Authors: Gandhimathi Padmanaban, Rayane Moustafa, Fred Feng
Abstract: Instrumented bicycle studies have produced direct field evidence on vehicle passing behavior, but extracting overtaking events from continuous rear-facing video has remained dependent on manual, frame-by-frame annotation. This bottleneck constrains sample sizes and limits naturalistic cycling safety research. We present a geometry-informed computer vision pipeline that automates overtaking event detection from a single bicycle-mounted camera without multi-sensor configurations or explicit camera calibration. The system combines RT-DETR object detection with ByteTrack multi-object tracking through a three-stage geometric validation module enforcing bearing angle trend, apparent size growth, and spatial confirmation criteria derived from perspective projection principles. Validated on 315 manually annotated real-world overtaking events from urban roads in Ann Arbor, Michigan, the pipeline achieved 97.8% recall with zero false positives. The system identified overtaking intentions a mean of 2.44 seconds before vehicle passage, with 84.1% of events exceeding the 1.5-second human reaction time threshold, demonstrating feasibility for active cyclist warning. Lateral passing distance measurements from 96 events revealed 33.3% of passes below the 5-foot (152.4 cm) threshold, consistent with non-compliance rates in prior field and self-reported studies. A preliminary calibration-free lateral distance estimation approach using bounding box geometric features achieved mean absolute errors of 13-14 cm under leave-one-out cross-validation, sufficient to distinguish close passes from standard passes for safety categorization. By automating event isolation from consumer-grade footage, the system removes the primary annotation bottleneck of instrumented bicycle research and provides a scalable foundation for vehicle-bicycle interaction analysis across larger datasets and diverse urban environments.
Authors: Yitong Li, Junsong Chen, Haopeng Li, Haozhe Liu, Jincheng Yu, Ligeng Zhu, Ping Luo, Song Han, Enze Xie
Abstract: Modern video diffusion models achieve higher generation quality through scaling, but this also increases inference cost. Although many acceleration methods have been proposed, a central challenge is that the most effective acceleration strategy is highly instance-specific: a recipe that works well for one combination of model, hardware, and inference configuration often does not transfer to another. Different models vary in architecture, numerical sensitivity, and attention concentration patterns. Inference settings differ in spatial and temporal resolution and video duration, while hardware platforms differ in memory hierarchy, supported numerical formats, and kernel throughput. These factors create a large tuning space, making manual performance engineering costly. We present Sol Video Inference Engine, an agentic, native, training-free acceleration framework for video diffusion models. It organizes five broadly applicable techniques, cache, sparse attention, token pruning, quantization, and kernel fusion, into an agentic acceleration stack for instance-specific optimization. For a concrete deployment target defined by a model, hardware platform, and serving configuration, parallel skill agents optimize the implementation of each technique, an agent integrator composes them into a global acceleration stack, and a human validator provides feedback on generation quality. We instantiate this workflow on three video models with different sizes and architectures: 64B Cosmos3-Super, 22B LTX-2.3, and 2B SANA-Video. With little human effort, the full stack achieves more than 2x end-to-end acceleration while maintaining near-lossless VBench quality, demonstrating the effectiveness of the agent framework for video diffusion acceleration.
Authors: Yiyang Chen, Yixin Tan, Binrui Shen
Abstract: Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens. However, we observe that highest attention regions are not always consistent with the intended semantic token. This probably stems from decoding drift, where language priors from previously generated answer tokens accumulate and mismatch with visual attention. Besides the priors from previous answer tokens, we find that structural tokens, e.g., modality boundary markers, may encompass the entire context and generate high attention to areas unrelated to the target. To avoid these distortions and provide consistency evaluation for large VLMs, we adopt prompt-side semantics and propose Prompt-Vision Token Activation Map (PV-TAM). PV-TAM further incorporates a filter to remove systematic bias induced by modality boundary markers. Unlike traditional methods that evaluate overlap solely through masks while ignoring activation intensity, our metrics leverage the peak distribution of attention to measure the alignment between prompts and visual regions. In experiments, PV-TAM consistently improves both attention-based and IoU-style localization metrics over answer-side baselines on various datasets.
Authors: Yuhan Rui, Shihan Qiao, Yibin Lou, Mingxi Yu, Yutong Wan, Yanqiao Chen, Dongsheng Hou, Zhen Cao, Athena Zhuoming Zhong, Qi Hao
Abstract: Efficient small object detection is bottlenecked by the inherent feature scarcity of tiny targets, which is further aggravated by operations of spatial-domain detectors that indiscriminately discard critical high-frequency details. Recovering these fragile cues within the spatial domain is notoriously difficult, as it often requires computationally expensive architectural upscaling that inadvertently amplifies background noise. To bridge this gap, we propose a paradigm \textbf{shift from spatial to spectral} feature processing, introducing a holistic solution with the following novelty: (1) A versatile \textbf{Frequency-Guided Feature Representation framework} that generalizes across diverse detector architectures (both CNN and Transformer-based), offering a robust alternative to spatial-only feature extraction; (2) The unified \textbf{Decompose--Enhance--Reconstruct (DER)} operator, instantiated via three \textbf{lightweight, plug-and-play} modules -- Wavelet-Difference Gate (WDG), Log-Gabor Enhancer (LGE), and Frequency-Driven Head (FDHead) -- to systematically inject frequency-aware modulation into the backbone, neck, and head. This mechanism decouples feature modeling from resolution reduction, capturing discriminative high-frequency components to enable accurate localization with significantly reduced parameter redundancy; (3) Extensive validation on multi-domain benchmarks (VisDrone2019, UAVDT, TinyPerson, DOTAv1) demonstrating consistent gains. Notably, our proposed \textbf{DERNet} series outperforms YOLOv11 models under the same scale while requiring \textbf{only 1/6 of the parameters}, backed by rigorous spectral diagnostics and error decomposition analysis.
Authors: Anindya Mondal, Sauradip Nag, Anjan Dutta
Abstract: ABACUS is a unified vision-language model that handles object counting, crowd counting, referring-expression counting, and count-faithful image generation without any benchmark-specific training required. Our model is built on existing 3B-parameter unified foundation model and is adapted for object localization tasks using three key innovations: density-aware adaptive zooming with objectness maps for spatial grounding; a boundary-aware count policy via GRPO to eliminate crop-boundary errors; and a cycle-consistent GRPO strategy where the understanding branch self-critiques generated outputs, closing the understanding-generation gap without any external annotations. ABACUS achieves state-of-the-art results across seven benchmarks, outperforming both task-specific specialists and larger generalist models.
Authors: Hoang-Bao Le, Aiden Durrant, Thai Son Mai, Binh T. Nguyen, Liting Zhou, Cathal Gurrin
Abstract: Vision-Language Models (VLMs) are typically pre-trained on large-scale image-text datasets to capture semantic correspondences between visual content and natural language. However, they remain surprisingly brittle to negation: models often rely on shallow word co-occurrence and are easily distracted by misleading or irrelevant textual cues, even when their overall retrieval or classification performance is strong. Moreover, directly finetuning on negation data can interfere with previously acquired knowledge, causing noticeable degradation on standard vision-language benchmarks. To tackle these issues, this work introduces HANCLIP (Hyperbolic + Angular + Negation), a family of VLMs that explicitly restructures the embedding space to encode "what an image is not" alongside "what it is." HANCLIP is trained on a compact set of 20,000 image-text quadruplets and combines a hyperbolic formulation, which models hierarchical semantic relations and asymmetries, with an angular triplet objective that drives systematic separation between negated descriptions and their corresponding positives. This geometry-aware design strengthens negation sensitivity while preserving the global structure of pretrained representations, rather than overwriting them. Extensive experiments across multiple vision-language tasks show that HANCLIP delivers consistent gains on the negation-focused NegBench benchmark, while maintaining competitive or improved performance on standard classification and image-text retrieval benchmarks. The framework is model-agnostic and can be plugged into CLIP, LongCLIP, SmartCLIP, and HiMo-CLIP without large-scale retraining, demonstrating that a carefully designed geometric objective can substantially extend the reasoning capabilities of existing VLMs using only modest additional data.
Authors: Davide Caffagni, Alberto Compagnoni, Federico Melis, Sara Sarto, Pier Luigi Dovesi, Mark Granroth-Wilding, Marcella Cornia, Lorenzo Baraldi
Abstract: Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision encoder. However, existing methods typically align a fixed layer of the language backbone, overlooking the fine-grained structure of Transformer models. In this work, we propose Head-Wise Representation Alignment (HeRA), a method that enforces cross-modal alignment at the level of individual attention heads. Our approach is grounded in the Platonic Representation Hypothesis, focusing on preserving the topological structure of representations (i.e., their local neighborhood relationships) across modalities. Following the Mutual K-Nearest Neighbor (MKNN) alignment metric, we introduce a contrastive objective that acts as a differentiable proxy for matching local structures. HeRA applies this objective during multimodal training to specific attention heads in the LLM, selected by their alignment score according to the MKNN metric. Counterintuitively, we find that aligning the least aligned heads yields the largest gains. Extensive evaluations across multiple MLLMs and 18 benchmarks demonstrate that HeRA consistently improves performance on challenging vision-centric tasks and serves as an effective regularizer against visual hallucinations by naturally curbing the over-reliance on linguistic priors. Our code is publicly released.
Authors: Yifei Zhao, Qian Lou, Mengxin Zheng
Abstract: Vision-language models (VLMs) are increasingly used as perception-reasoning backbones for embodied intelligence in safety-critical physical systems, where perception or reasoning errors can lead to unsafe decisions or actions. Although many red-teaming methods have been developed to probe VLM vulnerabilities, their evaluation remains fragmented across datasets, metrics, and threat models, making direct comparison difficult and obscuring whether observed differences arise from stronger attacks, more vulnerable models, or incompatible evaluation settings. Existing chatbot-centric red-teaming benchmarks mainly standardize jailbreak and content-safety evaluation, but they do not systematically capture physically grounded functional failures or cover red-teaming methods that target physical-world VLMs. This raises the key challenge of comparing diverse attack methods under a unified protocol while targeting the same scenario-specific failures. We introduce REALM, to our knowledge the first unified red-teaming benchmark for physical-world VLMs. REALM integrates 12 red-teaming methods, 3 model-agnostic defenses, and 13 VLMs under a practical black-box threat model with shared datasets and metrics. To align adversarial objectives across attack families, REALM introduces an agentic target-generation pipeline that constructs shared, scenario-specific, and physically grounded attack objectives for each scene, enabling fair comparison of diverse red-teaming methods under aligned adversarial goals. Our evaluation shows that text and typographic injection attacks induce the most failures, multimodal co-optimization yields the strongest visual-perturbation transfer, single-pass attacks approach iterative methods at much lower cost, and model scale alone does not confer adversarial robustness. Code is available at https://github.com/UCF-ML-Research/REALM.
Authors: Ahmad Algadhi, Ahmed Alzuhair, Omar Alkhulaif, Muzammil Behzad
Abstract: Prompt distillation compresses large vision-language models (VLMs) such as CLIP into lightweight student models by matching teacher predictions on unlabeled domain images. PromptKD (CVPR 2024) established this paradigm with a single PromptSRC-finetuned ViT-L/14 teacher and a ViT-B/16 student. We propose TheProfessor, a multi-teacher extension that distills from a fixed two-teacher ensemble: a domain-finetuned PromptSRC ViT-L/14 teacher and a zero-shot EVA-CLIP-L/14 teacher whose logits are pre-computed per dataset. We evaluate single-teacher PromptKD, equal-probability ensembling, and confidence-weighted ensembling on four base-to-novel datasets: Caltech-101, DTD, UCF101, and EuroSAT. In a 12-run single-seed sweep, confidence-weighted ensembling improves average HM from 87.52 to 89.28 (+1.77 points), while equal averaging improves average HM to 88.88 (+1.37 points). Gains are dataset dependent: they are negligible on Caltech-101 (+0.16 HM for confidence weighting), modest on UCF101 (+0.62), and largest on domain-shifted EuroSAT (+5.78). These results update our earlier Caltech-only analysis and show that multi-teacher prompt distillation is most useful when the second teacher contributes complementary supervision under domain shift.
Authors: Tai D. Nguyen, Matthew C. Stamm
Abstract: Advances in generative AI have made image falsification highly realistic, demanding trustworthy authentication systems. Existing forensic detectors can target certain forgery types but lack interpretability, while vision-language models (VLMs) provide explanations but cannot exploit forensic traces for reliable detection. We propose Forensic Knowledge Graphs (FKGs), a unified framework that integrates forensic evidence extraction, structured reasoning, and human-interpretable explanation. Our FKG structure encodes forensic traces along with their causal dependencies and links to scene content. To generate accurate FKGs, we introduce a novel forensic authentication network and an Iterative Context Refinement strategy that guides VLMs to produce faithful, grounded explanations. We also present FKG-50K, a dataset of 50,000 realistic forgeries with ground-truth FKGs. Experiments demonstrate that FKG outperforms both forensic detectors and VLMs in detection, forgery identification and localization, and forensic justification.
Authors: Qian Wang, Zhenyu Li, Abdelrahman Eldesokey, Peter Wonka
Abstract: Subject-driven image generation faces an "Identity-Diversity Paradox", where strong identity preservation often leads to rigid and low-diversity outputs. We propose a post-training framework called DivRL that jointly optimizes identity consistency and structural diversity simultaneously by leveraging disentangled visual features from a robust similarity model. Specifically, we introduce a Negative Self-Similarity Measure (nSSM) to quantify structural diversity, and Visual Semantic Matching (VSM) to evaluate identity consistency. We propose an "Explore-and-Suppress" strategy that treats VSM as a gated constraint: the model freely explores structurally diverse configurations, and only samples that violate the identity threshold are penalized via a quadratic hinge loss. This converts identity preservation from a competing objective into a feasibility constraint, allowing nSSM and VSM to improve jointly. Experiments demonstrate that our method effectively pushes the model to generate both consistent and diverse images and improves structural diversity while maintaining comparable identity consistency through a gated optimization formulation.
