-2.0.
Authors: Yu Wang, Yi Wang, Rui Dai, Yujie Wang, Kaikui Liu, Xiangxiang Chu, Yansheng Li
Abstract: As hubs of human activity, urban surfaces consist of a wealth of semantic entities. Segmenting these various entities from satellite imagery is crucial for a range of downstream applications. Current advanced segmentation models can reliably segment entities defined by physical attributes (e.g., buildings, water bodies) but still struggle with socially defined categories (e.g., schools, parks). In this work, we achieve socio-semantic segmentation by vision-language model reasoning. To facilitate this, we introduce the Urban Socio-Semantic Segmentation dataset named SocioSeg, a new resource comprising satellite imagery, digital maps, and pixel-level labels of social semantic entities organized in a hierarchical structure. Additionally, we propose a novel vision-language reasoning framework called SocioReasoner that simulates the human process of identifying and annotating social semantic entities via cross-modal recognition and multi-stage reasoning. We employ reinforcement learning to optimize this non-differentiable process and elicit the reasoning capabilities of the vision-language model. Experiments demonstrate our approach's gains over state-of-the-art models and strong zero-shot generalization. The dataset and code are open-sourced under the Apache License 2.0 at https://github.com/AMAP-ML/SocioReasoner.
Authors: Zaibin Zhang, Yuhan Wu, Lianjie Jia, Yifan Wang, Zhongbo Zhang, Yijiang Li, Binghao Ran, Fuxi Zhang, Zhuohan Sun, Zhenfei Yin, Lijun Wang, Huchuan Lu
Abstract: While contemporary Vision-Language Models (VLMs) excel at 2D visual understanding, they remain constrained by a passive, 2D-centric paradigm that severely limits genuine 3D spatial reasoning. To bridge this gap, we introduce Think3D, a novel framework that equips VLM agents with interactive, 3D chain-of-thought reasoning capabilities. By integrating a suite of 3D manipulation tools, Think3D transforms passive perception into active spatial exploration, closely mirroring human geometric reasoning. We demonstrate that Think3D acts as a highly effective zero-shot plug-in for state-of-the-art closed-source models (e.g., GPT-4.1, Gemini 2.5 Pro), yielding absolute performance gains of +7.8% on BLINK Multi-view and MindCube, and +4.7% on VSI-Bench. Furthermore, to optimize tool-use in smaller open-weight models, we propose Think3D-RL, a reinforcement learning paradigm designed to autonomously learn spatial exploration strategies. When applied to Qwen3-VL-4B, Think3D-RL amplifies the performance gain from a marginal +0.7% to a substantial +10.7%. Notably, this RL formulation induces an exploration policy that qualitatively aligns with the sophisticated behavior of much larger models, entirely circumventing the need for costly operation-trajectory annotations. Ultimately, Think3D establishes tool-augmented active exploration as an effective paradigm for unlocking human-like 3D reasoning in multimodal agents. Code, models, and data are available at https://github.com/zhangzaibin/spagent.
Authors: Kai Wittenmayer, Sukrut Rao, Amin Parchami-Araghi, Bernt Schiele, Jonas Fischer
Abstract: Language-aligned vision foundation models perform strongly across diverse downstream tasks. Yet, their learned representations remain opaque, making interpreting their decision-making difficult. Recent work decompose these representations into human-interpretable concepts, but provide poor spatial grounding and are limited to image classification tasks. In this work, we propose CFM, a language-aligned concept foundation model for vision that provides fine-grained concepts, which are human-interpretable and spatially grounded in the input image. When paired with a foundation model with strong semantic representations, we get explanations for any of its downstream tasks. Examining local co-occurrence dependencies of concepts allows us to define concept relationships through which we improve concept naming and obtain richer explanations. On benchmark data, we show that CFM provides performance on classification, segmentation, and captioning that is competitive with opaque foundation models while providing fine-grained, high quality concept-based explanations. Code at https://github.com/kawi19/CFM.
Authors: Xin Zhang, Liangxiu Han, Tam Sobeih, Yue Shi, Yalin Zheng, Uazman Alam, Maryam Ferdousi, Rayaz Malik
Abstract: Corneal Confocal Microscopy (CCM) is a sensitive tool for assessing small-fiber damage in Diabetic Peripheral Neuropathy (DPN), yet the development of robust, automated deep learning-based diagnostic models is limited by scarce labelled data and fine-grained variability in corneal nerve morphology. Although Artificial Intelligence (AI)-driven foundation generative models excel at natural image synthesis, they often struggle in medical imaging due to limited domain-specific training, compromising the anatomical fidelity required for clinical analysis. To overcome these limitations, we propose a Weight-Decomposed Low-Rank Adaptation (WDLoRA)-based multimodal generative framework for clinically guided CCM image synthesis. WDLoRA is a parameter-efficient fine-tuning (PEFT) mechanism that decouples magnitude and directional weight updates, enabling foundation generative models to independently learn the orientation (nerve topology) and intensity (stromal contrast) required for medical realism. By jointly conditioning on nerve segmentation masks and disease-specific clinical prompts, the model synthesises anatomically coherent images across the DPN spectrum (Control, T1NoDPN, T1DPN). A comprehensive three-pillar evaluation demonstrates that the proposed framework achieves state-of-the-art visual fidelity (Fr\'echet Inception Distance (FID): 5.18) and structural integrity (Structural Similarity Index Measure (SSIM): 0.630), significantly outperforming GAN and standard diffusion baselines. Crucially, the synthetic images preserve gold-standard clinical biomarkers and are statistically equivalent to real patient data. When used to train automated diagnostic models, the synthetic dataset improves downstream diagnostic accuracy by 2.1% and segmentation performance by 2.2%, validating the framework's potential to alleviate data bottlenecks in medical AI.
Authors: Nadav Kadvil, Malak Fares, Ayellet Tal
Abstract: Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses. We introduce a general, efficient, and training-free defense that combines image transformations with agentic data consolidation to recover correct model behavior. A key component of our approach is a two-stage detection mechanism that quickly filters out the majority of clean inputs. We first assess image consistency under content-preserving transformations at negligible computational cost. For more challenging cases, we examine discrepancies in a text-embedding space. Only when necessary do we invoke a powerful LLM to resolve attack-induced divergences. A key idea is to consolidate multiple responses, leveraging both their similarities and their differences. We show that our method achieves state-of-the-art accuracy while maintaining notable efficiency: most clean images skip costly processing, and even in the presence of numerous adversarial examples, the overhead remains minimal.
Authors: Shengqiong Wu, Bobo Li, Xinkai Wang, Xiangtai Li, Lei Cui, Furu Wei, Shuicheng Yan, Hao Fei, Tat-seng Chua
Abstract: Unified Vision-Language Models (UVLMs) aim to advance multimodal learning by supporting both understanding and generation within a single framework. However, existing approaches largely focus on architectural unification while overlooking the need for explicit interaction between the two capabilities during task solving. As a result, current models treat understanding and generation as parallel skills rather than synergistic processes. To achieve real synergy, we introduce the interleaved Analyzing-Drafting problem-solving loop (AD-Loop), a new think paradigm that dynamically alternates between analytic and drafting operations. By interleaving textual thoughts with visual thoughts, AD-Loop enables models to iteratively refine both comprehension and outputs, fostering genuine synergy. To train this mechanism, we design a two-stage strategy: supervised learning on interleaved thought data to initialize alternation, followed by reinforcement learning to promote adaptive and autonomous control. Extensive experiments demonstrate that AD-Loop consistently improves performance across standard benchmarks for both understanding and generation, with strong transferability to various UVLMs architectures. Visual analyses further validate the effectiveness of implicit visual thoughts. These results highlight AD-Loop as a principled and broadly applicable strategy for synergizing comprehension and creation. The project page is at https://sqwu.top/AD-Loop.
Authors: Di Zhang, Zhangpeng Gong, Xiaobo Pang, Jiashuai Liu, Junbo Lu, Hao Cui, Jiusong Ge, Zhi Zeng, Kai Yi, Yinghua Li, Si Liu, Tingsong Yu, Haoran Wang, Mireia Crispin-Ortuzar, Weimiao Yu, Chen Li, Zeyu Gao
Abstract: Foundation models have recently achieved impressive success in computational pathology, demonstrating strong generalization across diverse histopathology tasks. However, existing models overlook the heterogeneous and non-uniform organization of pathological regions of interest (ROIs) because they rely on natural image backbones not tailored for tissue morphology. Consequently, they often fail to capture the coherent tissue architecture beyond isolated patches, limiting interpretability and clinical relevance. To address these challenges, we present Cross-modal Adaptive Region Encoder (CARE), a foundation model for pathology that automatically partitions WSIs into several morphologically relevant regions. Specifically, CARE employs a two-stage pretraining strategy: (1) a self-supervised unimodal pretraining stage that learns morphological representations from 34,277 whole-slide images (WSIs) without segmentation annotations, and (2) a cross-modal alignment stage that leverages RNA and protein profiles to refine the construction and representation of adaptive regions. This molecular guidance enables CARE to identify biologically relevant patterns and generate irregular yet coherent tissue regions, selecting the most representative area as ROI. CARE supports a broad range of pathology-related tasks, using either the ROI feature or the slide-level feature obtained by aggregating adaptive regions. Based on only one-tenth of the pretraining data typically used by mainstream foundation models, CARE achieves superior average performance across 33 downstream benchmarks, including morphological classification, molecular prediction, and survival analysis, and outperforms other foundation model baselines overall.
Authors: Hexin Dong, Yi Lin, Pengyu Zhou, Xuan Zhong Feng, Alan Clint Legasto, Mingquan Lin, Hao Chen, Yuzhe Yang, George Shih, Yifan Peng
Abstract: Chest X-ray (CXR) interpretation is hindered by the long-tailed distribution of pathologies and the open-world nature of clinical environments. Existing benchmarks often rely on closed-set classes from single institutions, failing to capture the prevalence of rare diseases or the appearance of novel findings. To address this, we present the CXR-LT 2026 challenge. This third iteration of the benchmark introduces a multi-center dataset comprising over 145,000 images from PadChest and NIH Chest X-ray datasets. The challenge defines two core tasks: (1) Robust Multi-Label Classification on 30 known classes and (2) Open-World Generalization to 6 unseen (out-of-distribution) rare disease classes. We report the results of the top-performing teams, evaluating them via mean Average Precision (mAP), AUROC, and F1-score. The winning solutions achieved an mAP of 0.5854 on Task 1 and 0.4315 on Task 2, demonstrating that large-scale vision-language pre-training significantly mitigates the performance drop typically associated with zero-shot diagnosis.