Authors: Saar Huberman, Ron Mokady, Or Patashnik, Daniel Cohen-Or
Abstract: In modern generative models, images are specified and controlled through text prompts. In practice, images are generated from sequences of tokens derived from these prompts. However, the space of token sequences lacks a consistent accessible structure: semantically similar images may correspond to sequences that differ in wording, ordering, and placement of concepts, while similar token sequences may encode very different semantics. This apparent lack of structure makes it difficult to perform smooth transitions in this space, hindering applications such as image blending and continuous control of edits. We argue that this limitation stems not from the absence of semantic structure, but from misalignment between representations. To address this misalignment, we introduce Token-to-Token alignment, a framework that establishes explicit semantic correspondence between tokens across prompts. Our approach transforms prompts into a structured representation in which semantically corresponding concepts are mapped to consistent positions across prompts, and then aligns their token embeddings based on semantic similarity. Concretely, the method consists of two stages: a structural alignment that rephrases prompts into a shared structured form, followed by an embedding-level alignment that matches token representations across prompts. With this alignment in place, simple linear interpolation becomes a meaningful operation, producing smooth and coherent semantic transitions and enabling applications such as blending and continuous editing. Our results show that text embedding spaces in text-to-image models implicitly encode a continuous semantic structure that becomes accessible once representations are properly aligned, suggesting that semantic control can be achieved by organizing existing representations rather than modifying the generative model.
Authors: Jingke Wang, Zhenru Zhao, Shuangming Lei, Hao Su, Yuehao Huang, Yijia Xie, Kai Tang, Guanglin Xu, AiXue Ye, Yukai Ma, Yong Liu
Abstract: Vision-Language-Action driving models convert a pretrained Vision-Language Model into a driving policy, allowing them to use world knowledge and follow language guidances. However, existing VLA driving models still lack driving-oriented spatial intelligence: their policies are mainly grounded on perspective image tokens and language priors, while precise motion planning requires metric geometry, top-down scene structure, and attention to safety-critical perceptual cues. This limitation makes current models vulnerable to weak visual geometry modeling and perceptual coverage in expert demonstrations. In this paper, we present DriveStack-VLA, a framework built upon a large VLM backbone. To strengthen the spatial grounding of VLA driving, we develop dual visual modeling components. We inject a Bird-Eye-View representation into the Large Language Model decoder through a DeepStack-style connection, and propose Render-Teacher Alignment to align the perceptual focus of real images with that of rasterized images. Furthermore, to bridge the gap in multimodal trajectory selection, we introduce a head-based self-critique module that ranks sampled trajectories and conditionally refines the best one. DriveStack-VLA achieves 91.6 PDMS on NAVSIMv1, 91.0 EPDMS on NAVSIMv2 (with the human penalty filter enabled), and a driving score of 79.49 with a success rate of 56.36\% on the closed-loop Bench2Drive. More visualizations are available on our project page: https://anonymous.4open.science/w/drivestack-vla/.
Authors: Hoang-Phuc Nguyen, Dinh-Khoi Vo, Trong-Le Do, Hai-Dang Nguyen, Tan-Cong Nguyen, Vinh-Tiep Nguyen, Tam V. Nguyen, Khanh-Duy Le, Minh-Triet Tran, Trung-Nghia Le
Abstract: The demand for image manipulation has seen a significant increase recently. Traditional tools like Photoshop and Capture One, while powerful, require considerable expertise to use effectively. Generative AI has introduced alternative platforms, such as Luminar Neo, Pixlr X, and Canva. However, many of these solutions, including resource-heavy models like Stable Diffusion, often require substantial retraining and fine-tuning, leading to high costs for users. To address these challenges, we introduce Efficient Photo Editor (EPEdit), an application that integrates a robust backend framework with a user-friendly front-end interface. EPEdit supports a wide range of creative image editing tasks, including image generation, object replacement, object removal, background modification, changes in object pose or perspective, region-specific editing, and thematic collection design, all guided by masks and prompts. Users can interact with the system through simple text commands or by marking areas for precise adjustments, making it accessible even to those without technical expertise. At its core, EPEdit leverages zero-shot image editing algorithms based on Stable Diffusion model, removing the need for additional fine-tuning. This approach enables efficient image manipulation and thematic collection creation. User evaluations for tasks of image editing, thematic design, and overall system performance demonstrate that EPEdit outperforms existing solutions, offering a user-friendly, cost-effective solution for comprehensive image editing.
Authors: Phuc-Tan Nguyen, Hieu Nguyen, Minh-Triet Tran, Trung-Nghia Le
Abstract: This paper aims to bridge the semantic gap between visual content and natural language understanding by leveraging historical events in the real world as a source of knowledge for caption generation. We propose VisChronos, a novel framework that utilizes large language models and dense captioning models to identify and describe real-life events from a single input image. Our framework can automatically generate detailed and context-aware event descriptions, enhancing the descriptive quality and contextual relevance of generated captions to address the limitations of traditional methods in capturing contextual narratives. Furthermore, we introduce a new dataset, EventCap (https://zenodo.org/records/14004909), specifically constructed using the proposed framework, designed to enhance the model's ability to identify and understand complex events. The user study demonstrates the efficacy of our solution in generating accurate, coherent, and event-focused descriptions, paving the way for future research in event-centric image understanding.
Authors: Jonesh Shrestha
Abstract: Food images often contain several visible ingredients, so assigning one dish label to an entire image hides important visual structure. This work studies ingredient-level semantic segmentation on FoodSeg103, where the model predicts an ingredient class for each pixel. Two SegFormer variants were fine-tuned and evaluated under a controlled setup: SegFormer-B0 as the smaller baseline model and SegFormer-B1 as the larger final model. Both models use ImageNet-pretrained MiT backbones with newly initialized 104-class output layers. On the held-out FoodSeg103 test split of 2,135 images, B0 achieved 0.7709 pixel accuracy and 0.2521 mean IoU, while B1 achieved 0.7929 pixel accuracy and 0.3204 mean IoU. B1 improved every saved test metric, including a +0.0683 absolute gain in mean IoU. The system also converts predicted masks into visible ingredient-area percentages, giving a simple visual composition summary of the predicted meal. This summary can serve as a first-pass nutrition-awareness cue by providing a visual alternative to detailed food tracking similar to plate-based meal guidance, but it is not a direct estimate of calories, macronutrients, food mass, volume, density, or true portion size.
Authors: Taekbeom Lee, Youngseok Jang, Jeonghwa Heo, Jeongjun Choi, H. Jin Kim
Abstract: Embodied reasoning and exploration are increasingly considered crucial abilities for robots operating in complex and unfamiliar environments. To accomplish tasks in such settings, an agent must identify and acquire the information necessary for the task through exploration. We propose ObsGraph, an observation-centric hierarchical scene graph that unifies scene representation, retrieval, and exploration. It retains visual evidence and organizes it into room-view-object layers: rooms provide coarse semantic anchors, views preserve contextual object covisibility, and objects store fine-grained details. On top of this representation, we perform coarse-to-fine hierarchical retrieval under a bounded budget, and crucially use retrieval outcomes to structure the exploration candidate space--activating room-level exploration, view refinement, or frontier exploration--thereby tightly coupling representation, retrieval, and adaptive multi-scale exploration. Experiments across embodied reasoning and exploration benchmarks demonstrate improved success and efficiency, highlighting the benefits of structured scene representation and more targeted information gathering driven by identified evidence gaps.
Authors: Pengchao Wei, Xiaojie Guo
Abstract: Fabric moir\'e is a sampling-induced aliasing artifact caused by the interaction between fine textile patterns and camera sensor grids, producing structured interference that severely degrades image quality. Unlike screen-induced moir\'e, which stems from strictly periodic display lattices, fabric moir\'e is intrinsically more challenging due to the broadband and semi-periodic nature of textile weaves. The heavy spectral overlap between intrinsic texture and aliasing components renders fabric demoir\'eing substantially more ill-posed. Consequently, existing models trained on screen moir\'e datasets generalize poorly to these complex textile patterns. Despite its practical importance, fabric image demoir\'eing remains underexplored and lacks standardized benchmarks. We present the first comprehensive benchmark for fabric image demoir\'eing. To address the difficulty of acquiring pixel-aligned real-world pairs, we develop a physically motivated synthesis framework and construct a large-scale dataset comprising 16,050 paired multi-resolution fabric images with controllable aliasing severity. Furthermore, we customize a baseline model, which establishes promising performance on the proposed benchmark dataset with strong generalization ability. Our benchmark provides a standardized platform for advancing research in fabric image demoir\'eing.
Authors: Xiaohu Li, Chongxiao Qu, Caiyong Lin, Chenxiao Dou, Wei Hua
Abstract: Although deep learning-based methods can achieve high accuracy in automatic modulation recognition (AMR) tasks, their high computational cost makes it difficult to strike a balance between accuracy and power consumption, thereby limiting their application on resource-constrained platforms. Neuromorphic architectures that perform spike-driven inference with modest energy budgets have recently been explored for vision and timeseries tasks. Motivated by these works, we propose EMRFormer, a novel end-to-end spiking nerural network (SNN) architecture that applies spike-driven transformer to the constraints of neuromorphic hardware for AMR. The model incorporates an adaptive spike encoder and Integer Leaky Integrate-and-Fire neurons to mitigate the degradation of effective information and enhance SNN representational capacity. By integrating spike-separable Convolution Neural Networks (SSCNN) into Spike-Driven Transformers (SpikeFormer), EMRFormer effectively extracts multi-scale temporal features from the raw IQ waveforms. We validate our approach across various mainstream datasets, the experimental results show that EMRFormer achieves state-of-the-art interms of accuracy, outperforming all the baselines. Furthermore, the model maintains strong performance in low signal-to-noise(SNR) environments and reduces theoretical energy consumption by over 90%. Finally, we evaluate our model on a KA200 neuromorphic chip. The results show that our model achieves up to 5 times reduction in power compared to running on a 3090 GPU or an Orin NX. This work demonstrates a promising pathway for AMR on resource-constrained devices.
Authors: Tian Qiu, Jifeng Shen, Xin Zuo
Abstract: Effective cross-modal feature alignment and interaction are central challenges in multispectral object detection. Although global cross-attention provides strong long-range modeling ability, its quadratic complexity with respect to feature size limits deployment on resource-constrained platforms. We therefore propose Progressive Pixel-Neighborhood Deformable Cross-Attention for multispectral feature fusion, termed PNAFusion. The proposed framework is motivated by two observations: weak misalignment between visible and thermal images is usually concentrated around local neighborhoods, and semantic correspondence across modalities often follows non-linear spatial mappings that fixed receptive fields cannot model well. To address these issues, PNAFusion incorporates local spatial priors into its architectural design to concentrate feature interaction and alignment on the most relevant neighborhoods. Specifically, a Pixel-Neighborhood Cross-Attention (PNCA) module is introduced to avoid redundant global feature matching and suppress background noise. Meanwhile, an Adaptive Deformable Alignment (ADA) module captures non-linear spatial correspondences through learned pixel-wise offsets. These components are further integrated through an iterative feedback mechanism to progressively refine cross-modal feature alignment. Experiments on FLIR, M3FD, and DroneVehicle show that PNAFusion achieves 84.2, 90.5, and 85.5 mAP@0.5, respectively, under the YOLOv5 detector, and further reaches 86.8 mAP@0.5 on FLIR and 90.8 mAP@0.5 on M3FD when transferred to Co-DETR. Efficiency analysis indicates that PNAFusion reduces allocated GPU memory by 33.0\% compared with ICAFusion and reduces theoretical FLOPs from 194.8 G to 156.4 G, although the deformable sampling and iterative refinement introduce additional latency. Our code will be available at https://github.com/DanielQiuTian/PNAFusion.
Authors: Wenliang Zhong, Rob Barton, Lucas Goncalves, Kushal Kumar, Feng Jiang, Hehuan Ma, Yuzhi Guo, Vidit Bansal, Karim Bouyarmane, Junzhou Huang
Abstract: Unifying image clustering across different clustering scenarios remains challenging due to fundamental gaps among tasks. We introduce a Guideline-Driven Image Clustering Agent, the first universal framework that bridges these gaps through textual guidelines. To incorporate complex guidelines without task-specific training, we propose Generative Concept Proxy Modeling, which generates guideline-aware embeddings via concept proxy extraction. For scenarios requiring automatic cluster discovery, we introduce LLM Traversal based on Minimum Spanning Tree that selectively applies LLM reasoning for complex semantic judgments. Our method generalizes across diverse clustering scenarios spanning from general to fine-grained categorization, from global to local criteria, and from balanced to long-tail distributions. Our framework consistently outperforms specialized methods across diverse clustering tasks.
Authors: Reeshad Khan, John Gauch
Abstract: Robust perception underpins autonomous driving, and most recent progress comes from scaling the model-larger backbones, foundation models, and cooperative multi-agent fusion. We pursue a complementary, upstream question: what should the camera itself measure? Using a differentiable RAW-to-task pipeline, we decompose which sensor degrees of freedom benefit dense prediction. Learning the spectral colour-filter-array (CFA) weights is the dominant lever, improving mIoU by +0.017 (KITTI-360) and +0.023 (ACDC) over a fixed camera. In contrast, point-spread-function (optics) co-design is net-negative (-0.020 mIoU on KITTI-360) - a consequence of the data-processing inequality, which also bounds the task information that any downstream model, however large or cooperative, can recover. Noise co-optimisation is marginal, and counter to intuition enlarging the CFA tile beyond 2x2 consistently hurts, as the filters are confined to the rank three sRGB input. Because the intervention is at the sensor, the gains are model-agnostic; we validate robustness on ACDC's fog, night, rain, and snow, and conclude with a simple recipe: learn the 2x2 CFA weights and keep an identity PSF.
Authors: Hengji Zhou, Sijie Liu, Jianrun Chen, Xingchen Zou, Lianghao Xia, Liqiang Nie
Abstract: Short dramas, with their rapid shot rhythms, dialogue-driven focus shifts, and demanding cinematographic grounding, pose challenges that prompt-level or text-only video generation pipelines struggle to meet. We study plot-to-short-drama generation, where a global plot and local context are transformed into visually grounded multi-shot videos. We propose DramaDirector, a geometry-grounded framework that lets the planner borrow cinematographic geometry from a gallery of real short-drama shots indexed by depth and pose. DramaDirector decouples each shot into static visual and dynamic narrative conditions, trains the planner with schema-constrained SFT and GRPO under a learned text-visual alignment reward, and retrieves depth-pose references to guide first-frame generation and image-to-video synthesis. We also introduce DramaBoard, a benchmark built from 35 live-action dramas, 2.8K episodes, and 81K shots, with structured storyboards and multi-dimensional evaluation protocols. Experiments show that DramaDirector improves over representative multi-agent and video generation baselines on faithfulness, consistency, and controllability. Our code is released at: https://github.com/iLearn-Lab/DramaDirector
Authors: Aminu Lawal, Niyoj Oli, Sachin Acharya, Prashnna Gyawali, Maria Carmen Romano, Binod Bhattarai
Abstract: Vision-language models (VLMs) are prone to hallucination, which remains a major barrier to their safe deployment in clinical practice. To date, most hallucination detection methods have been evaluated on radiology benchmarks such as MIMIC-CXR and VQA-RAD, while gastrointestinal (GI) endoscopy remains largely underexplored. In this paper, we benchmark nine hallucination detection methods on the Gut-VLM dataset, a GI diagnostic Visual Question Answering (VQA) dataset with 4,392 test VQA pairs, across five VLMs (MedGemma-4B, MedGemma-27B, LLaVA-Med-7B, LLaVA-v1.6-7B, and Lingshu-32B). The methods span three categories: black-box methods (RadFlag, SelfCheckGPT-NLI), gray-box methods (AvgProb, AvgEnt, MaxProb, MaxEnt, Semantic Entropy, and VASE), and a white-box method (ReXTrust). Our results show that ReXTrust, a white-box method, achieves the highest AUC across all five models, outperforming the strongest alternative method on each VLM by a statistically significant margin (paired permutation test, p < 0.001 in all cases), reaching a peak AUC of 93.0 on MedGemma-4B. White-box hidden-state access provides a consistent advantage of 19.5 AUC points on average (range: 9.5--33.5), with ReXTrust maintaining strong performance even on LLaVA-v1.6-7B (AUC 79.9), where black-box methods and clustering-based gray-box methods collapse to near-chance performance. Among non-white-box methods, token-level gray-box statistics (MaxEnt, MaxProb) are the strongest alternatives, outperforming both clustering-based gray-box methods (Semantic Entropy, VASE) and black-box approaches on average. We further identify confident confabulation, a failure mode in which models hallucinate with high inter-sample consistency or high token-level probability, as a systemic failure for both consistency and uncertainty-based methods.
Authors: Yijian Lu, Chuangxin Zhao, Kai Sun, Lei Hou, Juanzi Li, Ji Qi
Abstract: Visual grounding in documents is a crucial ability for Large Multimodal Models (LMMs) in areas such as document understanding, deep research and document error detection. However, existing approaches exhibit poor grounding precision in text-rich document images, often failing to accurately locate the critical document elements needed for reliable reasoning. To address this gap, we introduce PreciseDoc, an LMM specifically designed for precise element grounding and can be further optimized for Document VQA tasks. Specifically, to enhance the basic localization capability, we construct challenging training data by two pipelines capable of mass-producing high-quality documents with paired metadata of fine-grained coordinates, including synthetic hand-filled documents with camera effects. The model develops more real-world functions beyond straightforward localization of single text, such as locating personal information from CVs. Furthermore, we introduce a training paradigm for visual grounded reasoning where the grounding and reasoning are supervised jointly with reinforcement learning to improve the contribution of the grounded evidence. A comprehensive evaluation on various benchmarks demonstrates the advantage of the proposed data and methods in document spatial grounding and document understanding.
Authors: Vladyslav Polushko, Tilman Bucher, Ronald R\"osch, Thomas M\"arz, Markus Rauhut, Andreas Weinmann
Abstract: Timely, high-resolution maps of flood extent around settlements are essential for emergency response and damage assessment. We consider airborne RGB imagery for flood mapping as it can be collected rapidly at low cost. To produce flood maps, deep learning models for water segmentation are often used. CNN based and small vision transformer models are used. However, they need much data for adaptation to a change of scenery, i.e., another flooding event. Vision foundation models or large vision transformers are known to generalize across domains. Recently, foundation models for Earth observation became available. They are pretrained on satellite data, whose spatial resolution, viewing geometry, and radiometry differ from nadir RGB imagery. Thus, adaptation is required. We investigate how a satellite-pretrained Earth observation foundation model can be adapted to centimeter-scale floodwater mapping from RGB imagery. Specifically, we fine-tune a model we call Prithvi-2.0-UPN consisting of the Prithvi-EO-2.0-600M Vision Transformer combined with a UPerNet decoder for binary water segmentation on two RGB datasets (BlessemFlood21, NeuenahrFlood). In a first experiment we observe that Prithvi-2.0-UPN reaches state-of-the-art results on BlessemFlood21 and NeuenahrFlood, when trained on their datasets. In a second experiment we show that Prithvi-2.0-UPN performs better than state-of-the-art baseline models for transfer to a new flood event (trained on BlessemFlood21, tested on NeuenahrFlood) in a zero-shot setting. However, the performance indicates room for improvement. In this respect, we investigate in a third experiment how performance improves when further fine-tuning the models with small shares of NeuenahrFlood training data: Prithvi-2.0-UPN improves the fastest and reaches almost the performance level when fully trained on NeuenahrFlood, indicating transfer capabilities.
Authors: Md. Ahanaf Arif Khan, Md. Tawhidur Rahman, Sangeeta Biswas, Md. Iqbal Aziz Khan, Subrata Pramanik, Sanjoy Kumar Chakravarty, Bimal Kumar Pramanik
Abstract: Existing head pose datasets predominantly feature subjects of Western or East Asian origin, leaving South Asian populations, particularly Bengali individuals, largely underrepresented. We introduce Bengal-HP_RU, the first publicly available head pose dataset centred on Bengali subjects, comprising 12,894 labelled head images annotated with continuous yaw, pitch, and roll values. Images were collected from Wikimedia Commons under free licences and processed through an automated pipeline followed by manual label correction. The dataset is partitioned by Wikimedia uploader identity to prevent data contamination, yielding 10,494 training and 2,400 test images across 296 unique uploaders. Bengal-HP_RU exhibits substantial diversity in subject age, gender, occlusion, illumination, and background, reflecting realistic in-the-wild conditions. The dataset is publicly available at https://doi.org/10.17632/xbw9kr37jb.2.
Authors: Tongyan Hua, Dongli Wu, Jinjing Zhu, Yinrui Ren, Zhongcheng Hong, Ying-Cong Chen, Hui Xiong, Wufan Zhao
Abstract: Generating explicit 3D city assets from a single satellite image is important for digital twins, urban simulation, and geospatial intelligence. Unlike satellite-to-street-view synthesis, the task requires a reusable textured mesh with plausible geometry and controllable appearance rather than a 3D proxy optimized only for rendering a small set of images or videos. The ICCV Sat2City framework made a first step by conditioning cascaded sparse-voxel latent diffusion on satellite-derived height maps, but its appearance was random, its training data were synthetic, and its task-specific VAE did not scale well to noisy real-world reconstructions. We present Sat2City v2, a journal extension that adapts a pretrained native structured-latent 3D foundation model to weakly aligned satellite images and textured meshes. We build a real-world dataset with 16,241 satellite-mesh pairs across 24 regions in 9 cities. Instead of learning a 3D representation from noisy city meshes, Sat2City v2 encodes each mesh into a pretrained native 3D latent space, fine-tunes a satellite-conditioned geometry flow, and uses the decoded shape to anchor satellite-conditioned texturing. This retains Sat2City's geometry-to-appearance cascade while enabling appearance-controllable generation from the satellite input. Experiments on metric-scale DSM reconstruction and generative city-asset benchmarks for geometry and appearance show that Sat2City v2 achieves the best overall performance among evaluated baselines. Overall, Sat2City v2 advances satellite-to-city generation from rendering-oriented 3D proxies to explicit textured mesh assets, supported by, to the best of our knowledge, the first documented satellite-mesh paired dataset collected from matched geographic crops for this asset-level task. Project page: https://ai4city-hkust.github.io/Sat2City-v2/
Authors: Min Hyeok Bang, Jun Hyeong Kim, Seung-Wook Kim, Se-Ho Lee
Abstract: In this paper, we present a novel geometry-aware style transfer framework for 3D Gaussian splatting (3DGS) that simultaneously transfers appearance attributes and geometric structures. Unlike prior works that primarily focus on color-based stylization and often overlook structural adaptation, our method explicitly incorporates geometry adaptation through a decoupled optimization scheme that alternately updates color and geometry parameters. This strategy alleviates potential interference between color and geometry updates, leading to stable and consistent scene-level geometry transformation. The decoupled optimization is enabled by the proposed geometry-aware contrastive feature matching (GCFM). GCFM integrates RGB, depth, and edge cues into a contrastive objective and is employed in both optimization phases to effectively transfer structural characteristics from style images to Gaussian primitives. Extensive experiments show that our approach achieves superior performance in both qualitative fidelity and quantitative metrics, significantly outperforming existing 3DGS-based stylization methods. Our code is available at \href{https://github.com/oweixx/gast}{https://github.com/oweixx/gast}.
URLs: https://github.com/oweixx/gast, https://github.com/oweixx/gast
Authors: Xin Wang, Wenxuan Liu, Tongtong Feng, Wenwu Zhu
Abstract: Existing literature claims that video generation essentially is world modelling. On the one hand, the claim is productive because it pushes generative AI beyond static images and toward temporally extended physical scenes. On the other hand, this claim dangerously relies on the belief that scaling visual prediction alone will automatically yield physical agents. We prefer a more accurate statement: video generation models learn a partial, implicit spatiotemporal world model, but not a fully grounded or controllable one. The reason is as follows: a model may generate a plausible video of a drone crossing a forest or a robot arm manipulating a cup, yet still fail to know which variables are controllable, which constraints belong to a particular body and which futures remain valid under intervention. The frontier in essence is not predictive realism alone, instead it emphasizes a self-evolving generative nature that requires the decisive criterion to be counterfactual controllability: the capability of asking what would happen under an action, to test whether the generated future can survive embodiment constraints and to feed the resulting action knowledge back into future imagination (generation). Therefore, in this paper we present a new perspective, i.e., autonomous video generation with counterfactual controllability is one promising way to realize self-evolving world models.
Authors: Muyuan Zhang, Jiancheng Zhang, Haijin Zeng, Yin-ping Zhao
Abstract: While Deep Unfolding Networks (DUNs) dominate video Snapshot Compressive Imaging (SCI), they remain constrained by a uniform design philosophy. Existing methods repeatedly stack high-complexity priors with identical structures, ignoring the fact that optimization trajectories converge toward static states. This results in representation stagnation, where high-cost computations are wasted on minimal feature updates. To address this inefficiency, we present Differential Unfolding (DU), a heterogeneous framework that replaces uniform repetition with dynamic evolution. Central to DU is the Differential Evolutionary Framework (DEF), which partitions the unfolding process into two complementary roles: structural anchoring and differential evolution. In this scheme, high-parameter general stages are sparsely deployed to generate high-fidelity feature foundations. Complementing these, lightweight differential stages employ a Differential Representation Prior (DRP) to propagate and refine these foundational features through a differential mechanism. By integrating Differential Representation Attention (DRA) for evolving attention maps and a Differential Modulated FFN (DM-FFN) for feature rectification, DRP effectively models cross-stage variations with minimal overhead. By focusing computational resources on dynamic evolution rather than static redundancy, DU achieves a superior trade-off between accuracy and efficiency. Extensive experiments verify that our method establishes new state-of-the-art results while significantly slashing computational overhead. https://github.com/Muyuan-Zhang/DU
Authors: Zengjie Chen, Yuxiang Cai, Jingcai Guo, Taotao Cai, Jianwei Yin, Zhi Chen
Abstract: Visual token reduction has emerged as an effective strategy for accelerating Multimodal Large Language Models (MLLMs). Many existing methods prune tokens by ranking text-visual attention scores. However, we show that attention is often dominated by a model-induced prior: even without textual instruction, MLLMs tend to focus on certain task-agnostic regions. Consequently, the attention scores of instruction-conditioned tokens are suppressed, increasing the risk that these tokens are discarded during pruning. To address this issue, we propose Prior-Corrected Token Reduction (PriorTR), a training-free token reduction method that explicitly separates task-conditioned attention from the model-induced prior. PriorTR estimates the attention map of the prior, and contrasts it with the task-conditioned attention distribution to measure the additional usable information contributed by each visual token. Importantly, PriorTR computes both the model-induced prior and the task-conditioned posterior within a single forward pass by introducing a null token that serves as an instruction-agnostic probe in the attention block. This design avoids duplicated propagation. Extensive experiments across multiple multimodal benchmarks and MLLMs demonstrate that PriorTR consistently improves the trade-off between accuracy and efficiency over strong training-free baselines, particularly under aggressive token budgets.
Authors: Xiangqian Zhao, Xinyang Jiang, Zhipeng Xu, Lingfeng He, Zilong Wang, Dongsheng Li, De Cheng, Nannan Wang
Abstract: Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes, resulting in poor generalization on minority groups. Bias mitigation remains challenging due to two fundamental issues. First, when group labels are unavailable, existing group-unsupervised methods typically infer spurious attributes implicitly from model behavior, making it difficult to identify spurious factors that are semantically aligned with real-world biases. Second, even with pseudo spurious supervision, most existing debiasing methods follow a single-branch design that operates within a single shared feature space, where target and spurious attributes are intrinsically entangled. To address the first challenge, we introduce Confidence-guided Bias Concept Mining (CBCM), which leverages diffusion-disentangled, semantically grounded concept representations to identify reliable spurious attributes without attribute annotations. To address the second challenge, we propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches and explicitly removes spurious information through cross null-space projection while preserving target-relevant semantics. Extensive experiments on four benchmark datasets show that our method achieves state-of-the-art worst group accuracy among group-unsupervised approaches, while tuning at most 0.22% of the model parameters. The source code is available in the supplementary materials.
Authors: Bin Chen, Yuxiang Cai, Yadan Luo, Yi Zhang, Jianwei Yin, Zhi Chen
Abstract: Reducing visual token redundancy is critical for accelerating Multimodal Large Language Models (MLLMs) without degrading cross-modal reasoning performance. Existing token pruning methods typically rely on single-layer signals, such as attention scores or token similarities, which overlook the cross-layer transformation of visual representations and may exhibit positional bias in multimodal token sequences. To address this limitation, we propose a training-free token pruning framework based on Cross-Layer Spectral Evolution (CLSE). Instead of measuring token importance from single-layer feature magnitudes, CLSE quantifies how token representations evolve across Transformer layers in the frequency domain. This evolution reflects the transition from high-frequency structural details to low-frequency semantic abstractions. We observe that tokens with stronger spectral redistribution across layers are more likely to be semantically active and should therefore be preserved. By modeling cross-layer token dynamics, CLSE provides a stable importance criterion that mitigates positional bias. Extensive experiments on both image and video benchmarks demonstrate that CLSE achieves a superior trade-off between efficiency and accuracy under aggressive token reduction. Across multiple MLLMs, CLSE reduces FLOPs, KV cache memory, and latency while maintaining competitive or improved performance.