Authors: Muquan Li, Hang Gou, Yingyi Ma, Rongzheng Wang, Ke Qin, Tao He
Abstract: Decoupled dataset distillation (DD) compresses large corpora into a few synthetic images by matching a frozen teacher's statistics. However, current residual-matching pipelines rely on static real patches, creating a fit-complexity gap and a pull-to-anchor effect that reduce intra-class diversity and hurt generalization. To address these issues, we introduce RETA -- a Retrieval and Topology Alignment framework for decoupled DD. First, Dynamic Retrieval Connection (DRC) selects a real patch from a prebuilt pool by minimizing a fit-complexity score in teacher feature space; the chosen patch is injected via a residual connection to tighten feature fit while controlling injected complexity. Second, Persistent Topology Alignment (PTA) regularizes synthesis with persistent homology: we build a mutual k-NN feature graph, compute persistence images of components and loops, and penalize topology discrepancies between real and synthetic sets, mitigating pull-to-anchor effect. Across CIFAR-100, Tiny-ImageNet, ImageNet-1K, and multiple ImageNet subsets, RETA consistently outperforms various baselines under comparable time and memory, especially reaching 64.3% top-1 accuracy on ImageNet-1K with ResNet-18 at 50 images per class, +3.1% over the best prior.
Authors: Pr\'axedes Mart\'inez-Moreno, Andrea Valsecchi, Pablo Mesejo, Pilar Navarro-Ram\'irez, Valentino Lugli, Sergio Damas
Abstract: Craniofacial Superimposition is a forensic technique for identifying skeletal remains by comparing a post-mortem skull with ante-mortem facial photographs. A critical step in this process is Skull-Face Overlay (SFO). This stage involves aligning a 3D skull model with a 2D facial image, typically guided by cranial and facial landmarks' correspondence. However, its accuracy is undermined by individual variability in soft-tissue thickness, introducing significant uncertainty into the overlay. This paper introduces Lilium, an automated evolutionary method to enhance the accuracy and robustness of SFO. Lilium explicitly models soft-tissue variability using a 3D cone-based representation whose parameters are optimized via a Differential Evolution algorithm. The method enforces anatomical, morphological, and photographic plausibility through a combination of constraints: landmark matching, camera parameter consistency, head pose alignment, skull containment within facial boundaries, and region parallelism. This emulation of the usual forensic practitioners' approach leads Lilium to outperform the state-of-the-art method in terms of both accuracy and robustness.
Authors: Wang Chen, Yuhui Zeng, Yongdong Luo, Tianyu Xie, Luojun Lin, Jiayi Ji, Yan Zhang, Xiawu Zheng
Abstract: Frame selection is crucial due to high frame redundancy and limited context windows when applying Large Vision-Language Models (LVLMs) to long videos. Current methods typically select frames with high relevance to a given query, resulting in a disjointed set of frames that disregard the narrative structure of video. In this paper, we introduce Wavelet-based Frame Selection by Detecting Semantic Boundary (WFS-SB), a training-free framework that presents a new perspective: effective video understanding hinges not only on high relevance but, more importantly, on capturing semantic shifts - pivotal moments of narrative change that are essential to comprehending the holistic storyline of video. However, direct detection of abrupt changes in the query-frame similarity signal is often unreliable due to high-frequency noise arising from model uncertainty and transient visual variations. To address this, we leverage the wavelet transform, which provides an ideal solution through its multi-resolution analysis in both time and frequency domains. By applying this transform, we decompose the noisy signal into multiple scales and extract a clean semantic change signal from the coarsest scale. We identify the local extrema of this signal as semantic boundaries, which segment the video into coherent clips. Building on this, WFS-SB comprises a two-stage strategy: first, adaptively allocating a frame budget to each clip based on a composite importance score; and second, within each clip, employing the Maximal Marginal Relevance approach to select a diverse yet relevant set of frames. Extensive experiments show that WFS-SB significantly boosts LVLM performance, e.g., improving accuracy by 5.5% on VideoMME, 9.5% on MLVU, and 6.2% on LongVideoBench, consistently outperforming state-of-the-art methods. Our code is available at https://github.com/MAC-AutoML/WFS-SB.
Authors: Haitian Wang, Xinyu Wang, Muhammad Ibrahim, Dustin Severtson, Ajmal Mian
Abstract: Accurate weed mapping in cereal fields requires pixel-level segmentation from UAV imagery that remains reliable across fields, seasons, and illumination. Existing multispectral pipelines often depend on thresholded vegetation indices, which are brittle under radiometric drift and mixed crop--weed pixels, or on single-stream CNN and Transformer backbones that ingest stacked bands and indices, where radiance cues and normalized index cues interfere and reduce sensitivity to small weed clusters embedded in crop canopy. We propose VISA, a two-stream segmentation network that decouples these cues and fuses them at native resolution. The radiance stream learns from calibrated five-band reflectance using local residual convolutions, channel recalibration, spatial gating, and skip-connected decoding, which preserve fine textures, row boundaries, and small weed structures that are often weakened after ratio-based index compression. The index stream operates on vegetation-index maps with windowed self-attention to model local structure efficiently, state-space layers to propagate field-scale context without quadratic attention cost, and Slot Attention to form stable region descriptors that improve discrimination of sparse weeds under canopy mixing. To support supervised training and deployment-oriented evaluation, we introduce BAWSeg, a four-year UAV multispectral dataset collected over commercial barley paddocks in Western Australia, providing radiometrically calibrated blue, green, red, red edge, and near-infrared orthomosaics, derived vegetation indices, and dense crop, weed, and other labels with leakage-free block splits. On BAWSeg, VISA achieves 75.6% mIoU and 63.5% weed IoU with 22.8 M parameters, outperforming a multispectral SegFormer-B1 baseline by 1.2 mIoU and 1.9 weed IoU. Under cross-plot and cross-year protocols, VISA maintains 71.2% and 69.2% mIoU, respectively.
Authors: Zhen Wang, Youcan Xu, Jun Xiao, Long Chen
Abstract: Video motion transfer aims to generate a target video that inherits motion patterns from a source video while rendering new scenes. Existing training-free approaches focus on constructing motion guidance based on the intermediate outputs of pre-trained T2V models, which results in heavy computational overhead and limited flexibility. In this paper, we present FlowMotion, a novel training-free framework that enables efficient and flexible motion transfer by directly leveraging the predicted outputs of flow-based T2V models. Our key insight is that early latent predictions inherently encode rich temporal information. Motivated by this, we propose flow guidance, which extracts motion representations based on latent predictions to align motion patterns between source and generated videos. We further introduce a velocity regularization strategy to stabilize optimization and ensure smooth motion evolution. By operating purely on model predictions, FlowMotion achieves superior time and resource efficiency as well as competitive performance compared with state-of-the-art methods.
Authors: Zhuorui Zhang, Roger Pallar\`es-L\'opez, Praneeth Namburi, Brian W. Anthony
Abstract: Acquiring per-frame video annotations remains a primary bottleneck for deploying computer vision in specialized domains such as medical imaging, where expert labeling is slow and costly. Label propagation offers a natural solution, yet existing approaches face fundamental limitations. Video trackers and segmentation models can propagate labels within a single sequence but require per-video initialization and cannot generalize across videos. Classic correspondence pipelines operate on detector-chosen keypoints and struggle in low-texture scenes, while dense feature matching and one-shot segmentation methods enable cross-video propagation but lack spatiotemporal smoothness and unified support for both point and mask annotations. We present Match4Annotate, a lightweight framework for both intra-video and inter-video propagation of point and mask annotations. Our method fits a SIREN-based implicit neural representation to DINOv3 features at test time, producing a continuous, high-resolution spatiotemporal feature field, and learns a smooth implicit deformation field between frame pairs to guide correspondence matching. We evaluate on three challenging clinical ultrasound datasets. Match4Annotate achieves state-of-the-art inter-video propagation, outperforming feature matching and one-shot segmentation baselines, while remaining competitive with specialized trackers for intra-video propagation. Our results show that lightweight, test-time-optimized feature matching pipelines have the potential to offer an efficient and accessible solution for scalable annotation workflows.
Authors: Florentin Dipner, William Talbot, Turcan Tuna, Andrei Cramariuc, Marco Hutter
Abstract: This paper presents a robust one-shot badminton shuttlecock detection framework for non-stationary robots. To address the lack of egocentric shuttlecock detection datasets, we introduce a dataset of 20,510 semi-automatically annotated frames captured across 11 distinct backgrounds in diverse indoor and outdoor environments, and categorize each frame into one of three difficulty levels. For labeling, we present a novel semi-automatic annotation pipeline, that enables efficient labeling from stationary camera footage. We propose a metric suited to our downstream use case and fine-tune a YOLOv8 network optimized for real-time shuttlecock detection, achieving an F1-score of 0.86 under our metric in test environments similar to training, and 0.70 in entirely unseen environments. Our analysis reveals that detection performance is critically dependent on shuttlecock size and background texture complexity. Qualitative experiments confirm their applicability to robots with moving cameras. Unlike prior work with stationary camera setups, our detector is specifically designed for the egocentric, dynamic viewpoints of mobile robots, providing a foundational building block for downstream tasks, including tracking, trajectory estimation, and system (re)-initialization.
Authors: Mridankan Mandal
Abstract: Accurate estimation of pasture biomass from agricultural imagery is critical for sustainable livestock management, yet existing methods are limited by the small, imbalanced, and sparsely annotated datasets typical of real world monitoring. In this study, adaptation of vision foundation models to agricultural regression is systematically evaluated on the CSIRO Pasture Biomass benchmark, a 357 image dual view dataset with laboratory validated, component wise ground truth for five biomass targets, through 17 configurations spanning four backbones (EfficientNet-B3 to DINOv3-ViT-L), five cross view fusion mechanisms, and a 4x2 metadata factorial. A counterintuitive principle, termed "fusion complexity inversion", is uncovered: on scarce agricultural data, a two layer gated depthwise convolution (R^2 = 0.903) outperforms cross view attention transformers (0.833), bidirectional SSMs (0.819), and full Mamba (0.793, below the no fusion baseline). Backbone pretraining scale is found to monotonically dominate all architectural choices, with the DINOv2 -> DINOv3 upgrade alone yielding +5.0 R^2 points. Training only metadata (species, state, and NDVI) is shown to create a universal ceiling at R^2 ~ 0.829, collapsing an 8.4 point fusion spread to 0.1 points. Actionable guidelines for sparse agricultural benchmarks are established: backbone quality should be prioritized over fusion complexity, local modules preferred over global alternatives, and features unavailable at inference excluded.
Authors: Jingyuan Yang, Rucong Chen, Weibin Luo, Hui Huang
Abstract: Story generation aims to produce image sequences that depict coherent narratives while maintaining subject consistency across frames. Although existing methods have excelled in producing coherent and expressive stories, they remain largely emotion-neutral, focusing on what subject appears in a story while overlooking how emotions shape narrative interpretation and visual presentation. As stories are intended to engage audiences emotionally, we introduce emotion-aware story generation, a new task that aims to generate subject-consistent visual stories with explicit emotional directions. This task is challenging due to the abstract nature of emotions, which must be grounded in concrete visual elements and consistently expressed across a narrative through visual composition. To address these challenges, we propose EmoStory, a two-stage framework that integrates agent-based story planning and region-aware story generation. The planning stage transforms target emotions into coherent story prompts with emotion agent and writer agent, while the generation stage preserves subject consistency and injects emotion-related elements through region-aware composition. We evaluate EmoStory on a newly constructed dataset covering 25 subjects and 600 emotional stories. Extensive quantitative and qualitative results, along with user studies, show that EmoStory outperforms state-of-the-art story generation methods in emotion accuracy, prompt alignment, and subject consistency.
Authors: Joan Perramon-Lluss\`a, Amelia Jim\'enez-S\'anchez, Grzegorz Skorupko, Fotis Avgoustidis, Carlos Mart\'in-Isla, Karim Lekadir, Polyxeni Gkontra
Abstract: Foundation models (FMs) show great promise for robust downstream performance across medical imaging tasks and modalities, including cardiac magnetic resonance (CMR), following task-specific adaptation. However, adaptation using single-site data may lead to suboptimal performance and increased model bias, while centralized fine-tuning on clinical data is often infeasible due to privacy constraints. Federated fine-tuning offers a privacy-preserving alternative; yet conventional approaches struggle under heterogeneous, non-IID multi-center data and incur substantial communication overhead when adapting large models. In this work, we study federated FM fine-tuning for 3D CMR disease detection and propose Med-DualLoRA, a client-aware parameter-efficient fine-tuning (PEFT) federated framework that disentangles globally shared and local low-rank adaptations (LoRA) through additive decomposition. Global and local LoRA modules are trained locally, but only the global component is shared and aggregated across sites, keeping local adapters private. This design improves personalization while significantly reducing communication cost, and experiments show that adapting only two transformer blocks preserves performance while further improving efficiency. We evaluate our method on a multi-center state-of-the-art cine 3D CMR FM fine-tuned for disease detection using ACDC and combined M\&Ms datasets, treating each vendor as a federated client. Med-DualLoRA achieves statistically significant improved performance (balanced accuracy 0.768, specificity 0.612) compared to other federated PEFT baselines, while maintaining communication efficiency. Our approach provides a scalable solution for local federated adaptation of medical FMs under realistic clinical constraints.
Authors: Tianhao Qian, Zhuoxuan Li, Jinde Cao, Xinli Shi, Leszek Rutkowski
Abstract: Efficient deep learning traditionally relies on static heuristics like weight magnitude or activation awareness (e.g., Wanda, RIA). While successful in unstructured settings, we observe a critical limitation when applying these metrics to the structural pruning of deep vision networks. These contemporary metrics suffer from a magnitude bias, failing to preserve critical functional pathways. To overcome this, we propose a decoupled kinetic paradigm inspired by Alternating Gradient Flow (AGF), utilizing an absolute feature-space Taylor expansion to accurately capture the network's structural "kinetic utility". First, we uncover a topological phase transition at extreme sparsity, where AGF successfully preserves baseline functionality and exhibits topological implicit regularization, avoiding the collapse seen in models trained from scratch. Second, transitioning to architectures without strict structural priors, we reveal a phenomenon of Sparsity Bottleneck in Vision Transformers (ViTs). Through a gradient-magnitude decoupling analysis, we discover that dynamic signals suffer from signal compression in converged models, rendering them suboptimal for real-time routing. Finally, driven by these empirical constraints, we design a hybrid routing framework that decouples AGF-guided offline structural search from online execution via zero-cost physical priors. We validate our paradigm on large-scale benchmarks: under a 75% compression stress test on ImageNet-1K, AGF effectively avoids the structural collapse where traditional metrics aggressively fall below random sampling. Furthermore, when systematically deployed for dynamic inference on ImageNet-100, our hybrid approach achieves Pareto-optimal efficiency. It reduces the usage of the heavy expert by approximately 50% (achieving an estimated overall cost of 0.92$\times$) without sacrificing the full-model accuracy.
Authors: Hamza Mooraj, George Pantazopoulos, Alessandro Suglia
Abstract: Reliable crop disease detection requires models that perform consistently across diverse acquisition conditions, yet existing evaluations often focus on single architectural families or lab-generated datasets. This work presents a systematic empirical comparison of three model paradigms for fine-grained crop disease classification: Convolutional Neural Networks (CNNs), contrastive Vision-Language Models (VLMs), and generative VLMs. To enable controlled analysis of domain effects, we introduce AgriPath-LF16, a benchmark containing 111k images spanning 16 crops and 41 diseases with explicit separation between laboratory and field imagery, alongside a balanced 30k subset for standardized training and evaluation. All models are trained and evaluated under unified protocols across full, lab-only, and field-only training regimes using macro-F1 and Parse Success Rate (PSR) to account for generative reliability. The results reveal distinct performance profiles. CNNs achieve the highest accuracy on lab imagery but degrade under domain shift. Contrastive VLMs provide a robust and parameter-efficient alternative with competitive cross-domain performance. Generative VLMs demonstrate the strongest resilience to distributional variation, albeit with additional failure modes stemming from free-text generation. These findings highlight that architectural choice should be guided by deployment context rather than aggregate accuracy alone.
Authors: Zhaoyu Liu, Xi Weng, Lianyu Hu, Zhe Hou, Kan Jiang, Jin Song Dong, Yang Liu
Abstract: Tennis is one of the most widely followed sports, generating extensive broadcast footage with strong potential for professional analysis, automated coaching, and real-time commentary. However, automatic tennis understanding remains underexplored due to two key challenges: (1) the lack of large-scale benchmarks with fine-grained annotations and expert-level commentary, and (2) the difficulty of building accurate yet efficient multimodal systems suitable for real-time deployment. To address these challenges, we introduce TennisVL, a large-scale tennis benchmark comprising over 200 professional matches (471.9 hours) and 40,000+ rally-level clips. Unlike existing commentary datasets that focus on descriptive play-by-play narration, TennisVL emphasizes expert analytical commentary capturing tactical reasoning, player decisions, and match momentum. Furthermore, we propose TennisExpert, a multimodal tennis understanding framework that integrates a video semantic parser with a memory-augmented model built on Qwen3-VL-8B. The parser extracts key match elements (e.g., scores, shot sequences, ball bounces, and player locations), while hierarchical memory modules capture both short- and long-term temporal context. Experiments show that TennisExpert consistently outperforms strong proprietary baselines, including GPT-5, Gemini, and Claude, and demonstrates improved ability to capture tactical context and match dynamics. Our dataset and code are publicly available at https://github.com/LZYAndy/TennisExpert.
Authors: Jiahao Zhu, Shanshan Lao, Lijie Liu, Gen Li, Tianhao Qi, Wei Han, Bingchuan Li, Fangfang Liu, Zhuowei Chen, Tianxiang Ma, Qian HE, Yi Zhou, Xiaohua Xie
Abstract: With the advancement of video generation foundation models (VGFMs), customized generation, particularly subject-to-video (S2V), has attracted growing attention. However, a key challenge lies in balancing the intrinsic priors of a VGFM, such as motion coherence, visual aesthetics, and prompt alignment, with its newly derived S2V capability. Existing methods often neglect this balance by enhancing one aspect at the expense of others. To address this, we propose LibraGen, a novel framework that views extending foundation models for S2V generation as a balance game between intrinsic VGFM strengths and S2V capability. Specifically, guided by the core philosophy of "Raising the Fulcrum, Tuning to Balance," we identify data quality as the fulcrum and advocate a quality-over-quantity approach. We construct a hybrid pipeline that combines automated and manual data filtering to improve overall data quality. To further harmonize the VGFM's native capabilities with its S2V extension, we introduce a Tune-to-Balance post-training paradigm. During supervised fine-tuning, both cross-pair and in-pair data are incorporated, and model merging is employed to achieve an effective trade-off. Subsequently, two tailored direct preference optimization (DPO) pipelines, namely Consis-DPO and Real-Fake DPO, are designed and merged to consolidate this balance. During inference, we introduce a time-dependent dynamic classifier-free guidance scheme to enable flexible and fine-grained control. Experimental results demonstrate that LibraGen outperforms both open-source and commercial S2V models using only thousand-scale training data.