Authors: Yiding Sun, Dongxu Zhang, Jihua Zhu, Haozhe Cheng, Zhengqiao Li, Pengcheng Li, Chaowei Fang, Yonghao Dong, Lin Chen
Abstract: While point cloud foundation models have significantly advanced point cloud video understanding, existing parameter-efficient fine-tuning (PEFT) methods still suffer from two critical limitations: prohibitive annotation costs for large-scale point cloud datasets and severe memory bottlenecks. In this paper, we aim to mine richer supervision signals from existing data rather than blindly scaling datasets. A further key principle is that the memory footprint of fine-tuning must be drastically reduced compared to full fine-tuning, which remains elusive for current PEFT techniques. Driven by these challenges, we identify three core desiderata: data-, parameter-, and memory efficiency, and present PoinTriE, a unified framework that excels along all three dimensions. For pre-training, pseudo-motion trajectories are synthesized via rigid transformations, paired with text corpora and 2D projections derived from raw point clouds. We then propose a Geometric-Motion Duality Network optimized via multimodal contrastive learning, rigid rotation prediction, and motion distribution divergence to produce dense self-supervision. During fine-tuning, we freeze the pretrained backbone and only update a lightweight Spatio-temporal Side Network built with LoRA units. Equipped with a gradient flow masking strategy, PoinTriE simultaneously reduces memory consumption and parameter overhead. Extensive experiments confirm that PoinTriE establishes new state-of-the-art results on action recognition and semantic segmentation tasks.
Authors: Dominik Lindner, Johann Schmidt, Tom Siegl, Martin Becker, Sebastian Stober
Abstract: Pretrained vision models often misclassify inputs that are rotated, scaled, or sheared, even though these affine transformations leave the object class unchanged. Robustness is usually restored either by building equivariance into the architecture or by retraining with augmentation, both of which require changing or retraining the model. Test-time canonicalization instead leaves the classifier untouched. It undoes the transformation of each input, mapping it to a canonical form near the training distribution before classification. Existing canonicalizers, however, rely on a narrow set of logit-based energy scores and bespoke search procedures, leaving the design space of scoring functions and optimizers unexplored. We reframe canonicalization as out-of-distribution (OOD) detection, which lets any OOD score serve as the energy minimized over transformations. Across benchmarks ranging from handwritten characters and sketches to natural images and 3D point clouds, we systematically evaluate around twenty OOD scores and nine search algorithms, finding that distance-based scores paired with random search and local refinement perform best overall. Because canonicalizing an already-aligned input can hurt accuracy, we add a gated mechanism that transforms an input only when its OOD score indicates this is needed, preserving most in-distribution accuracy while retaining the robustness gains on transformed inputs. Code is available at github.com/johschm/its.
Authors: Afifa Khaled, Said Jadid Abdulkadir, Majdy Mohamed Eltayeb Eltahir
Abstract: Three-dimensional scene completion has evolved as a major problem in computer vision and robotics, and its applications are diverse, including autonomous navigation and augmented reality. In this study, a systematic review has been conducted to compile the research contributions made in the last ten years, i.e., 2016 to 2026, which has revolutionized the field from the voxel semantic completion paradigm represented by SSCNet to the latest paradigm that combines generative diffusion priors with real-time rendering using a Gaussian splatting technique. The evolution in representation paradigms, such as voxel grids, point learning, implicit neural fields, transformer networks, diffusion networks, and the latest paradigm based on rendering-aware 3D Gaussian primitives, has been discussed in this study. A comprehensive analysis has been carried out on the contributions made in the last ten years, and a taxonomy has been developed to provide a clear idea about the contributions made in the field. The study has also discussed the research contributions made in the field, along with the challenges that still need to be addressed. Finally, the study has presented a research agenda that will provide a clear idea about the directions that can be followed in the development of the next-generation system
Authors: Kun Zhang, Chenxin Fang, Tao Chen, Baiyang Song, Yunhang Shen, Yiyi Zhou, Rongrong Ji
Abstract: Long video understanding remains a daunting challenge for Multimodal Large Language Models (MLLMs) due to the excessive computation and memory footprint. Thus, keyframe selection is often adopted to mitigate this shortcoming, which however still suffers from low flexibility and high noise due to its hard sampling principle. In this paper, we define video frame selection as a problem of Quasi-Gaussian Sampling, and propose an adaptive and training-free approach termed AdaQ. Inspired by the 3-$\sigma$ rule of Gaussian distribution, the objective of AdaQ is to achieve the optimal 3-$\sigma$ interval for different examples, i.e., a smaller 3-$\sigma$ interval for the local query and a larger one for the global query, thereby facilitating robust and adaptive frame sampling. To validate AdaQ, we apply it to four MLLMs with three embedding models. The extensive experimental results not only show its obvious performance gains over the default MLLMs and the SOTA keyframe selection methods, e.g., helping Qwen3-VL-8B outperform GPT4o by 15.8% on average by using only 64 frames, but also confirm its superior robustness and high efficiency for long-video understanding, e.g., only 1 hyper-parameter needs to be set.
Authors: Miso Kim, Georu Lee, Yunji Kim, Hoki Kim, Jinseong Park, Woojin Lee
Abstract: Unlearning has emerged as a key technique to mitigate harmful content generation in diffusion models. However, existing methods often remove not only the target concept, but also benign co-occurring concepts. As illustrated in Fig.1, unlearning nudity can unintentionally suppress the concept of person, preventing a model from generating images with person. We define these undesirably suppressed co-occurring concepts that must be preserved CARE (Co-occurring Associated REtained concepts). Then, we introduce the CARE score, a general metric that directly quantifies their preservation across unlearning tasks. With this foundation, we propose ReCARE (Robust erasure for CARE), a framework that explicitly safeguards CARE while erasing only the target concept. ReCARE automatically constructs the CARE-set, a curated vocabulary of benign co-occurring tokens extracted from target images, and leverages this vocabulary during training for stable unlearning. Extensive experiments across various target concepts (Nudity, Van Gogh style, and Tench object) demonstrate that ReCARE achieves overall state-of-the-art performance in balancing robust concept erasure, overall utility, and CARE preservation.
Authors: Chang Liu, Mingwen Shao, Xiang Lv, Xinyuan Chen, Lingzhuang Meng, Qiao Zhang, Zhengyi Gong, Jinghao Hu
Abstract: Recent breakthroughs in 3D generation have advanced notably with the development of text-to-image diffusion model. However, existing methods remain two practical challenges: (1) They primarily generate single 3D object, but struggle to generate multi-object compositional 3D assets due to the lack of the modeling for Gaussian primitives in reasonable interactions. (2) They often suffer from cross-view inconsistency during 3D optimization, as Score Distillation Sampling inherently performs on each single view, inevitably resulting in cross-view hallucinations. To solve above issues, we propose I2C-3D, a novel optimization-based method to generate multi-view consistent compositional 3D assets with reasonable interactions. Specifically, we propose an Inclusive Interactive Collisions strategy to guide Gaussian primitives appearing in reasonable interaction regions naturally, thereby ensuring objects in the compositional scene interact in a physically plausible and visually coherent way. Additionally, to enhance multi-view consistency, Multi-View Adaptive Score Distillation Sampling is devised to distill multi-view consistency prior and layout prior from pre-trained diffusion model by modulating attention map of instance token and spatial token across viewpoints. Benefiting from above elaborate designs, I2C-3D not only generates high-fidelity multi-view consistent compositional 3D assets but also supports 3D editing flexibly, facilitating complex scene generation. Extensive experiments demonstrate our I2C-3D outperforms existing methods in generation quality and multi-view consistency.
Authors: Fuyou Mao, Yifei Chen, Beining Wu, Lixin Lin, Jinnan Dai, Zhiling Li, Yilei Chen, Yaqi Wang, Hao Zhang, Yan Tang, Huiyu Zhou, Feiwei Qin
Abstract: Accurate pulmonary vessel segmentation remains challenging due to the sparse, tortuous, and multi-scale nature of vascular structures, where small branches are easily lost and topology integrity is difficult to preserve under voxel-wise supervision. Existing deep segmentation models primarily optimize binary masks, lacking explicit geometric constraints, thus struggling to recover continuous tubular morphology and fine vascular connectivity. In this study, we introduce MorVess, a morphology-aware segmentation framework that integrates differentiable geometric priors with large-scale foundation model adaptation to achieve fine-grained vascular parsing. MorVess jointly predicts vessel masks, distance maps, and thickness maps, providing explicit supervision for vascular boundaries, centerline consistency, and smooth diameter transitions. A lightweight 2.5D adapter bridges 3D spatial context and 2D SAM representations, while a global-local fusion block aggregates multi-level semantics and geometric cues for high-fidelity topology reconstruction. Across two challenging pulmonary CT benchmarks, MorVess delivers superior Dice, clDice, and HD95 scores, substantially improving small-vessel recovery and global connectivity. These results demonstrate that embedding geometric intelligence into pretrained vision models offers a principled and scalable pathway toward precise vessel analysis and clinically reliable structural quantification. Our source code is available at https://github.com/MaoFuyou/MorVess.
Authors: Chirui Chang, Xiaoyang Lyu, Yi-Hua Huang, Haoru Tan, Shizhen Zhao, Yikang Ding, Jianmin Bao, Xin Tao, Pengfei Wan, Xiaojuan Qi
Abstract: Object-level geometric edits, including translating, rotating, scaling, duplicating, or removing an object, are routine operations in digital content creation (DCC) workflows, yet they remain unreliable in generative video editing. The key challenge lies in specifying the target object's 3D state change unambiguously across viewpoint and time, while consistently updating geometry-dependent secondary effects such as shadows and reflections. We introduce GIVE, a geometry-instructed video editing framework that represents edits through a unified object-state formulation. Two video-aligned geometry streams describe the target object before and after editing: a depth-box encoding coarse 3D placement and extent, and an orientation-box providing an appearance-agnostic orientation cue. Together, these streams provide a compact pre/post geometric specification for object-state transitions. To provide paired supervision for learning these edits, we build a scalable graphics-engine pipeline that executes object-level edit programs and renders controlled before/after pairs, isolating the intended geometric edit while keeping secondary effects consistent with the transformation. Experimental results demonstrate that GIVE produces faithful geometric edits with temporal coherence and consistent secondary effects across operators in a unified framework, and shows promising transfer to in-the-wild videos. Project page: https://geometry-instructed-video-editing.github.io/give/
URLs: https://geometry-instructed-video-editing.github.io/give/
Authors: Kim Youwang, Zhengyu Yang, Liuhao Ge, Yu Rong, Timur Bagautdinov, Su Zhaoen, Nir Sopher, Jovan Popovi\'c, Teng Deng, Tae-Hyun Oh, Chen Cao
Abstract: We introduce FiCA, a Feed-forward, instant Gaussian Codec Avatar generation pipeline that creates lifelike avatars from a single portrait image. Generating a photorealistic and drivable avatar from just a single image is significantly challenging due to the limited visual information available to accurately infer the 3D appearance and geometry of human heads. To address this, we develop a novel system that combines human-centric vision foundation models with a diffusion model. This system is designed to fully exploit partial visual observations to generate lifelike human avatars. Our proposed diffusion model learns a generative mapping from these partial observations to complete and authentic 3D mesh reconstruction. Additionally, we introduce a feed-forward mesh refinement network that enhances the fidelity and identity preservation of the generated avatars, eliminating the need for person-specific test-time optimization. By leveraging a universal prior model that decodes a generated mesh into a set of 3D Gaussians, we generate a photorealistic 3D Gaussian avatar, capable of being driven with novel expressions in real-time. Our experiments demonstrate that the avatars generated by our feed-forward approach faithfully represent diverse identities and surpass the visual quality of avatars produced by recent competing methods.
Authors: Xiuwei Chen, Wentao Hu, Yongxin Wang, Zisheng Chen, Likui Zhang, Kun Xiang, Jianhua Han, Hui-Ling Zhen, Jingyuan Zou, Hang Xu, Xiaodan Liang
Abstract: The integration of visual evidence has significantly enhanced the capabilities of large multimodal models. However, this integration predominantly relies on generating discrete outputs (etc., code or box coordinates) to invoke external tools, a process that introduces rigid dependencies and substantial latency. To overcome these limitations, we propose {EVA} (LatEnt Visual StAtes), a novel framework that natively generates continuous latent visual representations. These internal representations manifest as an adaptive sequence of Latent\_slot tokens, serving as intermediate visual thoughts during the reasoning process. These Latent\_slot tokens are then trained end-to-end with the discrete text tokens. This co-optimization, notably, causes extreme policy deviation in the 'transition window' following the Latent\_slot tokens. We develop D-GSPO (Decouple-GSPO) to target this root cause by decoupling the optimization of latent and discrete components. To support SFT, we construct EVA-230K, a high-quality text-image interleaved CoT dataset encompassing a diverse range of real-world scenes, documents, charts and OCR tasks. Extensive experiments across multiple benchmarks confirm that EVA achieves significant performance gains while enhancing inference efficiency.
Authors: Zexi Chena, Zitai Huang, Qiwen Gu, Zhiqi Li, Shengli Dong, Chenlei Wang, Junqiao Zhao, Hongdong Wang, Bing Han
Abstract: Autonomous robotic inspection in maritime environments presents unique challenges for Visual Place Recognition (VPR) due to cross-scene perceptual shifts. Robots navigating ship-borne environments must transition between visually distinct domains: open decks with sparse textures and severe illumination changes, and enclosed cabins with repetitive structures and high visual ambiguity. Existing VPR methods, designed primarily for urban or indoor scenes, fail to generalize reliably across these starkly different scenarios. To address this, we propose ProteusVPR, a two-stage retrieval-refinement framework. The first stage employs any standard VPR model for initial image retrieval. The second stage introduces a geometric-visual estimation network that fuses the retrieved image with two temporally preceding frames, incorporating geometric descriptors, a local affine coordinate system, and camera azimuth encoding to achieve precise localization. To support this task, we introduce the XHZ dataset, an 8K-panoramic ship-borne dataset collected from an operational vessel, featuring multi-floor cabin structures, deck transition zones, and strict query-database separation for rigorous evaluation. Extensive experiments on the XHZ dataset demonstrate that ProteusVPR consistently improves the localization accuracy across multiple VPR backbones, reducing mean localization error by over 60\% on average and that ProteusVPR offers an effective and robust solution for precise visual localization in challenging, cross-scene maritime environments.