Authors: Mahdi Naseri, Zhou Wang
Abstract: No-Reference Image Quality Assessment (NR-IQA) aims to estimate perceptual quality without access to a reference image of pristine quality. Learning an NR-IQA model faces a fundamental bottleneck: its need for a large number of costly human perceptual labels. We propose SHAMISA, a non-contrastive self-supervised framework that learns from unlabeled distorted images by leveraging explicitly structured relational supervision. Unlike prior methods that impose rigid, binary similarity constraints, SHAMISA introduces implicit structural associations, defined as soft, controllable relations that are both distortion-aware and content-sensitive, inferred from synthetic metadata and intrinsic feature structure. A key innovation is our compositional distortion engine, which generates an uncountable family of degradations from continuous parameter spaces, grouped so that only one distortion factor varies at a time. This enables fine-grained control over representational similarity during training: images with shared distortion patterns are pulled together in the embedding space, while severity variations produce structured, predictable shifts. We integrate these insights via dual-source relation graphs that encode both known degradation profiles and emergent structural affinities to guide the learning process throughout training. A convolutional encoder is trained under this supervision and then frozen for inference, with quality prediction performed by a linear regressor on its features. Extensive experiments on synthetic, authentic, and cross-dataset NR-IQA benchmarks demonstrate that SHAMISA achieves strong overall performance with improved cross-dataset generalization and robustness, all without human quality annotations or contrastive losses.
Authors: Bohan Zhang, Weidong Tang, Zhixiang Chi, Yi Jin, Zhenbo Li, Yang Wang, Yanan Wu
Abstract: On-the-Fly Category Discovery (OCD) aims to recognize known classes while simultaneously discovering emerging novel categories during inference, using supervision only from known classes during offline training. Existing approaches rely either on fixed label supervision or on diffusion-based augmentations to enhance the backbone, yet none of them explicitly train the model to perform the discovery task required at test time. It is fundamentally unreasonable to expect a model optimized on limited labeled data to carry out a qualitatively different discovery objective during inference. This mismatch creates a clear optimization misalignment between the offline learning stage and the online discovery stage. In addition, prior methods often depend on hash-based encodings or severe feature compression, which further limits representational capacity. To address these issues, we propose Learning through Creation (LTC), a fully feature-based and hash-free framework that injects novel-category awareness directly into offline learning. At its core is a lightweight, online pseudo-unknown generator driven by kernel-energy minimization and entropy maximization (MKEE). Unlike previous methods that generate synthetic samples once before training, our generator evolves jointly with the model dynamics and synthesizes pseudo-novel instances on the fly at negligible cost. These samples are incorporated through a dual max-margin objective with adaptive thresholding, strengthening the model's ability to delineate and detect unknown regions through explicit creation. Extensive experiments across seven benchmarks show that LTC consistently outperforms prior work, achieving improvements ranging from 1.5 percent to 13.1 percent in all-class accuracy. The code is available at https://github.com/brandinzhang/LTC
Authors: Lin Hong, Xiangtong Yao, M\"ur\"uvvet Bozkurt, Xin Wang, Fumin Zhang
Abstract: Underwater salient instance segmentation (USIS) is crucial for marine robotic systems, as it enables both underwater salient object detection and instance-level mask prediction for visual scene understanding. Compared with its terrestrial counterpart, USIS is more challenging due to the underwater image degradation. To address this issue, this paper proposes USIS-PGM, a single-stage framework for USIS. Specifically, the encoder enhances boundary cues through a frequency-aware module and performs content-adaptive feature reweighting via a dynamic weighting module. The decoder incorporates a Transformer-based instance activation module to better distinguish salient instances. In addition, USIS-PGM employs multi-scale Gaussian heatmaps generated from ground-truth masks through Photometric Gaussian Mixture (PGM) to supervise intermediate decoder features, thereby improving salient instance localization and producing more structurally coherent mask predictions. Experimental results demonstrate the superiority and practical applicability of the proposed USIS-PGM model.
Authors: Ngoc-Son Nguyen, Thanh V. T. Tran, Jeongsoo Choi, Hieu-Nghia Huynh-Nguyen, Truong-Son Hy, Van Nguyen
Abstract: Video dubbing has broad applications in filmmaking, multimedia creation, and assistive speech technology. Existing approaches either train directly on limited dubbing datasets or adopt a two-stage pipeline that adapts pre-trained text-to-speech (TTS) models, which often struggle to produce expressive prosody, rich acoustic characteristics, and precise synchronization. To address these issues, we propose DiFlowDubber with a novel two-stage training framework that effectively transfers knowledge from a pre-trained TTS model to video-driven dubbing, with a discrete flow matching generative backbone. Specifically, we design a FaPro module that captures global prosody and stylistic cues from facial expressions and leverages this information to guide the modeling of subsequent speech attributes. To ensure precise speech-lip synchronization, we introduce a Synchronizer module that bridges the modality gap among text, video, and speech, thereby improving cross-modal alignment and generating speech that is temporally synchronized with lip movements. Experiments on two primary benchmark datasets demonstrate that DiFlowDubber outperforms previous methods across multiple metrics.
Authors: Lorenzo Mur-Labadia, Matthew Muckley, Amir Bar, Mido Assran, Koustuv Sinha, Mike Rabbat, Yann LeCun, Nicolas Ballas, Adrien Bardes
Abstract: We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First, a dense predictive loss uses a masking-based objective in which both visible and masked tokens contribute to the training signal, encouraging explicit spatial and temporal grounding. Second, deep self-supervision applies the self-supervised objective hierarchically across multiple intermediate encoder layers to improve representation quality. Third, multi-modal tokenizers enable unified training across images and videos. Finally, the model benefits from effective scaling in both model capacity and training data. Together, these design choices produce representations that are spatially structured, semantically coherent, and temporally consistent. Empirically, V-JEPA 2.1 achieves state-of-the-art performance on several challenging benchmarks, including 7.71 mAP on Ego4D for short-term object-interaction anticipation and 40.8 Recall@5 on EPIC-KITCHENS for high-level action anticipation, as well as a 20-point improvement in real-robot grasping success rate over V-JEPA-2 AC. The model also demonstrates strong performance in robotic navigation (5.687 ATE on TartanDrive), depth estimation (0.307 RMSE on NYUv2 with a linear probe), and global recognition (77.7 on Something-Something-V2). These results show that V-JEPA 2.1 significantly advances the state of the art in dense visual understanding and world modeling.
Authors: Stefan Englmeier, Katharina Winter, Fabian B. Flohr
Abstract: Autonomous driving systems depend on on models that can reason about high-level scene contexts and accurately predict the dynamics of their surrounding environment. Vision- Language Models (VLMs) have recently emerged as promising tools for decision-making and scene understanding, offering strong capabilities in contextual reasoning. However, their limited spatial comprehension constrains their effectiveness as end-to-end driving models. World Models (WM) internalize environmental dynamics to predict future scene evolution. Recently explored as ego-motion predictors and foundation models for autonomous driving, they represent a promising direction for addressing key challenges in the field, particularly enhancing generalization while maintaining dynamic prediction. To leverage the complementary strengths of context-based decision making and prediction, we propose WorldVLM: A hybrid architecture that unifies VLMs and WMs. In our design, the high-level VLM generates behavior commands to guide the driving WM, enabling interpretable and context-aware actions. We evaluate conditioning strategies and provide insights into the hybrid design challenges.
Authors: Harel Yadid, Meir Yossef Levi, Roy Betser, Guy Gilboa
Abstract: All classifiers, including state-of-the-art vision models, possess invariants, partially rooted in the geometry of their linear mappings. These invariants, which reside in the null-space of the classifier, induce equivalent sets of inputs that map to identical outputs. The semantic content of these invariants remains vague, as existing approaches struggle to provide human-interpretable information. To address this gap, we present Semantic Interpretation of the Null-space Geometry (SING), a method that constructs equivalent images, with respect to the network, and assigns semantic interpretations to the available variations. We use a mapping from network features to multi-modal vision language models. This allows us to obtain natural language descriptions and visual examples of the induced semantic shifts. SING can be applied to a single image, uncovering local invariants, or to sets of images, allowing a breadth of statistical analysis at the class and model levels. For example, our method reveals that ResNet50 leaks relevant semantic attributes to the null space, whereas DinoViT, a ViT pretrained with self-supervised DINO, is superior in maintaining class semantics across the invariant space.
Authors: Sudip Laudari, Sang Hun Baek
Abstract: Geometric data augmentation is widely used in segmentation pipelines and typically assumes that polygon annotations represent simply connected regions. However, in structured domains such as architectural floorplan analysis, ring-type regions are often encoded as a single cyclic polygon chain connecting outer and inner boundaries. During augmentation, clipping operations may remove intermediate vertices and disrupt this cyclic connectivity, breaking the structural relationship between the boundaries. In this work, we introduce an order-preserving polygon augmentation strategy that performs transformations in mask space and then projects surviving vertices back into index-space to restore adjacency relations. This repair maintains the original traversal order of the polygon and preserves topological consistency with minimal computational overhead. Experiments demonstrate that the approach reliably restores connectivity, achieving near-perfect Cyclic Adjacency Preservation (CAP) across both single and compound augmentations.
Authors: Jiahe Song, Chuang Wang, Yinfan Wang, Hao Zheng, Rui Nie, Bowen Jiang, Xingjian Wei, Junyuan Gao, Yubin Wang, Bin Wang, Lijun Wu, Jiang Wu, Qian Yu, Conghui He
Abstract: Reaction diagram parsing (RxnDP) is critical for extracting chemical synthesis information from literature. Although recent Vision-Language Models (VLMs) have emerged as a promising paradigm to automate this complex visual reasoning task, their application is fundamentally bottlenecked by the inability to align visual chemical entities with pre-trained knowledge, alongside the inherent discrepancy between token-level training and reaction-level evaluation. To address these dual challenges, this work enhances VLM-based RxnDP from two complementary perspectives: prompting representation and learning paradigms. First, we propose Identifier as Visual Prompting (IdtVP), which leverages naturally occurring molecule identifiers (e.g., bold numerals like 1a) to activate the chemical knowledge acquired during VLM pre-training. IdtVP enables powerful zero-shot and out-of-distribution capabilities, outperforming existing prompting strategies. Second, to further optimize performance within fine-tuning paradigms, we introduce Re3-DAPO, a reinforcement learning algorithm that leverages verifiable rewards to directly optimize reaction-level metrics, thereby achieving consistent gains over standard supervised fine-tuning. Additionally, we release the ScannedRxn benchmark, comprising scanned historical reaction diagrams with real-world artifacts, to rigorously assess model robustness and out-of-distribution ability. Our contributions advance the accuracy and generalization of VLM-based reaction diagram parsing. We will release data, models, and code on GitHub.