Authors: Wei Bao, Siqi Li, Shouan Pan, Yi Xie, Yue Gao
Abstract: Event-based object Detection (EvDet), as a biologically inspired visual perception paradigm, demonstrates superior performance in scenarios demanding high temporal resolution and a wide dynamic range. Nevertheless, the inherent sparse representations and inadequate visual semantics of event data result in a considerable performance disparity between EvDet and frame-based object detection. Previous works attempt to alleviate this cross-modal discrepancy through knowledge distillation, yet they only focus on spatial visual semantics or pair-wise relational information, thus limiting performance in more complex scenarios. To address this challenge, this paper proposes M^2C-EvDet, a Multi-domain and Multi-order Cross-modal knowledge distillation framework for EvDet. Built upon frequency learning and hypergraph computation, M^2C-EvDet integrates two specialized modules: Adaptive Frequency-Decoupled Feature Distillation (AF^2D^2) and Multi-Order Relational Distillation (MORD).
Authors: Qiman Wu, Hanlin Chen, Lyujie Chen, Rui Xin, Jianlei Zheng, Mingyuan Wang, Jiahui Hu, Da Zhu, Yuecheng Ma, Yuhua Wei, Yizhao Wang, Hua Zhou, Yuheng Zhang, Anhua Liu, Shaman Tang, Yue He, Pengfei Diao, Shuang Su, Haotong Xin, Weichao Huang, Hang Zhang, Xianming Liu
Abstract: Modern VLMs and VLA systems commonly adopt off-the-shelf ViTs such as SigLIP2 as visual encoders, but diverse downstream requirements in latency, temporal modeling, and VLM integration often call for customized SOTA-level ViTs. Training such encoders remains beyond the reach of much of the community, as it requires massive image-text data, while standard softmax attention makes high-resolution or dynamic-resolution pretraining prohibitively costly and often forces low-resolution pretraining followed by post-hoc adaptation. TuringViT addresses these challenges with three key designs: Turing Linear Attention (TLA) for efficient sequence modeling, VISTA-Curation to construct supervision-rich image-video training data, and native dynamic-resolution pretraining that supports flexible inputs from the start and transfers seamlessly to downstream VLMs. As a result, TuringViT outperforms leading open-source ViT baselines with only 10% of the data, achieves stronger downstream VLM performance, and delivers substantially better latency scaling on high-resolution inputs. Our scaling-law analysis further shows that TuringViT continues to improve predictably with curated data scale, far from saturation. Its fast adaptation, hardware-friendly design, and efficient deployment have made it a unified visual foundation across XPeng's AI systems. More broadly, TuringViT provides a reproducible pipeline that dramatically lowers the cost for the community to train, customize, and deploy SOTA-level ViTs, moving toward making such Vision Transformers accessible to all.
Authors: Zhongju Wang, Beier Wang, Yatao Bian, Pichao Wang, Zhi Wang, Daoyi Dong, Hongdong Li, Huadong Mo, Zhenhong Sun
Abstract: Although text-to-motion generation has achieved strong progress in synthesizing realistic single-person motions from language, extending it to text-driven 3D human-human interaction (HHI) remains non-trivial, as HHI requires modeling the underlying \textbf{social structure} that governs phase progression, actor roles, and inter-actor coordination. In this paper, we formulate HHI generation as a social structure modeling and grounding problem: the model must first infer how an interaction unfolds and how the two actors coordinate their roles, and then realize this structure as continuous, physically plausible, and partner-aware 3D motion. To study how such structure should be modeled, we first examine the capability boundary of large language models (LLMs) for HHI generation. Our analysis shows that LLMs can \textit{think} by recovering phase decompositions and partner-aware roles, but cannot directly \textit{move}, as they fail to generate dynamic, physically plausible, and interaction-aware motion. This motivates our planner-executor paradigm, \textbf{Think with LLM, Move with Motion Skill}. The LLM planner converts implicit interaction semantics into motion-aligned social supervision by decomposing interactions into phases, assigning partner-aware actor roles, and aligning them with motion sequence. The motion executor then grounds the planned social structure into coordinated two-person motion by adapting a pretrained solo motion model with LoRA, previous-phase self-conditioning, and ego-relative partner conditioning. Together, our Solo-to-Social framework bridges social organization and motion realization, producing 3D HHI with improved phase consistency, role alignment, and partner-aware coordination.
Authors: Bingxuan Li, Yining Hong, Cheng Qian, Hyeonjeong Ha, Jiateng Liu, Zhenhailong Wang, Yue Guo, Yunzhu Li, Heng Ji
Abstract: Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a broad spectrum of rare and irregular interactions remains underrepresented. Although recent visual world models, including image and video generation models, achieve impressive realism on existing benchmarks, they primarily focus on simulating common physical interactions. This raises a central question: Do current visual world models internalize and generalize physical principles? In this work, we introduce Tailor-Bench, a benchmark that challenges world models to simulate irregular physical interactions. To enable systematic evaluation, we design three scenario modes that progressively challenge model reasoning: Regular scenarios reflect common tool-task pairs, Unconventional scenarios replace conventional tools with attribute-compatible substitutes to test affordance generalization, and Impossible scenarios introduce attribute-violating tools to probe constraint awareness. Additionally, we design two complementary settings under a unified evaluation protocol: predictive generation requires inferring outcomes without guidance, while descriptive generation specifies the target outcome for faithful realization. Our experimental results reveal a clear long-tail gap in physical world modeling: performance degrades from Regular to Unconventional and Impossible scenarios, indicating limited generalization beyond common interactions. Failure analysis further shows that models rely on superficial visual patterns: image models fail to realize correct state changes, while video models further suffer from temporal inconsistencies.
Authors: Hongli Xiao, Youjian Zhang, Yaohui Jin, Xiaoguang Ren, Wenjing Yang, Long Lan
Abstract: High-quality 3D vehicle assets are essential for autonomous driving simulation. Although multi-view diffusion-based paradigms enable controllable single-image reconstruction, they typically produce limited viewpoints and exhibit cross-view geometric inconsistencies, thereby reducing reconstruction fidelity in real-world scenarios. In this work, we introduce 3DCarGen, a scalable single-view 3D car generation framework designed for real-world images by synthesizing an arbitrary number of 3D-consistent multi-view images. Specifically, given a single image as input, we first synthesize a set of images from fixed viewpoints. These images are then fed into a feed-forward reconstruction model, resulting in a coarse 3D representation based on 3D Gaussian Splatting. Conditioned on this explicit 3D prior, our multi-view diffusion model generates 3D-consistent images from arbitrary camera viewpoints. We further extend a fast mesh reconstruction algorithm by incorporating color-normal joint optimization to recover detailed and coherent 3D vehicle models from the synthesized dense views. Extensive experiments on synthetic and real-world datasets demonstrate that our approach achieves robust geometric consistency and reconstruction fidelity compared to existing methods. Code and models will be released.
Authors: Cl\'ement Dauvilliers (Inria), Claire Monteleoni (Inria)
Abstract: Microwave satellite imagery plays a crucial role in monitoring tropical cyclone precipitation and intensity worldwide, but suffers from long revisit times, potentially missing rapid storm evolution phases. While this raises the need for an interpolation method, it is made challenging by the high level of heterogeneity of microwave data coming from different instruments. In this work, we introduce the first generative model that can be applied to multiple geospatial sources that change across samples, occur at irregular time intervals, are misaligned geographically, and come from instruments with varying characteristics. We apply this model to the case of spatio-temporal interpolation of tropical cyclone microwave images from other microwave and infrared instruments. We train using a self-supervised task in which a random source is masked and reconstructed, and show that it leads to a significant decrease in Continuous Ranked Probability Score over supervised training. We show a further improvement by combining infrared and microwave data compared to microwave only. Using these improvements, the generative model produces an ensemble mean on par with that of a deterministic model, while generating a power spectrum significantly closer to that of true observations. To the best of our knowledge, this is the first generative model that interpolates microwave images of cyclones by combining multiple microwave instruments and infrared observations at irregular time intervals.
Authors: Yinuo Zhang, Guangshun Wei, Yuanfeng Zhou, Yiran Shen
Abstract: High frame-rate RGB-D videos are crucial for a variety of downstream tasks, including motion analysis, dynamic scene understanding, and 3D reconstruction. However, due to hardware and sensing constraints, practical RGB-D cameras are typically limited to low frame rates, making it difficult to capture rapid scene dynamics. Existing video interpolation methods have achieved strong performance on RGB data, but they are not readily applicable to RGB-D scenarios, where they often yield blurry boundaries, visible artifacts, and degraded geometric consistency. Furthermore, motion estimation from only two boundary frames is inherently under-constrained in complex dynamic scenes. Event cameras, by contrast, provide asynchronous measurements with ultra-high temporal resolution, offering dense motion cues. In this paper, we propose a unified multimodal framework for RGB-D video interpolation that jointly exploits RGB appearance, depth geometry, and event-based temporal cues. Specifically, it first extracts and fuses RGB, depth and event cues, then estimates bidirectional flow with motion basis refinement for RGB and Z-axial refinement for depth, and finally synthesizes the target RGB-D frame via bidirectional warping and soft blending. In addition, we construct a new RGB-D-Event dataset to alleviate the scarcity of tri-modal training data. Extensive experiments on a public benchmark and the proposed dataset demonstrate that our method achieves superior photometric fidelity for RGB interpolation and stronger geometric accuracy for depth interpolation than existing approaches.
Authors: Yajing Wang, Chao Bi, Junshu Sun, Shufan Shen, Zhaobo Qi, Shuhui Wang, Qingming Huang
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive vision-language understanding, yet still struggle with fine-grained perception in high-resolution images. While existing training-free methods typically rely on attention-based localization or coarse-to-fine search, they are often misled by distractors and fail to locate multiple targets. Our investigation attributes these failures to Contextual Dominance, where salient distractors overwhelm target attention and cause inaccurate localization, and Semantic Bias, where global semantics cause the model to fixate on the most salient concept, resulting in incomplete localization in multi-object scenarios. Built on these insights, we propose ActiveScope, a training-free framework that enhances MLLMs by actively seeking and correcting perception. ActiveScope features two modules. The Semantic Anchor Localization (SAL) utilizes fine-grained semantic anchors to independently localize key targets, thereby mitigating semantic bias. The Interference-Suppressed Refinement (ISR) refines localization by suppressing attention on salient distractions to overcome contextual dominance. Extensive experiments on high-resolution image understanding benchmarks demonstrate that ActiveScope outperforms existing training-free methods (e.g., 96.34 percent accuracy on $V^{*}$ Bench), validating the superiority of the active search and self-correction paradigm. Our code is available at https://github.com/jasmine-ww/ActiveScope.
Authors: Sujun Sun, Mingwu Ren, Haofeng Zhang
Abstract: Cross-domain Few-shot Segmentation (CD-FSS) aims to learn generalizable segmentation capability from abundant annotated samples in the source domain, enabling accurate segmentation of novel classes in the target domain with only a few annotated samples. Existing CD-FSS methods mainly focus on mitigating feature distribution shifts caused by style gaps while ignoring significant differences in class semantic granularity and discriminative attributes across domains, leading to two key degradations in support-query matching: semantic over-alignment and attribute over-alignment. To this end, we propose the Dual Hierarchical Aggregation Network (DHANet), which comprises three key modules. First, the Hierarchical Spatial Aggregation (HSA) module performs multi-scale region aggregation of pixel features along the spatial dimension, generating hierarchical semantic-enhanced features to alleviate semantic over-alignment. Additionally, the HCA module conducts multi-scale attribute aggregation along the channel dimension, generating hierarchical attribute-enhanced features to mitigate attribute over-alignment. Finally, we propose the Online Probabilistic Semantic Bank (OPSB), which progressively constructs and updates class probability distributions from query predictions during inference, and samples multiple pseudo-prototypes as additional support information to mitigate insufficient support. Extensive experiments on four target-domain datasets demonstrate that our method achieves state-of-the-art performance.
Authors: Sujun Sun, Mingwu Ren, Haofeng Zhang
Abstract: Cross-domain Few-shot Segmentation (CD-FSS) aims to transfer knowledge learned from source domain to distinct target domains, segmenting unseen target classes with only a few annotated samples. Although existing methods have made significant progress, they still rely on training or fine-tuning processes, which incur high computational costs and risk overfitting. We observe that when powerful and general-purpose vision foundation models are incorporated into these methods, their performance shows only marginal improvement or even degrades due to overfitting. To address this, we eliminate trainable parameters and propose a training-free framework to avoid both training overhead and overfitting. Built upon the self-supervised vision encoder DINOv3, our framework addresses cross-domain challenges through three core modules. First, the Semantic-aware Feature Re-fusion (SAFR) module identifies and re-fuses features that emphasize semantic patterns, generating representations with enhanced semantic discriminability. Additionally, the Adaptive Support Enhancement (ASE) module narrows semantic gaps between support and query through robust query information aggregation. Finally, the Hybrid Prototype Matching (HPM) module integrates matching results from diverse prototypes to adapt to varying semantic complexity across domains. Extensive experiments on four target domain datasets demonstrate that our method achieves state-of-the-art performance in CD-FSS without any training.
Authors: Hongli Xiao, Youjian Zhang, Yucai Bai, Chaoyue Wang, Yaohui Jin, Xiaoguang Ren, Wenjing Yang, Long Lan
Abstract: Recovering realistic 3D vehicle models from autonomous driving scenes is crucial for synthesizing training data and building simulation environment. However, most existing vehicle generation methods fail to fully exploit multimodal sensors i.e. multi-view images and LiDAR point clouds) and rely on neural rendering based reconstruction, leading to low-quality mesh. Recently, native 3D generative models have made significant progress, yet they are not built for arbitrary multi-view inputs and often struggle with in-the-wild driving images. In this work, we present MM-TRELLIS, a multi-modal version of TRELLIS for in-the-wild 3D vehicle generation that integrates LiDAR and image sensors from autonomous driving datasets into native 3D generative models. Specifically, multi-view images are cycled as conditioning inputs, while LiDAR point clouds provide test-time guidance to ensure geometric accuracy and cross-view consistency. During denoising, we first align the guidance point cloud with the model priors, then enforce consistency between the generated geometry and the guidance point cloud. Finally, we introduce a voxel filtering strategy based on the opacity of 3D Gaussian Splatting to suppress floaters and produce clean meshes. Comprehensive experiments on Waymo dataset demonstrate our method outperforms existing methods in high-fidelity 3D vehicle generation. Code is available at https://github.com/HongliXiao/MM-TRELLIS.