Authors: Wooseok Lee, Jin Mo Yang, Saewoong Bahk, Hyung-Sin Kim
Abstract: For reliable deployment of deep-learning systems, out-of-distribution (OOD) detection is indispensable. In the real world, where test-time inputs often arrive as streaming mixtures of in-distribution (ID) and OOD samples under evolving covariate shifts, OOD samples are domain-constrained and bounded by the environment, and both ID and OOD are jointly affected by the same covariate factors. Existing methods typically assume a stationary ID distribution, but this assumption breaks down in such settings, leading to severe performance degradation. We empirically discover that, even under covariate shift, covariate-shifted ID (csID) and OOD (csOOD) samples remain separable along a discriminative axis in feature space. Building on this observation, we propose DART, a test-time, online OOD detection method that dynamically tracks dual prototypes -- one for ID and the other for OOD -- to recover the drifting discriminative axis, augmented with multi-layer fusion and flip correction for robustness. Extensive experiments on a wide range of challenging benchmarks, where all datasets are subjected to 15 common corruption types at severity level 5, demonstrate that our method significantly improves performance, yielding 15.32 percentage points (pp) AUROC gain and 49.15 pp FPR@95TPR reduction on ImageNet-C vs. Textures-C compared to established baselines. These results highlight the potential of the test-time discriminative axis tracking for dependable OOD detection in dynamically changing environments.
Authors: Xuerui Qiu, Yutao Cui, Guozhen Zhang, Junzhe Li, JiaKui Hu, Xiao Zhang, Yang Li, Songtao Liu, Miles Yang, Yu Shi, Zhao Zhong, Liefeng Bo
Abstract: Unified Multimodal Models struggle to bridge the fundamental gap between the abstract representations needed for visual understanding and the detailed primitives required for generation. Existing approaches typically compromise by employing decoupled encoders, stacking representation encoder atop VAEs, or utilizing discrete quantization. However, these methods often disrupt information coherence and lead to optimization conflicts. To this end, we introduce HYDRA-TOK, a representation-harmonized pure ViT in the insight that visual modeling should evolve from generation to understanding. HYDRA-TOK reformulates the standard backbone into a progressive learner that transitions from a Gen-ViT, which captures structure-preserving primitives, to a Sem-ViT for semantic encoding. Crucially, this transition is mediated by a Generation-Semantic Bottleneck (GSB), which compresses features into a low-dimensional space to filter noise for robust synthesis, then restores dimensionality to empower complex semantic comprehension. Built upon this foundation, we present HYDRA, a native unified framework integrating perception and generation within a single parameter space. Extensive experiments establish HYDRA as a new state-of-the-art. It sets a benchmark in visual reconstruction (rFID 0.08) and achieves top-tier generation performance on GenEval (0.86), DPG-Bench (86.4), and WISE (0.53), while simultaneously outperforming previous native UMMs by an average of 10.0 points across eight challenging understanding benchmarks.
Authors: Fanqing Meng, Lingxiao Du, Jiawei Gu, Jiaqi Liao, Linjie Li, Zijian Wu, Xiangyan Liu, Ziqi Zhao, Mengkang Hu, Yue Zhang, Zichen Liu, Jiaheng Zhang, Michael Qizhe Shieh
Abstract: As agentic systems increasingly rely on reinforcement learning from verifiable rewards, standardized ``gym'' infrastructure has become essential for rapid iteration, reproducibility, and fair comparison. Vision agents lack such infrastructure, limiting systematic study of what drives their learning and where current models fall short. We introduce \textbf{Gym-V}, a unified platform of 179 procedurally generated visual environments across 10 domains with controllable difficulty, enabling controlled experiments that were previously infeasible across fragmented toolkits. Using it, we find that observation scaffolding is more decisive for training success than the choice of RL algorithm, with captions and game rules determining whether learning succeeds at all. Cross-domain transfer experiments further show that training on diverse task categories generalizes broadly while narrow training can cause negative transfer, with multi-turn interaction amplifying all of these effects. Gym-V is released as a convenient foundation for training environments and evaluation toolkits, aiming to accelerate future research on agentic VLMs.
Authors: Xianbao Hou, Yonghao He, Zeyd Boukhers, John See, Hu Su, Wei Sui, Cong Yang
Abstract: Diffusion models have significantly mitigated the impact of annotated data scarcity in remote sensing (RS). Although recent approaches have successfully harnessed these models to enable diverse and controllable Layout-to-Image (L2I) synthesis, they still suffer from limited fine-grained control and fail to strictly adhere to bounding box constraints. To address these limitations, we propose RSGen, a plug-and-play framework that leverages diverse edge guidance to enhance layout-driven RS image generation. Specifically, RSGen employs a progressive enhancement strategy: 1) it first enriches the diversity of edge maps composited from retrieved training instances via Image-to-Image generation; and 2) subsequently utilizes these diverse edge maps as conditioning for existing L2I models to enforce pixel-level control within bounding boxes, ensuring the generated instances strictly adhere to the layout. Extensive experiments across three baseline models demonstrate that RSGen significantly boosts the capabilities of existing L2I models. For instance, with CC-Diff on the DOTA dataset for oriented object detection, we achieve remarkable gains of +9.8/+12.0 in YOLOScore mAP50/mAP50-95 and +1.6 in mAP on the downstream detection task. Our code will be publicly available: https://github.com/D-Robotics-AI-Lab/RSGen
Authors: Yulin Luo, Hao Chen, Zhuangzhe Wu, Bowen Sui, Jiaming Liu, Chenyang Gu, Zhuoyang Liu, Qiuxuan Feng, Jiale Yu, Shuo Gu, Peng Jia, Pheng-Ann Heng, Shanghang Zhang
Abstract: Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for robotic manipulation, in which reliable action prediction critically depends on accurately interpreting and integrating visual observations conditioned on language instructions. Although recent works have sought to enhance the visual capabilities of VLA models, most approaches treat the LLM backbone as a black box, providing limited insight into how visual information is grounded into action generation. Therefore, we perform a systematic analysis of multiple VLA models across different action-generation paradigms and observe that sensitivity to visual tokens progressively decreases in deeper layers during action generation. Motivated by this observation, we propose \textbf{DeepVision-VLA}, built on a \textbf{Vision-Language Mixture-of-Transformers (VL-MoT)} framework. This framework enables shared attention between the vision foundation model and the VLA backbone, injecting multi-level visual features from the vision expert into deeper layers of the VLA backbone to enhance visual representations for precise and complex manipulation. In addition, we introduce \textbf{Action-Guided Visual Pruning (AGVP)}, which leverages shallow-layer attention to prune irrelevant visual tokens while preserving task-relevant ones, reinforcing critical visual cues for manipulation with minimal computational overhead. DeepVision-VLA outperforms prior state-of-the-art methods by 9.0\% and 7.5\% on simulated and real-world tasks, respectively, providing new insights for the design of visually enhanced VLA models.
Authors: Qian Shao, Bang Du, Yixuan Wu, Zepeng Li, Qiyuan Chen, Qianqian Tang, Jian Wu, Jintai Chen, Hongxia Xu
Abstract: Deep learning models for pulmonary disease screening from Computed Tomography (CT) scans promise to alleviate the immense workload on radiologists. Still, their high computational cost, stemming from processing entire 3D volumes, remains a major barrier to widespread clinical adoption. Current sub-sampling techniques often compromise diagnostic integrity by introducing artifacts or discarding critical information. To overcome these limitations, we propose an Efficient and Reliable Framework (ERF) that fundamentally improves the practicality of automated CT analysis. Our framework introduces two core innovations: (1) A Cluster-based Sub-Sampling (CSS) method that efficiently selects a compact yet comprehensive subset of CT slices by optimizing for both representativeness and diversity. By integrating an efficient k-nearest neighbor search with an iterative refinement process, CSS bypasses the computational bottlenecks of previous methods while preserving vital diagnostic features. (2) An Ambiguity-aware Uncertainty Quantification (AUQ) mechanism, which enhances reliability by specifically targeting data ambiguity arising from subtle lesions and artifacts. Unlike standard uncertainty measures, AUQ leverages the predictive discrepancy between auxiliary classifiers to construct a specialized ambiguity score. By maximizing this discrepancy during training, the system effectively flags ambiguous samples where the model lacks confidence due to visual noise or intricate pathologies. Validated on two public datasets with 2,654 CT volumes across diagnostic tasks for 3 pulmonary diseases, ERF achieves diagnostic performance comparable to the full-volume analysis (over 90% accuracy and recall) while reducing processing time by more than 60%. This work represents a significant step towards deploying fast, accurate, and trustworthy AI-powered screening tools in time-sensitive clinical settings.
Authors: Hongyu Zhou, Zorah L\"ahner
Abstract: With the rising popularity of 3D Gaussian splatting and the expanse of applications from rendering to 3D reconstruction, there comes also a need for geometry processing applications directly on this new representation. While considering the centers of Gaussians as a point cloud or meshing them is an option that allows to apply existing algorithms, this might ignore information present in the data or be unnecessarily expensive. Additionally, Gaussian splatting tends to contain a large number of outliers which do not affect the rendering quality but need to be handled correctly in order not to produce noisy results in geometry processing applications. In this work, we propose a formulation to compute the Laplace-Beltrami operator, a widely used tool in geometry processing, directly on Gaussian splatting using the Mahalanobis distance. While conceptually similar to a point cloud Laplacian, our experiments show superior accuracy on the point clouds encoded in the Gaussian splatting centers and, additionally, the operator can be used to evaluate the quality of the output during optimization.