Authors: Sachin Sharma, Michele Flammini, Federico Simonetta
Abstract: Fine-tuning transformer-based handwritten text recognition (HTR) models on medieval manuscripts is challenging because these models are pre-trained on modern text and must adapt to a very different visual domain. This paper studies how three controllable fine-tuning choices (contrast normalization, data augmentation, and layer freezing) affect recognition accuracy when adapting TrOCR to small historical datasets. We run controlled experiments on a 13th-century Italian manuscript (I-CT 91 "Cortonese") and replicate the same experimental grid on the public READ-16 benchmark as robustness evidence. On Cortonese, our best configuration achieves 8.03% character error rate (CER). Statistical comparisons across 13 configurations show that freezing up to three encoder layers or six decoder layers does not significantly harm accuracy, while deeper freezing becomes progressively detrimental. Removing contrast normalization (CLAHE) yields 7.84% CER, comparable to a domain-specialized baseline, suggesting strong optimization can reduce reliance on image preprocessing. Cross-dataset validation on READ-16 shows that decoder freezing thresholds transfer more robustly than encoder thresholds, and combined freezing strategies require dataset-specific re-validation. Finally, we use Grad-CAM gradient attributions and decoder cross-attention maps to diagnose error patterns and failure modes revealed by the ablations. Source code is available at https://github.com/LaudareProject/TrOCR-analysis
Authors: Yinji Ge, Guixu Zheng, Wulong Guo, Qian Feng, Xu Wu, Kai Zhou, Xinyuan Liu, Fei Xing
Abstract: Vision Foundation Models (VFMs) have significantly advanced dense feature matching, yet severe in-plane rotation remains a critical challenge. Existing solutions face a fundamental dilemma: data-driven methods require inefficient parameter scaling to implicitly learn rotations, whereas strictly equivariant networks lack the semantic capacity of modern VFMs. Consequently, current frameworks typically freeze VFMs and shift the entire burden of rotation generalization to the downstream decoder. To break this architectural bottleneck, we propose REDI-Match, an efficient framework driven by a novel Rotation-Equivariant Distillation (REDI) paradigm. Instead of relying on rotation data augmentation to establish rotational correspondences, REDI distills the non-equivariant semantic representations of a VFM into a lightweight, strictly rotation-equivariant encoder, leveraging an equivariant geometric architecture to constrain robust high-dimensional semantics. To fully exploit these features, we equip the decoder with an entropy-driven spatial alignment module. By evaluating discrete rotation hypotheses, this mechanism explicitly locks onto the canonical coordinate system, eliminating global ambiguity before continuous refinement. Extensive experiments demonstrate that REDI-Match establishes a new state-of-the-art (SOTA) across multiple benchmarks. Notably, it achieves a 13.89% absolute pose accuracy improvement on the highly challenging SatAst dataset while operating 1.9x faster than the current SOTA (RoMa v2), enabling real-time inference (~41 FPS) on a single RTX 4090 GPU. Code: https://github.com/YinjiGe/REDI-Match.
Authors: Jiahao Lyu, Pei Fu, Zhenhang Li, Shaojie Zhang, Jiahui Yang, Yu Zhou, Can Ma, Zhenbo Luo, Jian Luan
Abstract: In-Image Machine Translation (IIMT) aims to translate scene text in an image and render the translated text back into the original regions while preserving the overall visual appearance. Recent unified multimodal models provide a promising solution by combining visual-text understanding and image generation within a single framework. However, directly adapting such models to IIMT remains challenging. In particular, they often suffer from understanding-generation conflicts, where the translation inferred during understanding is inconsistent with the text supervision used in generation, and spatial position misalignment, where the rendered text does not accurately match the target text regions. To address these issues, we present UniTranslator, a unified multimodal framework for IIMT that tightly couples translation understanding and text editing. Specifically, we introduce an Understand-Generation Alignment Module (UGAM) to bridge the representation gap between understanding and generation, encouraging semantic consistency between translated content prediction and text rendering. We further propose a Spatial Mask Decoder (SMD) with pixel-level supervision over text regions to improve spatial grounding, geometric alignment, and layout controllability during generation. Extensive experiments on multiple benchmarks demonstrate that UniTranslator achieves state-of-the-art performance across diverse language directions and complex real-world layouts. Moreover, our results reveal a strong mutual reinforcement effect between translation understanding and image generation, highlighting the advantage of unified translation multimodal learning. Code is available at https://github.com/SeerRay-Lab/Unitranslator.
Authors: Boaz Meivar, Shaked Perek, Shani Shvartzman, Eli Schwartz, Shai Avidan
Abstract: Counterfactual analysis is widely used to study evidence use in vision-language models, but its diagnostic value is limited on well-posed tasks: when several cues independently support the same answer, removing one may not change the prediction. We propose monocular metric object-size estimation as an ill-posed diagnostic setting for evidence selection: because physical size cannot be determined from a single uncalibrated image, models must rely on imperfect cues category priors, target appearance, local context, apparent image size, and scene geometry. We assemble Metric VQA ($10{,}813$ dimension queries from Objectron and $331$ tape-measured in-the-wild scenes) and evaluate $12$ open-weight VLMs ($3$--$397$\,B parameters) with counterfactual analysis decomposing six visual and language evidence channels. Even the largest VLMs tested (Qwen3-VL-235B, Qwen3.5-397B, InternVL3.5-241B) trail a text-only frontier LLM on the in-the-wild split. The diagnostic analysis shows: target identity is the most load-bearing cue, target pixels and local context help only some models, apparent size shifts predictions without a directional readout, and global scene geometry is largely unused. We analyze LoRA fine-tuning as an actionable intervention specific to metric estimation: while the task is learnable, the models do not learn to leverage scene geometry.
Authors: Yang Zhou, Wenxue Li, Peng Zhang, Yifei Chen, Fei Wang, Daiguo Zhou
Abstract: Face Video Restoration (FVR) aims to recover high-fidelity facial videos from degraded input while preserving identity and semantic consistency across frames. Existing methods often struggle to simultaneously address three key challenges: identity shift, viewpoint-entangled guidance, and perceptual realism. To tackle these issues, we propose TIGER, a structured tri-prior fusion framework that Tames Identity, Geometry, and gEnerative pRiors for high-quality FVR. Specifically, an Identity Prior is first established by injecting subject-discriminative embeddings into the latent space, effectively anchoring the subject's identity against severe degradations. Then, to provide temporally consistent structural guidance for dynamic videos, TIGER constructs a Geometry Prior by lifting 2D reference cues into a disentangled 3D parameter space, creating a geometric anchor through cross-source parameter fusion. Moreover, to achieve maximum efficiency without compromising realism, we harness the video generation model's Generative Prior through a one-step rectified flow. We further design a progressive three-stage training optimization strategy that refines structural fidelity, textural reconstruction, and distribution-level realism to ensure robust optimization. We also construct a large-scale FVR dataset to facilitate robust training and standardized evaluation. Extensive experiments demonstrate that TIGER achieves state-of-the-art performance in both identity fidelity and temporal stability, delivering a high-quality, efficient and identity-consistent FVR. Project page: https://yzhoulv.github.io/Tiger/.
Authors: Hojun Choi, Seulbin Hwang, Dae Jung Kim, Kisung Kim, Hyunjung Shim, Jinhan Lee
Abstract: Bird's-eye view (BEV) perception fuses multi-camera images into a unified top-down representation for autonomous driving. Despite recent progress, state-of-the-art methods remain confined to closed-set scenarios, making them vulnerable to unpredictable real-world environments. In this work, we introduce open-vocabulary BEV segmentation (OVBS), which leverages vision-language models (VLMs) to recognize categories beyond the training set while maintaining precise BEV perception and real-time efficiency. A key challenge in OVBS lies in the 3D geometric inconsistency inherent in the ill-posed lifting of 2D VLM semantics into BEV. To address this, we propose OVBEVSeg, a geometry-aware OVBS framework that enhances efficient Gaussian splatting (GS)-based unprojection by leveraging robust 3D geometric constraints across three progressive stages: (1) 2D-to-BEV pseudo-labeling via reliable 3D projection for OV generalization; (2) joint 2D-BEV per-scene optimization with BEV structural constraints for 3D geometric consistency; and (3) 3D geometric distillation for online efficiency. On the nuScenes dataset, OVBEVSeg achieves state-of-the-art performance, outperforming closed-set methods by 15.3 mIoU on unseen categories. Remarkably, even with no novel-class ground-truth labels, it remains competitive with self- and semi-supervised baselines trained with up to 40% of ground-truth annotations. Furthermore, it achieves 2.5x faster inference with only 0.22x the memory consumption of projection-based methods. Project page: https://hchoi256.github.io/projects/ovbevseg/.
Authors: Zhewen He, Junyi Hu, Haomian Huang, Zhenhua Li, Yu-Shen Liu, Yi Fang
Abstract: Sign language models are typically trained on datasets captured under constrained conditions, with limited viewpoint, background, and signer-identity diversity, leading to poor robustness under real-world distribution shifts. We introduce SignNet-1M, a large-scale augmented dataset spanning ASL, CSL, and German Sign Language (DGS). SignNet-1M synthesizes realistic variations along three axes: (i) novel-view rendering (rotation and zoom) via 3D Gaussian Splatting (3DGS), (ii) scene/identity editing via diffusion models for background replacement and signer substitution while preserving sign motion and linguistic content, and (iii) post-rendering augmentations that emulate capture and compression artifacts (e.g., pose/temporal perturbations and video-level corruptions) to better match in-the-wild recordings. Beyond data release, we provide a unified benchmark suite across downstream tasks (e.g., translation and recognition) and ablations that isolate each augmentation component. Experiments across backbones show that training with SignNet-1M consistently improves generalization under cross-view, cross-background, cross-identity, and post-rendering shifts, while maintaining strong in-distribution performance. The dataset, full augmentation pipeline, and benchmark are available at https://signnet.chatsign.ai/.
Authors: Stefano Mereu, Oleksandr Kuznetsov, Gabriele Marchello, Alessandro Galdelli, Emanuele Frontoni, Adriano Mancini, Ferdinando Cannella
Abstract: Convolutional Kolmogorov--Arnold Networks (KANs) replace the fixed weights of a convolutional kernel with learnable univariate functions. The dominant formulation attaches one such function to every kernel entry and lets it act on pixel values, expressive but parameter-heavy and prone to overfitting. We argue that the learnable functions are better placed in the \emph{structure} of the convolution than on each edge, and we organise the design space along a single axis: whether the function acts on the pixel \emph{values} or on the filter \emph{shape}. We study three realisations. SV-KAN applies one shared univariate function to the values and leaves the spatial filter free and static, aa classical convolution with a single learnable shared activation. AG-KAN keeps the shared value function but supplies the spatial structure through a content-adaptive Gaussian gate. RF-KAN instead moves the learnable functions onto the filter shape, building each filter from oriented ridge profiles expanded in a localised oscillatory (Morlet) wavelet basis with content-adaptive amplitudes. Under a matched four-layer protocol with in-run references and three seeds, RF-KAN and SV-KAN reach $88.47\pm0.10\%$ and $88.20\pm0.31\%$ on CIFAR-10 and $64.40\pm0.19\%$ and $64.57\pm0.30\%$ on CIFAR-100, at about $0.4$M parameters. At this matched scale the shape model and the simplest value model meet at the top, both above a plain convolution and every per-edge KAN we tested, including the official Gram variant, at roughly a fifth of the parameters. A controlled study attributes the RF-KAN gain to an intrinsically localised oscillatory basis and to content adaptivity, and an ablation that removes the learned shape entirely, leaving only the shared value function, collapses accuracy by over forty points, identifying the learned shape as the load-bearing ingredient at this scale.
Authors: Mathis Kruse, Melissa Schween, Bodo Rosenhahn
Abstract: Detecting anomalies in industrial objects is an important topic for increasing production efficiency. More complex objects often require the analysis of several view points, which has led to the field of multi-view anomaly detection. We present MATCH, the first multi-view anomaly detection method based on Flow Matching (FM). With the ODE formulation of Flow Matching, we can estimate likelihoods and thereby derive an anomaly score to detect anomalies in multi-view image data at object, image, and pixel-level. The architectural flexibility of FM models allows us to efficiently transform features of different spatial sizes to the normal distribution. We evaluate thoroughly on the already established Real-IAD data set and are also the first to provide a comprehensive evaluation of popular anomaly detection methods for the MANTA-Tiny data set. MATCH achieves state-of-the-art performance in both anomaly detection and segmentation, all while running on consumer-level hardware. By omitting the costly divergence term needed for likelihood estimation, we ensure that MATCH is usable in real-time production scenarios. Lastly, several ablation studies are conducted to validate the methodological choices.
Authors: Lars Doorenbos, Duc Manh Vu, Serdar Ozsoy, Juergen Gall
Abstract: The incorporation of additional modalities into action recognition models increases their performance across a wide range of settings. However, how this additional information can contribute to making the models more robust remains underexplored, particularly for the case of multi-modal out-of-distribution (OOD) detection. While methods exist that regularize the multi-modal training process with OOD detection in mind, they still apply off-the-shelf OOD detectors designed for the uni-modal case during inference, discarding important information. Based on an interesting relationship we find between the multi-modal and uni-modal predictions, we propose to use this signal to build a post-hoc detector explicitly designed for the multi-modal scenario. We combine this new source of information with a feature-space score, which detects off-manifold samples in the multi-modal space, and normalize them by the multi-modal logits. In doing so, the proposed hybrid detector is compatible with existing training-time approaches and consistently improves performance. Experiments on a wide range of established datasets from the MultiOOD benchmark show that, on average, our approach outperforms the state of the art. Our results show the importance of explicitly considering the different modalities at inference time for multi-modal OOD detection.