Authors: Jay Kamat, J\'ulia Borr\`as, Carme Torras
Abstract: Cloth manipulation is a difficult problem mainly because of the non-rigid nature of cloth, which makes a good representation of deformation essential. We present a new representation for the deformation-state of clothes. First, we propose the dGLI disk representation based on topological indices computed for edge segments of the cloth border that are arranged on a circular grid. The heat-map of the dGLI disk uncovers patterns that correspond to features of the cloth state that are consistent for different shapes, sizes or orientation of the cloth. We then abstract these important features from the dGLI disk into a circle, calling it the Cloth StatE representation (CloSE). This representation is compact, continuous, and general for different shapes. We show that this representation is able to accurately predict the fold locations for several simulation clothing datasets. Finally, we also show the strengths of this representation in two relevant applications: semantic labeling and high- and low-level planning. The code and the dataset can be accessed from: https://close-representation.github.io/
Authors: Gal Fiebelman, Hadar Averbuch-Elor, Sagie Benaim
Abstract: 3D Gaussian Splatting has recently enabled fast and photorealistic reconstruction of static 3D scenes. However, dynamic editing of such scenes remains a significant challenge. We introduce a novel framework, Physics-Guided Score Distillation, to address a fundamental conflict: physics simulation provides a strong motion prior that is insufficient for photorealism , while video-based Score Distillation Sampling (SDS) alone cannot generate coherent motion for complex, multi-particle scenarios. We resolve this through a unified optimization framework where physics simulation guides Score Distillation to jointly refine the motion prior for photorealism while simultaneously optimizing appearance. Specifically, we learn a neural dynamics model that predicts particle motion and appearance, optimized end-to-end via a combined loss integrating Video-SDS for photorealism with our physics-guidance prior. This allows for photorealistic refinements while ensuring the dynamics remain plausible. Our framework enables scene-wide dynamic weather effects, including snowfall, rainfall, fog, and sandstorms, with physically plausible motion. Experiments demonstrate our physics-guided approach significantly outperforms baselines, with ablations confirming this joint refinement is essential for generating coherent, high-fidelity dynamics.
Authors: Donato Crisostomi, Alessandro Zirilli, Antonio Andrea Gargiulo, Maria Sofia Bucarelli, Simone Scardapane, Fabrizio Silvestri, Iacopo Masi, Emanuele Rodol\`a
Abstract: Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set of parameters with no additional training overhead. Yet, existing merging methods fall short of matching the full accuracy of separately fine-tuned endpoints. We present MASS (MoErging through Adaptive Subspace Selection), a new approach that closes this gap by unifying multiple fine-tuned models while retaining near state-of-the-art performance across tasks. Building on the low-rank decomposition of per-task updates, MASS stores only the most salient singular components for each task and merges them into a shared model. At inference time, a non-parametric, data-free router identifies which subspace (or combination thereof) best explains an input's intermediate features and activates the corresponding task-specific block. This procedure is fully training-free and introduces only a two-pass inference overhead plus a ~2 storage factor compared to a single pretrained model, irrespective of the number of tasks. We evaluate MASS on CLIP-based image classification using ViT-B-16, ViT-B-32 and ViT-L-14 for benchmarks of 8, 14 and 20 tasks respectively, establishing a new state-of-the-art. Most notably, MASS recovers up to ~98% of the average accuracy of individual fine-tuned models, making it a practical alternative to ensembling at a fraction of the storage cost.
Authors: Ziyi Zhang, Li Shen, Deheng Ye, Yong Luo, Huangxuan Zhao, Meng Liu, Wei Yu, Lefei Zhang
Abstract: Text-to-multiview (T2MV) diffusion models have shown great promise in generating multiple views of a scene from a single text prompt. While few-step backbones enable real-time T2MV generation, they often compromise key aspects of generation quality, such as per-view fidelity and cross-view consistency. Reinforcement learning (RL) finetuning offers a potential solution, yet existing approaches designed for single-image diffusion do not readily extend to the few-step T2MV setting, as they neglect cross-view coordination and suffer from weak learning signals in few-step regimes. To address this, we propose MVC-ZigAL, a tailored RL finetuning framework for few-step T2MV diffusion models. Specifically, its core insights are: (1) a new MDP formulation that jointly models all generated views and assesses their collective quality via a joint-view reward; (2) a novel advantage learning strategy that exploits the performance gains of a self-refinement sampling scheme over standard sampling, yielding stronger learning signals for effective RL finetuning; and (3) a unified RL framework that extends advantage learning with a Lagrangian dual formulation for multiview-constrained optimization, balancing single-view and joint-view objectives through adaptive primal-dual updates under a self-paced threshold curriculum that harmonizes exploration and constraint enforcement. Collectively, these designs enable robust and balanced RL finetuning for few-step T2MV diffusion models, yielding substantial gains in both per-view fidelity and cross-view consistency. Code is available at https://github.com/ZiyiZhang27/MVC-ZigAL.
Authors: Bao Pham, Gabriel Raya, Matteo Negri, Mohammed J. Zaki, Luca Ambrogioni, Dmitry Krotov
Abstract: Dense Associative Memories (DenseAMs) are generalizations of Hopfield networks, which have superior information storage capacity and can store training data points (memories) at local minima of the energy landscape. When the amount of training data exceeds the critical memory storage capacity of these models, new local minima, which are different from the training data, emerge. In Associative Memory these emergent local minima are called $\textit{spurious}\; \textit{states}$, which hinder memory retrieval. In this work, we examine diffusion models (DMs) through the DenseAM lens, viewing their generative process as an attempt of a memory retrieval. In the small data regimes, DMs create distinct attractors for each training sample, akin to DenseAMs below the critical memory storage. As the training data size increases, they transition from memorization to generalization. We identify a critical intermediate phase, predicted by DenseAM theory -- the spurious states. In generative modeling, these states are no longer negative artifacts but rather are the first signs of generative capabilities. We characterize the basins of attraction, energy landscape curvature, and computational properties of these previously overlooked states. Their existence is demonstrated across a wide range of architectures and datasets.
Authors: Jieren Deng, Zhizhang Hu, Ziyan He, Aleksandar Cvetkovic, Pak Kiu Chung, Dragomir Yankov, Chiqun Zhang
Abstract: Map applications are still largely point-and-click, making it difficult to ask map-centric questions or connect what a camera sees to the surrounding geospatial context with view-conditioned inputs. We introduce IMAIA, an interactive Maps AI Assistant that enables natural-language interaction with both vector (street) maps and satellite imagery, and augments camera inputs with geospatial intelligence to help users understand the world. IMAIA comprises two complementary components. Maps Plus treats the map as first-class context by parsing tiled vector/satellite views into a grid-aligned representation that a language model can query to resolve deictic references (e.g., ``the flower-shaped building next to the park in the top-right''). Places AI Smart Assistant (PAISA) performs camera-aware place understanding by fusing image--place embeddings with geospatial signals (location, heading, proximity) to ground a scene, surface salient attributes, and generate concise explanations. A lightweight multi-agent design keeps latency low and exposes interpretable intermediate decisions. Across map-centric QA and camera-to-place grounding tasks, IMAIA improves accuracy and responsiveness over strong baselines while remaining practical for user-facing deployments. By unifying language, maps, and geospatial cues, IMAIA moves beyond scripted tools toward conversational mapping that is both spatially grounded and broadly usable.
Authors: Chenguang Wang, Xiang Yan, Yilong Dai, Ziyi Wang, Susu Xu
Abstract: Realistic visual renderings of street-design scenarios are essential for public engagement in active transportation planning. Traditional approaches are labor-intensive, hindering collective deliberation and collaborative decision-making. While AI-assisted generative design shows transformative potential by enabling rapid creation of design scenarios, existing generative approaches typically require large amounts of domain-specific training data and struggle to enable precise spatial variations of design/configuration in complex street-view scenes. We introduce a multi-agent system that edits and redesigns bicycle facilities directly on real-world street-view imagery. The framework integrates lane localization, prompt optimization, design generation, and automated evaluation to synthesize realistic, contextually appropriate designs. Experiments across diverse urban scenarios demonstrate that the system can adapt to varying road geometries and environmental conditions, consistently yielding visually coherent and instruction-compliant results. This work establishes a foundation for applying multi-agent pipelines to transportation infrastructure planning and facility design.
Authors: Karim Kadry, Shoaib Goraya, Ajay Manicka, Abdalla Abdelwahed, Naravich Chutisilp, Farhad Nezami, Elazer Edelman
Abstract: Generative models of 3D cardiovascular anatomy can synthesize informative structures for clinical research and medical device evaluation, but face a trade-off between geometric controllability and realism. We propose CardioComposer: a programmable, inference-time framework for generating multi-class anatomical label maps from interpretable ellipsoidal primitives. These primitives represent geometric attributes such as the size, shape, and position of discrete substructures. We specifically develop differentiable measurement functions based on voxel-wise geometric moments, enabling loss-based gradient guidance during diffusion model sampling. We demonstrate that these losses can constrain individual geometric attributes in a disentangled manner and provide compositional control over multiple substructures. Finally, we show that our method is compatible with a broad range of anatomical systems containing non-convex substructures, spanning cardiac, vascular, and skeletal organs. We release our code at https://github.com/kkadry/CardioComposer.
Authors: Simon Welker, Lorenz Kuger, Tim Roith, Berthy Feng, Martin Burger, Timo Gerkmann, Henry Chapman
Abstract: In this work, we present and investigate the novel blind inverse problem of position-blind ptychography, i.e., ptychographic phase retrieval without any knowledge of scan positions, which then must be recovered jointly with the image. The motivation for this problem comes from single-particle diffractive X-ray imaging, where particles in random orientations are illuminated and a set of diffraction patterns is collected. If one uses a highly focused X-ray beam, the measurements would also become sensitive to the beam positions relative to each particle and therefore ptychographic, but these positions are also unknown. We investigate the viability of image reconstruction in a simulated, simplified 2-D variant of this difficult problem, using variational inference with modern data-driven image priors in the form of score-based diffusion models. We find that, with the right illumination structure and a strong prior, one can achieve reliable and successful image reconstructions even under measurement noise, in all except the most difficult evaluated imaging scenario.
Authors: Alexander Michael Rusnak
Abstract: What does it mean for a machine to recognize beauty? While beauty remains a culturally and experientially compelling but philosophically elusive concept, deep learning systems increasingly appear capable of modeling aesthetic judgment. In this paper, we explore the capacity of neural networks to represent beauty despite the immense formal diversity of objects for which the term applies. By drawing on recent work on cross-model representational convergence, we show how aesthetic content produces more similar and aligned representations between models which have been trained on distinct data and modalities - while unaesthetic images do not produce more aligned representations. This finding implies that the formal structure of beautiful images has a realist basis - rather than only as a reflection of socially constructed values. Furthermore, we propose that these realist representations exist because of a joint grounding of aesthetic form in physical and cultural substance. We argue that human perceptual and creative acts play a central role in shaping these the latent spaces of deep learning systems, but that a realist basis for aesthetics shows that machines are not mere creative parrots but can produce novel creative insights from the unique vantage point of scale. Our findings suggest that human-machine co-creation is not merely possible, but foundational - with beauty serving as a teleological attractor in both cultural production and machine perception.
Authors: George Webber, Andrew J. Reader
Abstract: Recovering true signals from noisy measurements is a central challenge in inverse problems spanning medical imaging, geophysics, and signal processing. Current methods balance prior signal priors (regularization) with agreement with noisy data (data-fidelity). Conventional data-fidelity loss functions, such as mean-squared error (MSE) or negative log-likelihood, seek pointwise agreement with noisy measurements, often leading to overfitting to noise. In this work, we instead evaluate data-fidelity collectively by testing whether the observed measurements are statistically consistent with the noise distributions implied by the current estimate. We introduce distributional consistency (DC) loss, a data-fidelity objective that replaces pointwise matching with distribution-level calibration. DC loss acts as a direct and practical plug-in replacement for standard data consistency terms: i) it is compatible with modern unsupervised regularizers that operate without paired measurement-ground-truth data, ii) it is optimized in the same way as traditional losses, and iii) it avoids overfitting to measurement noise without early stopping or priors. Its scope naturally fits many practical inverse problems where the measurement-noise distribution is known and where the measured dataset consists of many independent noisy values. We demonstrate efficacy in two key example application areas: i) in image denoising with deep image prior, using DC instead of MSE loss removes the need for early stopping and achieves higher PSNR; ii) in medical image reconstruction from Poisson-noisy data, DC loss reduces artifacts in highly-iterated reconstructions and enhances the efficacy of hand-crafted regularization. These results position DC loss as a statistically grounded, performance-enhancing alternative to conventional fidelity losses for an important class of unsupervised noise-dominated inverse problems.
Authors: Raktim Gautam Goswami, Amir Bar, David Fan, Tsung-Yen Yang, Gaoyue Zhou, Prashanth Krishnamurthy, Michael Rabbat, Farshad Khorrami, Yann LeCun
Abstract: Modeling dexterous hand-object interactions is challenging as it requires understanding how subtle finger motions influence the environment through contact with objects. While recent world models address interaction modeling, they typically rely on coarse action spaces that fail to capture fine-grained dexterity. We, therefore, introduce DexWM, a Dexterous Interaction World Model that predicts future latent states of the environment conditioned on past states and dexterous actions. To overcome the scarcity of finely annotated dexterous datasets, DexWM represents actions using finger keypoints extracted from egocentric videos, enabling training on over 900 hours of human and non-dexterous robot data. Further, to accurately model dexterity, we find that predicting visual features alone is insufficient; therefore, we incorporate an auxiliary hand consistency loss that enforces accurate hand configurations. DexWM outperforms prior world models conditioned on text, navigation, or full-body actions in future-state prediction and demonstrates strong zero-shot transfer to unseen skills on a Franka Panda arm with an Allegro gripper, surpassing Diffusion Policy by over 50% on average across grasping, placing, and reaching tasks.
Authors: Zhuo Zhang, Yonghui Liu, Meijie Zhang, Feiyang Tan, Yikang Ding
Abstract: In this paper, we unleash the potential of the powerful monodepth model in camera-LiDAR calibration and propose CLAIM, a novel method of aligning data from the camera and LiDAR. Given the initial guess and pairs of images and LiDAR point clouds, CLAIM utilizes a coarse-to-fine searching method to find the optimal transformation minimizing a patched Pearson correlation-based structure loss and a mutual information-based texture loss. These two losses serve as good metrics for camera-LiDAR alignment results and require no complicated steps of data processing, feature extraction, or feature matching like most methods, rendering our method simple and adaptive to most scenes. We validate CLAIM on public KITTI, Waymo, and MIAS-LCEC datasets, and the experimental results demonstrate its superior performance compared with the state-of-the-art methods. The code is available at https://github.com/Tompson11/claim.
Authors: Samuel Cerezo, Javier Civera
Abstract: Deformable scenes violate the rigidity assumptions underpinning classical visual--inertial odometry (VIO), often leading to over-fitting to local non-rigid motion or to severe camera pose drift when deformation dominates visual parallax. In this paper, we introduce DefVINS, the first visual-inertial odometry pipeline designed to operate in deformable environments. Our approach models the odometry state by decomposing it into a rigid, IMU-anchored component and a non-rigid scene warp represented by an embedded deformation graph. As a second contribution, we present VIMandala, the first benchmark containing real images and ground-truth camera poses for visual-inertial odometry in deformable scenes. In addition, we augment the synthetic Drunkard's benchmark with simulated inertial measurements to further evaluate our pipeline under controlled conditions. We also provide an observability analysis of the visual-inertial deformable odometry problem, characterizing how inertial measurements constrain camera motion and render otherwise unobservable modes identifiable in the presence of deformation. This analysis motivates the use of IMU anchoring and leads to a conditioning-based activation strategy that avoids ill-posed updates under poor excitation. Experimental results on both the synthetic Drunkard's and our real VIMandala benchmarks show that DefVINS outperforms rigid visual--inertial and non-rigid visual odometry baselines. Our source code and data will be released upon acceptance.
Authors: Checheng Yu, Chonghao Sima, Gangcheng Jiang, Hai Zhang, Haoguang Mai, Hongyang Li, Huijie Wang, Jin Chen, Kaiyang Wu, Li Chen, Lirui Zhao, Modi Shi, Ping Luo, Qingwen Bu, Shijia Peng, Tianyu Li, Yibo Yuan
Abstract: High-reliability long-horizon robotic manipulation has traditionally relied on large-scale data and compute to understand complex real-world dynamics. However, we identify that the primary bottleneck to real-world robustness is not resource scale alone, but the distributional shift among the human demonstration distribution, the inductive bias learned by the policy, and the test-time execution distribution -- a systematic inconsistency that causes compounding errors in multi-stage tasks. To mitigate these inconsistencies, we propose $\chi_{0}$, a resource-efficient framework with effective modules designated to achieve production-level robustness in robotic manipulation. Our approach builds off three technical pillars: (i) Model Arithmetic, a weight-space merging strategy that efficiently soaks up diverse distributions of different demonstrations, varying from object appearance to state variations; (ii) Stage Advantage, a stage-aware advantage estimator that provides stable, dense progress signals, overcoming the numerical instability of prior non-stage approaches; and (iii) Train-Deploy Alignment, which bridges the distribution gap via spatio-temporal augmentation, heuristic DAgger corrections, and temporal chunk-wise smoothing. $\chi_{0}$ enables two sets of dual-arm robots to collaboratively orchestrate long-horizon garment manipulation, spanning tasks from flattening, folding, to hanging different clothes. Our method exhibits high-reliability autonomy; we are able to run the system from arbitrary initial state for consecutive 24 hours non-stop. Experiments validate that $\chi_{0}$ surpasses the state-of-the-art $\pi_{0.5}$ in success rate by nearly 250%, with only 20-hour data and 8 A100 GPUs. Code, data and models will be released to facilitate the community.
Authors: Yixuan Shen, Peng He, Honglu Liu, Jinxuan Fan, Yuyang Ji, Tingting Li, Tianlong Chen, Kaidi Xu, Feng Liu
Abstract: K-12 science classrooms are rich sites of inquiry where students coordinate phenomena, evidence, and explanatory models through discourse; yet, the multimodal complexity of these interactions has made automated analysis elusive. Existing benchmarks for classroom discourse focus primarily on mathematics and rely solely on transcripts, overlooking the visual artifacts and model-based reasoning emphasized by the Next Generation Science Standards (NGSS). We address this gap with SciIBI, the first video benchmark for analyzing science classroom discourse, featuring 113 NGSS-aligned clips annotated with Core Instructional Practices (CIP) and sophistication levels. By evaluating eight state-of-the-art LLMs and Multimodal LLMs, we reveal fundamental limitations: current models struggle to distinguish pedagogically similar practices, suggesting that CIP coding requires instructional reasoning beyond surface pattern matching. Furthermore, adding video input yields inconsistent gains across architectures. Crucially, our evidence-based evaluation reveals that models often succeed through surface shortcuts rather than genuine pedagogical understanding. These findings establish science classroom discourse as a challenging frontier for multimodal AI and point toward human-AI collaboration, where models retrieve evidence to accelerate expert review rather than replace it.
Authors: Pengyuan Wu, Pingrui Zhang, Zhigang Wang, Dong Wang, Bin Zhao, Xuelong Li
Abstract: Diffusion-based policies have achieved remarkable results in robotic manipulation but often struggle to adapt rapidly in dynamic scenarios, leading to delayed responses or task failures. We present DCDP, a Dynamic Closed-Loop Diffusion Policy framework that integrates chunk-based action generation with real-time correction. DCDP integrates a self-supervised dynamic feature encoder, cross-attention fusion, and an asymmetric action encoder-decoder to inject environmental dynamics before action execution, achieving real-time closed-loop action correction and enhancing the system's adaptability in dynamic scenarios. In dynamic PushT simulations, DCDP improves adaptability by 19\% without retraining while requiring only 5\% additional computation. Its modular design enables plug-and-play integration, achieving both temporal coherence and real-time responsiveness in dynamic robotic scenarios, including real-world manipulation tasks. The project page is at: https://github.com/wupengyuan/dcdp
Authors: Jiashu Yang, Chi Zhang, Abudukelimu Wuerkaixi, Xuxin Cheng, Cao Liu, Ke Zeng, Xu Jia, Xunliang Cai
Abstract: Multimodal document question answering requires retrieving dispersed evidence from visually rich long documents and performing reliable reasoning over heterogeneous information. Existing multimodal RAG systems remain limited by two bottlenecks: static retrieval that ignores query complexity, and end-to-end Vision-Language Models (VLMs) that couple visual perception with logical reasoning, leading to inefficient computation and unstable answer generation. We propose AutoThinkRAG, a complexity-aware inference architecture for multimodal document QA. It has two components: (1) a Query Complexity Router that analyzes query difficulty and structure to adaptively select retrieval and reasoning paths; and (2) a Perception--Reasoning Decoupling architecture that uses a lightweight VLM as a high-fidelity visual interpreter to convert query-relevant visual cues into textual representations, which are then passed to an LLM for logical reasoning and answer synthesis. This design improves both efficiency and robustness, especially on long-document and unanswerable queries. Experiments on DocBench and MMLongBench show that AutoThinkRAG achieves 82.13\% and 51.29\% overall accuracy, respectively, while reducing per-query token consumption by 18.9\% and monetary cost by 18.2\%. Further analyses show that the gains are most pronounced on complex queries requiring adaptive retrieval and multi-step reasoning.