Authors: Yijia Lei, Jinzhao Li, Yichi Zhang, Jiacheng Hua, Yin Li, Miao Liu
Abstract: We introduce EgoSAT, the first comprehensive benchmark for egocentric video reasoning in streaming settings, designed to evaluate the capabilities of modern vision-language models (VLMs). The benchmark targets streaming interaction understanding, where video frames arrive sequentially and models must continuously interpret evolving visual context. EgoSAT unifies several previously distinct tasks within a single streaming framework. In this formulation, queries about completed events correspond to retrospective reasoning, queries about ongoing activities require online understanding, and queries about future actions involve prospective anticipation. This unified setting requires models to reason about the past, present, and future while operating under the constraint that only previously observed frames are available. EgoSAT contains 1,997 unique videos spanning 165 hours of egocentric footage and around 4,800 high-quality question-answer pairs, carefully designed to probe reasoning across varying temporal contexts. Using this benchmark, we evaluate a diverse set of both open-weight and closed-weight VLMs, providing a systematic assessment of their ability for streaming interaction understanding. By distinguishing answerability and conducting diagnostics on confidence of models, we find existing models not only struggle with prospective and retrospective modeling, but also exhibit severe mis-calibration: confidence often fails to track inherent answerability, leading to dangerous "confidently wrong" behaviors. Project page: https://leiyj23.github.io/EgoSAT/
Authors: Christian Z\"ollner (Department of Applied Tumor Biology Institute of Pathology Heidelberg University Hospital), Mozzam Motiwala (Department of Applied Tumor Biology Institute of Pathology Heidelberg University Hospital), Aysel Ahadova (Department of Applied Tumor Biology Institute of Pathology Heidelberg University Hospital), Gerrit Anders (Leibniz Institut f\"ur Wissensmedien), Robert H\"uneburg (National Center for Hereditary Tumor Syndromes University Hospital Bonn, Department of Internal Medicine I University Hospital Bonn), Jacob Nattermann (National Center for Hereditary Tumor Syndromes University Hospital Bonn, Department of Internal Medicine I University Hospital Bonn), Matthias Kloor (Department of Applied Tumor Biology Institute of Pathology Heidelberg University Hospital)
Abstract: Training of neural networks for histopathology classification tasks typically relies on data encoding into latent space, which reduces complexity and improves performance. There are several encoder networks available, either pretrained on general image datasets such as ImageNET, or specifically on histopathological images. Training of encoder networks should be adapted to downstream tasks, allowing encoding of biologic/diagnostic content while rendering networks invariant to label-irrelevant transformations. This paper investigates the effect of classical image transformation on the latent space, using networks provided by Lunit Inc. and Bioptimus, both focusing on pathological images, and by Meta Research Team. We assess variance of embeddings resulting from standard data transformations by comparing original and transformed image embeddings and by contrasting them with random, unrelated embeddings, using image tiles from hematoxylin/eosin-stained sections available in a colorectal tissue dataset and the publicly accessible TCGA dataset. Our findings show that embeddings of original and transformed images are closer to each other than to random embeddings, indicating robustness to transformations. However, they are not fully invariant, revealing that the encoder networks do not completely neutralize transformation effects in latent space, explaining why transformation-mediated augmentation of datasets can improve performance. Significant differences were observed between general and histopathology-specific encoder networks.
Authors: Kamil Kwarciak, Marek Wodzinski
Abstract: Medical point cloud completion is important for anatomical reconstruction and downstream clinical workflows, yet generative modeling in this setting remains insufficiently studied. We investigate completion through continuous-time generative modeling and introduce PCFM, a PTv3-backed flow matching approach for medical point cloud completion. We evaluate on SkullFix and SkullBreak, and additionally on the more recent Mandibular Defect dataset. We build strong baselines by adapting PTv3 to a deterministic encoder-decoder completion model and by instantiating diffusion completion (PCDiff) with both PVCNN and PTv3 denoisers. PCFM with PTv3 is competitive with the deterministic PTv3 baseline and achieves state-of-the-art generative performance across datasets, while requiring substantially fewer sampling steps than diffusion. At the best operating points, PTv3 also yields clear throughput gains, providing up to a 7$\times$ speed-up for PCFM compared to a PVCNN backbone. Finally, we study empirical scaling trends by varying model size and point cardinality, showing consistent gains with higher point resolution and informative trade-offs across model scales.
Authors: Qingxiao Li, Zikai Wang, Qingli Wang, Nan Xu
Abstract: We present S1-Omni-Image, an open-weight unified multimodal model for scientific image understanding, generation, and editing. Unlike general-purpose image generation models, scientific image tasks require not only high-fidelity synthesis, but also robust understanding of scientific semantics, structural relations, domain knowledge, and task intent. To this end, S1-Omni-Image builds on the scientific multimodal reasoning backbone S1-VL-32B and couples its understanding capability with an image generation module under a unified think-before-generate paradigm. Given a user instruction, the model first produces a task-oriented reasoning trace, a textual answer, and a task special token; their hidden states are then injected into the generation module to condition image generation or editing. S1-Omni-Image supports scientific image understanding, generation, and editing in a unified framework. For generation, it focuses on scientific illustrations and text rendering, including logical diagrams, relational comparisons, data charts, and realistic scientific visualizations. For editing, it casts segmentation and other domain-specific vision tasks as native image editing problems, enabling multi-turn illustration editing, medical and geographic image segmentation, medical image translation, and scientific image super-resolution. We construct SciGenEdit, a 314K-sample training dataset, and release the model weights, inference code, and SciGenEdit-10K. Experiments show that S1-Omni-Image substantially improves scientific image generation and editing while preserving the scientific image understanding capability inherited from S1-VL-32B. It outperforms open-source models on GenExam and TechImage-Bench, achieves state-of-the-art results on four editing benchmarks including MSD, cigRockSEM, SynthRAD2025, and IXI, and maintains stable performance on scientific image understanding evaluations.
Authors: Le Xiang, Chenxi Zhai, Shu Wei, Jingjing Wu, Qunyi Xie, Xiao Tan, Kunbin Chen, Wei He
Abstract: Vision-Language Models (VLMs) have revolutionized document parsing by enabling end-to-end mapping from images to structured text, imposing a significant latency bottleneck, particularly for token-dense documents. While Multi-Token Prediction (MTP) has emerged as a promising approach for accelerating inference, its potential is constrained by optimization instability when scaling to deeper look-ahead depth. In this paper, we propose \textbf{P-MTP}, a framework that leverages \textbf{Progressive Multi-Token Prediction} with a lightweight MTP module to scale the look-ahead depth for high-throughput document parsing. Specifically, we introduce Progressive Curriculum Loss that adaptively re-weights different look-ahead depths using cumulative path reliability and retrospective target consistency. By effectively suppressing gradient noise in long-range predictions, P-MTP, facilitates an automated easy-to-hard optimization transition, enabling the model to master increasingly distant look-ahead depths. Furthermore, we propose Confidence-Gated Dynamic Drafting to maximize the effective look-ahead depth and acceptance rate by adaptively calibrating speculative length during inference, thereby minimizing computational waste and further pushing the boundaries of inference speedup. Experimental results across multiple benchmarks and architectures demonstrate that P-MTP, achieves up to a $5\times$ speedup with negligible loss in accuracy, providing the first successful validation of extensive look-ahead MTP in the document parsing domain.
Authors: Mohamad Alansari, Yonathan Michael, Hasan AlMarzouqi, Muzammal Naseer, Naoufel Werghi, Sajid Javed
Abstract: We revisit the memory update mechanism in SAM2-based visual object tracking and identify confidence-only mask selection as the dominant cause of drift under occlusion, rapid motion, and distractors. We introduce SENTRY, a training-free, plug-and-play, refine-before-write module that validates each memory update for short-horizon temporal consistency before committing it. SENTRY aggregates diverse segmentation hypotheses per frame, backtracks them into short tracklets, and uses neighbor-aware cycle-consistent matching against recent trajectories to favor temporally and geometrically consistent masks. It leaves the base architecture untouched, replacing confidence-driven writes with consistency-validated ones. For fair evaluation, we re-evaluate major open-source SAM2-based trackers across all available scales and datasets, filling gaps in prior reports. Integrated into five strong baselines, SENTRY delivers consistent gains across nine benchmarks, achieving new zero-shot SOTA on LaSOT, LaSOT_ext, GOT-10k, VOT20, VOT22, and DiDi. Despite these checks, the SAM2-L version runs at 32.8 FPS on an A100, and across compatible hosts adds only about 0.4--0.6 GB VRAM. Our results provide the first unified all-scale evaluation of SAM2-based trackers and show that enforcing temporal validity at write time stabilizes memory-augmented tracking without retraining. Project page: https://hamadya.github.io/SENTRY/page/
Authors: Junpeng Jing, Ronglai Zuo, Zhelun Shen, Shangchen Zhou, Rolandos Alexandros Potamias, Stefanos Zafeiriou, Krystian Mikolajczyk, Jiankang Deng
Abstract: Recent advances in stereo matching have achieved remarkable accuracy, but often rely on large models, heavy computation, or additional foundation-model priors, making them difficult to deploy on resource-constrained platforms. In contrast, efficient stereo models offer faster inference but are commonly considered less capable of strong zero-shot generalization. In this paper, we challenge this assumption by introducing Lite Any Stereo V2 (LAS2), an ultra-fast model series designed for efficient zero-shot stereo matching. LAS2 is developed from both architecture and training perspectives. Architecturally, we revisit efficient stereo design under practical deployment settings and propose a 2D-only cost aggregation framework, optimized for real inference latency rather than theoretical MACs alone. For training, we develop a three-stage strategy that combines synthetic supervision, self-distillation, and real-world knowledge distillation. To improve the reliability of real-world pseudo supervision, we further introduce pseudo-label filtering and an error-clamping operation, enabling smoother synthetic-to-real transfer. We instantiate LAS2 as a family of models, including feed-forward variants for different efficiency budgets and an iterative variant for higher accuracy. Extensive experiments show that LAS2 achieves state-of-the-art accuracy among efficient stereo methods while maintaining significantly lower latency. Specifically, LAS2-H achieves stronger overall zero-shot performance than the iterative method Fast-FoundationStereo, with 1.8x and 2.7x faster inference on H200 and Orin, respectively. The project page, demos, and code are available at https://tomtomtommi.github.io/LiteAnyStereoV2/.
Authors: Tianyu Zhu, Yingping Liang, Hesong Li, Ying Fu
Abstract: Text-driven Referring Video Object Segmentation (RVOS) aims to locate and segment target objects in videos given natural language. However, existing models are typically trained on 2D image or video datasets with naive segmentation losses, which overlooks the geometric consistency across frames and leads to weak spatial understanding. In this paper, we propose Geometry-enhanced Language-guided Video segmentation (GeoLaV), a two-stage framework that distills 3D geometric knowledge from images to enhance text-driven video segmentation. In the first stage, we perform monocular geometry pretraining with monocular novel-view synthesis, enabling the model to acquire geometry-consistent visual representations via spatial alignment on large-scale single-image datasets. In the second stage, we introduce geometry-aware distillation and fine-tune the model on video segmentation datasets, transferring 3D structural knowledge from a general 3D prior model. This process reinforces 3D awareness and improves both spatiotemporal coherence and language grounding in segmentation. Extensive experiments show that our method using only image segmentation data already provides notable zero-shot generalization in RVOS. When combined with geometry-aware distillation for fine-tuning on videos, our method achieves state-of-the-art performance across multiple RVOS benchmarks. The code is available at https://github.com/Tony1882880/GeoLaV.
Authors: Yixuan Li, Guangzhi Sun, Yudong Yang, Wei Li, Zejun MA, Chao Zhang
Abstract: Video large language models (LLMs) are often constrained by computation and memory budgets, leading them to use reduced frame rates and spatial resolutions, which may cause them to miss critical information for question answering (QA). A practical and efficient solution is a two-stage paradigm: first perform coarse video understanding to localize relevant segments, and then re-watch these segments at higher temporal or spatial fidelity. In this paper, we present video-SALMONN-R$^3$, the first end-to-end video-LLM that enables re-watch through reinforcement learning without relying on chain-of-thought (CoT) cold-start. This design removes the need for costly CoT data annotations and avoids CoT-based supervised fine-tuning (SFT), which can otherwise degrade the pretrained video understanding abilities. To address the mismatch between the reasoning-first behavior induced by re-watch and the answer-first tendency of pretrained video-LLMs, we propose a re-answer strategy, in which the model first produces a direct answer in the first watch and then refines it after re-watching. Finally, to improve question adherence during re-watching, we propose a re-ask mechanism that re-injects the query when revisiting localized segments. Experimental results show that video-SALMONN-R$^3$ consistently outperforms both the base model and the QA-SFT baseline, while surpassing prior re-watch-based approaches with significantly lower computational cost. Code, models, and data will be publicly released upon acceptance.
Authors: Peize Li, Fanhu Zeng, Tongda Xu, Xingguo Xu, Xinjie Zhang, Xingtong Ge, Haotian Zhang, Yan Wang
Abstract: In-camera JPEG previews are ubiquitous in raw image formats and provide an sRGB reference at negligible storage cost. Although existing metadata-based reconstruction frameworks can exploit this side information when recovering raw images, their context models often become computationally expensive especially at high resolution, eg, 4K raw image, given that attention mechanisms scale quadratically with feature maps, hindering its practical application. To address these limitations, we propose MambaRaw, a JPEG-conditioned metadata-based raw image reconstruction framework that uses State Space Models (SSMs) to estimate entropy parameters efficiently. Our key contribution comprises a Spatial-Energy Coupled Context Modeling mechanism with two lightweight modules: (1) TileMambaBlock, which performs Mamba-style selective scanning only on information-dense tiles to improve the efficiency; and (2) Energy-Aware Refinement (EAR), an identity-initialized residual module that enhance feature representation to match the long-tail energy distribution of raw signals. Extensive experiments on three camera datasets (Sony, Olympus, Samsung) show consistent improvements over strong metadata-based baselines and set a new state of the art for JPEG-guided raw reconstruction with great efficiency. Notably, at low metadata bitrates, MambaRaw increases PSNR by 1.2--1.4 dB and reduces end-to-end coding latency by about 9%. Code is released at https://github.com/Peizeli1/MambaRaw.
Authors: Xingsong Ye, Yongkun Du, Jiaxin Zhang, Haojie Zhang, Chong Sun, Chen Li, Jing Lyu, Zhineng Chen
Abstract: WordArt (artistic text) features highly customized fonts, textures, and layouts, making WordArt-oriented scene TExt Recognition (WATER) substantially more challenging than general Scene Text Recognition (STR). Existing STR datasets and methods, typically built around regular scene text and fixed-template inputs, struggle to scale to WATER. Thus, we aim to advance this task from both data and model perspectives. On the data side, we construct a 2M synthetic dataset, WATER-S, with the scale improved by hundreds of times compared to existing artistic text data. WATER-S consists of two complementary subsets. One rendered by an upgraded rendering pipeline (SynthWordArt), which provides highly accurate and controllable synthetic WordArt data. The other is generated by combining Qwen3-VL for prompt mining and Z-Image for image synthesis, which improves the coverage of realistic and diverse data. On the model side, we propose WATERec. It adopts an visual encoder supporting arbitrary-shaped inputs and an autoregressive decoder to model complex layouts, structurally breaking the bottleneck of fixed-template STR on WordArt. Experiments show that this architecture outperforms prior STR methods, achieving state-of-the-art performance on irregular texts such as WordArt. Together with WATER-R, carefully reorganized from existing real STR data, our strong baseline with the new synthetic data and model design reaches 90.40% accuracy on WordArt-Bench, surpassing both general-purpose and OCR-specialized vision-language models by a large margin. Code and data are available at https://github.com/YesianRohn/WATER.