Authors: Mohammed Baharoon, Thibault Heintz, Siavash Raissi, Mahmoud Alabbad, Mona Alhammad, Hassan AlOmaish, Sung Eun Kim, Oishi Banerjee, Pranav Rajpurkar
Abstract: We introduce CRIMSON, a clinically grounded evaluation framework for chest X-ray report generation that assesses reports based on diagnostic correctness, contextual relevance, and patient safety. Unlike prior metrics, CRIMSON incorporates full clinical context, including patient age, indication, and guideline-based decision rules, and prevents normal or clinically insignificant findings from exerting disproportionate influence on the overall score. The framework categorizes errors into a comprehensive taxonomy covering false findings, missing findings, and eight attribute-level errors (e.g., location, severity, measurement, and diagnostic overinterpretation). Each finding is assigned a clinical significance level (urgent, actionable non-urgent, non-actionable, or expected/benign), based on a guideline developed in collaboration with attending cardiothoracic radiologists, enabling severity-aware weighting that prioritizes clinically consequential mistakes over benign discrepancies. CRIMSON is validated through strong alignment with clinically significant error counts annotated by six board-certified radiologists in ReXVal (Kendalls tau = 0.61-0.71; Pearsons r = 0.71-0.84), and through two additional benchmarks that we introduce. In RadJudge, a targeted suite of clinically challenging pass-fail scenarios, CRIMSON shows consistent agreement with expert judgment. In RadPref, a larger radiologist preference benchmark of over 100 pairwise cases with structured error categorization, severity modeling, and 1-5 overall quality ratings from three cardiothoracic radiologists, CRIMSON achieves the strongest alignment with radiologist preferences. We release the metric, the evaluation benchmarks, RadJudge and RadPref, and a fine-tuned MedGemma model to enable reproducible evaluation of report generation, all available at https://github.com/rajpurkarlab/CRIMSON.
Authors: Shahab Aslani, Mehran Azimbagirad, Daryl Cheng, Daisuke Yamada, Ryoko Egashira, Adam Szmul, Justine Chan-Fook, Robert Chapman, Alfred Chung Pui So, Shanshan Wang, John McCabe, Tianqi Yang, Jose M Brenes, Eyjolfur Gudmundsson, The SUMMIT Consortium, Susan M. Astley, Daniel C. Alexander, Sam M. Janes, Joseph Jacob
Abstract: Background: Pleuroparenchymal fibroelastosis (PPFE) is an upper lobe predominant fibrotic lung abnormality associated with increased mortality in established interstitial lung disease. However, the clinical significance of radiologic PPFE progression in lung cancer screening (LCS) populations remains unclear. Methods: We analysed longitudinal low-dose CT scans and clinical data from two LCS studies: National Lung Screening Trial (NLST; n=7,980); SUMMIT study (n=8,561). An automated algorithm quantified PPFE volume on baseline and follow-up scans. Annualised change in PPFE was derived and dichotomised using a distribution-based threshold to define progressive PPFE. Associations between progressive PPFE and mortality were evaluated using Cox proportional hazards models adjusted for demographic and clinical variables. In SUMMIT cohort, associations between progressive PPFE and clinical outcomes were assessed using incidence rate ratios (IRR) and odds ratios (OR). Findings: Progressive PPFE independently associated with mortality in both LCS cohorts (NLST: Hazard Ratio (HR)=1.25, 95% Confidence Interval (CI): 1.01--1.56, p=0.042; SUMMIT: HR=3.14, 95% CI: 1.66--5.97, p<0.001). Within SUMMIT, progressive PPFE was strongly associated with higher respiratory admissions (IRR=2.79, p<0.001), increased antibiotic and steroid use (IRR=1.55, p=0.010), and showed a trend towards higher modified medical research council scores (OR=1.40, p=0.055). Interpretation: Radiologic PPFE progression independently associates with mortality across two large LCS cohorts, and associates with adverse clinical outcomes. Quantitative assessment of PPFE progression may provide a clinically relevant imaging biomarker to identify individuals at increased risk of respiratory morbidity within LCS programmes.
Authors: Toby Murray
Abstract: Sensitivity-based robustness certification has emerged as a practical approach for certifying neural network robustness, including in settings that require verifiable guarantees. A key advantage of these methods is that certification is performed by concrete numerical computation (rather than symbolic reasoning) and scales efficiently with network size. However, as with the vast majority of prior work on robustness certification and verification, the soundness of these methods is typically proved with respect to a semantic model that assumes exact real arithmetic. In reality deployed neural network implementations execute using floating-point arithmetic. This mismatch creates a semantic gap between certified robustness properties and the behaviour of the executed system. As motivating evidence, we exhibit concrete counterexamples showing that real arithmetic robustness guarantees can fail under floating-point execution, even for previously verified certifiers, with discrepancies becoming pronounced at lower-precision formats such as float16. We then develop a formal, compositional theory relating real arithmetic Lipschitz-based sensitivity bounds to the sensitivity of floating-point execution under standard rounding-error models, specialised to feed-forward neural networks with ReLU activations. We derive sound conditions for robustness under floating-point execution, including bounds on certificate degradation and sufficient conditions for the absence of overflow. We formalize the theory and its main soundness results, and implement an executable certifier based on these principles, which we empirically evaluate to demonstrate its practicality.
Authors: Naaisha Agarwal, Yihan Wu, Yichang Jian, Yikuan Hu, Nishad Mansoor, Mohan Li, Yifei Peng, Wang-Zhou Dai, Yao-Xiang Ding, Emanuele Sansone
Abstract: Building AI systems that can plan, act, and create in the physical world requires more than pattern recognition. Such systems must understand the causal mechanisms and constraints governing physical processes in order to guide sequential decisions. This capability relies on internal representations, analogous to an internal language model, that relate observations, actions, and resulting environmental changes. However, many existing benchmarks treat visual perception and programmatic reasoning as separate problems, focusing either on visual recognition or on symbolic tasks. The domain of origami provides a natural testbed that integrates these modalities. Constructing shapes through folding operations requires visual perception, reasoning about geometric and physical constraints, and sequential planning, while remaining sufficiently structured for systematic evaluation. We introduce OrigamiBench, an interactive benchmark in which models iteratively propose folds and receive feedback on physical validity and similarity to a target configuration. Experiments with modern vision-language models show that scaling model size alone does not reliably produce causal reasoning about physical transformations. Models fail to generate coherent multi-step folding strategies, suggesting that visual and language representations remain weakly integrated.
Authors: Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas, Andrea M. Bejar, Baver Tutun, Emre Uysal, Ezgi Bulbul, Mehmet Fatih Dogan, Berrin Erok, Berna Akkus Yildirim, Sukru Mehmet Erturk, Ulas Bagci
Abstract: Publicly available full-field digital mammography (FFDM) datasets remain limited in size, clinical annotations, and vendor diversity, hindering the development of robust models. We introduce LUMINA, a curated, multi-vendor FFDM dataset that explicitly encodes acquisition energy and vendor metadata to capture clinically relevant appearance variations often overlooked in existing benchmarks. This dataset contains 1824 images from 468 patients (960 benign, 864 malignant), with pathology-confirmed labels, BI-RADS assessments, and breast-density annotations. LUMINA spans six acquisition systems and includes both high- and low-energy imaging styles, enabling systematic analysis of vendor- and energy-induced domain shifts. To address these variations, we propose a foreground-only pixel-space alignment method (''energy harmonization'') that maps images to a low-energy reference while preserving lesion morphology. We benchmark CNN and transformer models on three clinically relevant tasks: diagnosis (benign vs. malignant), BI-RADS classification, and density estimation. Two-view models consistently outperform single-view models. EfficientNet-B0 achieves an AUC of 93.54% for diagnosis, while Swin-T achieves the best macro-AUC of 89.43% for density prediction. Harmonization improves performance across architectures and produces more localized Grad-CAM responses. Overall, LUMINA provides (1) a vendor-diverse benchmark and (2) a model-agnostic harmonization framework for reliable and deployable mammography AI.
Authors: Kejin Lu, Jianfa Bai, Qingqiu Li, Runtian Yuan, Jilan Xu, Junlin Hou, Yuejie Zhang, Rui Feng
Abstract: Accurate classification of lung diseases from chest CT scans plays an important role in computer-aided diagnosis systems. However, medical imaging datasets often suffer from severe class imbalance, which may significantly degrade the performance of deep learning models, especially for minority disease categories. To address this issue, we propose a gender-aware two-stage lung disease classification framework. The proposed approach explicitly incorporates gender information into the disease recognition pipeline. In the first stage, a gender classifier is trained to predict the patient's gender from CT scans. In the second stage, the input CT image is routed to a corresponding gender-specific disease classifier to perform final disease prediction. This design enables the model to better capture gender-related imaging characteristics and alleviate the influence of imbalanced data distribution. Experimental results demonstrate that the proposed method improves the recognition performance for minority disease categories, particularly squamous cell carcinoma, while maintaining competitive performance on other classes.