Authors: Inam Ullah, Imran Razzak, Shoaib Jameel
Abstract: Learning causal models from fragmented biomedical data is challenging because clinical, molecular, and imaging variables are often incomplete or not jointly observed. We propose RetiSEM, a domain-constrained structural equation modelling (SEM) framework for causal graph recovery and mediation analysis under limited multimodal resources. This proposed work organises variables into biologically informed blocks, applies forbidden-edge constraints, and decomposes pathway-level effects into TE, NDE, and NIE components. We evaluate RetiSEM across ten synthetic benchmark scenarios that vary in dimensionality, nonlinearity, causal depth, and pathway structure, together with a fragmented real-world setting that combines NHANES clinical variables with externally derived retinal representations. This approach achieves lower structural error and higher causal accuracy than unconstrained baselines across the synthetic benchmarks. In the real-data analysis, retinal variables behave mainly as downstream biomarker-like indicators, with smaller but detectable indirect effects. These findings support our strategy as an interpretable framework for testing structured causal hypotheses in limited-resource biomedical AI. The code and resources for this work are publicly available at: https://github.com/Inamullah-Colab/ReitSEM.
Authors: Ling Li, Zhizhen Cai, Xinkun Wu, Ziyu Zhu, Jiaqing Lyu, Bowen Liu, Zhidong Deng
Abstract: Grounding deictic gestures in natural images is fundamental to AR and human-robot collaboration, providing a basis for seamless spatial interaction. While Transformer-based visual models have achieved significant progress in general object detection, their global attention mechanisms often neglect micro-geometric relationships, degrading orientation accuracy. In pointing tasks, this deficiency manifests as an inability to accurately capture the pointing ray implied by finger poses, which results in pointing drift and localization ambiguity when dealing with distant or densely packed objects. To address this, we propose VistaRef, a framework designed to explicitly enhance spatial orientation awareness. First, we develop the Local Hand Entity Modeling (LHEM) module, which incorporates hand-pose embeddings to strengthen the model's capability to capture subtle finger deviations. Second, drawing inspiration from multi-view geometry, we construct the Geometric Ray Modeling (GRM) module to transform implicit orientation information into explicit spatial geometric features, guiding feature aggregation and deep fusion via attention mechanisms. Furthermore, we introduce a novel Orientation-Consistent Alignment Loss (OCAL) to synergistically supervise hand presence and pointing consistency, ensuring that all architectural improvements collectively serve the core objective of spatial localization. Experimental results demonstrate that VistaRef significantly outperforms the baseline, achieving a 14-point absolute gain in grounding accuracy. Qualitative analysis further confirms that VistaRef effectively models the geometric correlation from hand to target, bridging the spatial perception gap inherent in traditional Transformers for complex scenarios. Code: https://github.com/lingli1724/VistaRef.
Authors: Anil Bayram Gogebakan, Filippo Marostica, Alessio Caviglia, Alessandro Savino, Stefano Di Carlo
Abstract: Existing automotive event datasets rely on appearance-based annotations from frame pipelines, making them poorly suited for motion-aware event perception. We present a geometry-driven, annotation-free framework that classifies detected objects as static or independently moving by exploiting ego-motion structure directly from the event stream. A Focus of Expansion model with yaw compensation estimates global background motion, while objects are labeled as moving when local motion deviates from this prediction, as quantified by a scale-invariant residual. Temporal stabilization improves robustness across consecutive event windows. The method requires no learning, no manual motion labels, and works with any input bounding boxes. Experiments on MVSEC and the Prophesee 1 Megapixel Automotive Detection dataset demonstrate consistent performance across diverse driving scenarios, with yaw compensation improving results during turns and a simple translational local model offering a favorable accuracy-efficiency trade-off.
Authors: Jian Xu, Delu Zeng, John Paisley, Qibin Zhao
Abstract: A growing family of training-free solvers -- FlowDPS, FLOWER, PnP-Flow and their diffusion ancestors (DPS, DAPS) -- repurpose a pretrained flow-matching prior to solve imaging inverse problems by adding a measurement-guidance term to the deterministic probability-flow ODE. Despite strong empirical results, what these per-step corrections actually approximate -- and how far the resulting samples are from the true posterior $p(x\mid y)$ -- has not been characterized. We give a posterior-transport account of flow-based inverse problem solving. Our starting point is a simple but consequential fact: for a \emph{deterministic} flow prior, Bayesian conditioning is realized entirely by a \emph{reweighting of the source distribution}, not by a drift correction; pushing the reweighted source through the \emph{unmodified} velocity field yields exact posterior samples. From this we show that trajectory-guidance solvers can be read as the minimum-kinetic-energy \emph{correction} field needed to morph the unconditional source into the posterior, and that FlowDPS / FLOWER / PnP-Flow correspond to distinct zeroth-order / Gaussian / proximal approximations of this single object; we bound the resulting posterior bias in Wasserstein distance. A controlled $2$D study with a closed-form posterior confirms the theory decisively: source reweighting matches the true posterior to the Monte-Carlo floor on every metric, whereas trajectory guidance incurs $200$--$800\times$ larger error and collapses posterior modes, \emph{regardless of guidance strength}. Guided by the analysis we propose a cheap, principled velocity-correction solver that is competitive across two in-domain priors (AFHQ, CelebA) and two out-of-distribution settings while, unlike point-estimate source-space optimizers, producing diverse posterior samples with uncertainty that correlates with reconstruction error.
Authors: Jiachen Qian
Abstract: GUI agents powered by vision-language models show strong potential for automating digital tasks, yet frequently fail in long-horizon scenarios due to the absence of step-level verification. Existing process reward models verify actions through textual reasoning alone, missing the visual nature of GUI state changes. We introduce VisCritic, a visual process reward framework that verifies agent actions by directly comparing pre-action and post-action screenshots in visual feature space. VisCritic employs a Siamese vision transformer to extract change-aware representations, coupled with an Action-Aware Critic Head that jointly evaluates action success, task progress, and error type. A critic-training data construction pipeline generates weakly supervised samples from existing trajectories without additional human labels for critic training. Experiments and offline analyses across five benchmarks demonstrate that VisCritic serves as a plug-and-play enhancement for diverse GUI agents, generally improving benchmark metrics while providing visual diagnostic cues.
Authors: Lei Xu, Haowei Wang, Shen Chen, Taiping Yao, Bin Li, Changsheng Chen
Abstract: Multi-modal Large Language Models (MLLMs) offer powerful reasoning for forensic tasks, yet existing approaches utilizing exogenous segmentation decoders often suffer from suboptimal localization. The reliance on stitched pipelines introduces information bottlenecks during backpropagation, which dilutes spatial signals and is limited by semantic priors of the segmentor. To address these limitations, we propose ForensicsTok, which reformulates image manipulation localization as an autoregressive sequence generation task. ForensicsTok directly generates spatially grounded token sequences, enabling precise mask prediction without intermediary supervision. Specifically, we introduce a Token Splatting Decoder (TSD) to map tokens to binary masks via codebook-aware code smoothing, which mitigates sharp gradients from deterministic detokenizers. Furthermore, to capture diverse tampering clues, we propose a Hierarchical Expert Fusion (HEF) module that injects multi-scale features from a forensic expert model. This unified architecture effectively compensates for the lack of forensic priors in standard MLLMs. Extensive experiments on six benchmarks show that ForensicsTok substantially improves over existing MLLM-based baselines and slightly improves over strong forensic expert baselines, while exhibiting stronger robustness to perturbations.
Authors: Ling Li, Bowen Liu, Zinuo Zhan, Jianhui Zhong, Ziyu Zhu, Bingcai Wei, Kenglun Chang, Zhidong Deng
Abstract: Pointing-based visual grounding requires models to precisely locate target objects by deciphering complex spatial relationships between the visual scene and pointing gestures. Traditional methods typically encode input images into static feature representations and perform reasoning primarily within the linguistic domain, often overlooking the rich perceptual cues and explicit spatial geometry inherent in images. In this study, we aim to mitigate the cognitive vulnerability of models in interpreting gestural spatial relations by proposing PointVG-R, a reasoning-guided Multi-modal Large Language Model (MLLM). PointVG-R introduces geometric-aware reasoning for pointing-based grounding, enabling the model to think with images through the strategic integration of Reinforcement Learning (RL) and cold-start data. Specifically, we design a novel geometric reasoning pipeline that simulates the iterative cognitive process humans employ when interpreting pointing gestures. Furthermore, we construct EgoPoint-CoT, a high-quality visual Chain-of-Thought (CoT) dataset featuring detailed reasoning trajectories to guide the model via Supervised Fine-Tuning (SFT) and RL. To address the varying quality of learning signals encountered during training, we further propose an Adaptive Importance Weighting strategy based on Group Variance, which dynamically adjusts reward signals to optimize the learning process. Experimental results demonstrate that PointVG-R achieves SOTA performance, outperforming the baseline by $\textbf{15.86}$ points in mIoU. Extensive ablation studies further validate the efficacy of our proposed modules. Code: https://github.com/lingli1724/PointVG-R.
Authors: Jiayi Lei, Yuandong Pu, Xingyu Han, Rongpeng Zhu, Jing Xu, Jinyao Wang, Zijian Zhou, Bin Fu, Yuewen Cao, Yihao Liu, Yongsheng Li
Abstract: Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it remains unclear whether their success reflects genuine causal understanding or sophisticated pattern matching over visual-textual correlations. Inspired by Russell's inductivist turkey, we introduce Counterfactual-World (CF-World), a counterfactual benchmark designed to investigate whether text-to-image models can generate images under rules that systematically contradict real-world priors. CF-World organizes each scenario into three progressive levels: factual generation under ordinary world knowledge, explicit counterfactual generation with direct visual instructions, and implicit counterfactual generation requiring causal deduction from altered rules. We evaluate both open-source and closed-source T2I models using a Vision Language Model (VLM)-based evaluator (CF-Eval). Furthermore, we introduce two metrics: Prior Resistance Rate (PRR), which measures a models' ability to overcome entrenched real-world priors, and Reasoning Retention Rate (RRR), which assesses whether models can maintain reasoning-dependent counterfactual generation without explicit visual cues. Experiments show that all models exhibit sharp degradation from factual to counterfactual settings. Further analyses suggest that these failures arise because current T2I models encode world knowledge and visual appearances as tightly coupled patterns. Consequently, their heavy reliance on frequent visual co-occurrences within the training data forces them to default to familiar commonsense priors when tasked with rendering counterfactual worlds.
Authors: Wuming Yang, Xiang Zhang, Hongmin Zhao
Abstract: Heterogeneous Knowledge Distillation (HKD) aims to transfer knowledge across varying architectures (e.g., from Transformer to CNN) but inherently suffers from severe training instability. We reveal that this instability stems from two highly coupled challenges: massive feature norm discrepancies that cause optimization drag, and severe gradient conflicts between the primary and distillation objectives arising from distinct inductive biases. To achieve stable distillation, we propose SPOFA, a framework built upon a novel Feature and Gradient Dual Stabilization mechanism. Specifically, at the feature level, we introduce a LayerNorm-based decoupling projector that explicitly decouples feature magnitude from direction, creating a bounded and stable space for semantic alignment. At the gradient level, we propose a momentum-driven Exponential Moving Average (MEMA) dynamic scaler. By establishing a robust historical baseline of the optimization trajectory, MEMA actively evaluates instantaneous gradient conflicts and adaptively penalizes harmful distillation signals, guaranteeing stable convergence. Importantly, SPOFA achieves this dual stabilization with an extremely lightweight parameter footprint. Extensive experiments on two mainstream benchmarks demonstrate that SPOFA achieves state-of-the-art accuracy, significantly outperforming computationally expensive methods while introducing only minimal computational overhead compared to standard baselines.
Authors: Ao Wang, Yikuang Yuluo, Yujie Liu, Shuangyang Zhong, Yuwen Zhang, Zihao Wang, Fenglin Liu, Andreas Maier, Haijun Yu, Yixing Huang
Abstract: Quadratic unconstrained binary optimization (QUBO)-based quantum computed tomography (CT) casts reconstruction as a binary quadratic problem for quantum annealing and hybrid quantum--classical solvers. For grayscale CT, however, image encoding is constrained by the binary-variable budget: fixed global bit-plane encodings increase QUBO size and coupling complexity as gray-level precision improves, whereas low-bit encodings introduce quantization error. We propose a QUBO-based grayscale CT reconstruction framework that combines dynamic interval encoding with prior-balanced optimization. Each refinement round encodes active pixels only within local gray-level intervals around the current estimate, and a boundary-hit-guided update rule adaptively switches between search expansion and local refinement. To improve optimization stability, the method balances projection-domain data consistency and an edge-preserving quadratic prior before forming the final QUBO. Sparse-view and limited-angle fan-beam CT experiments show that the proposed method recovers structures and gray-level distributions more faithfully than the evaluated analytic, iterative, variational, and representation-based baselines. Expressivity analysis and ablation studies further indicate that the improvement mainly arises from effective gray-level representation through dynamic local encoding and more stable data-fidelity--prior coupling. Experiments on the D-Wave hybrid binary quadratic model (BQM) solver further demonstrate that the formulation is executable on a hardware-backed hybrid quantum--classical backend.
Authors: Zhenyang Li, Lutao Jiang, Yizhou Zhao, Ying-Cong Chen, Xin Wang, Weikai Chen, Yifan Peng
Abstract: Reconstructing realistic, physically plausible garments from a single image remains a fundamental challenge. Template-free methods capture surface geometry but lack explicit sewing structure for simulation; while programmatic systems are simulation-ready but constrained by predefined templates. This reveals a fundamental representation gap between geometric reconstruction and structured garment construction. We present PatternGSL, a structured garment representation in the form of a template-free and learnable specification language that encodes complete sewing patterns, including panel boundaries, parameterized seams, and explicit stitch topology, in a compact and standardized form. PatternGSL preserves the physical rigor of pattern-based models while removing template dependence, elevating sewing structure as a first-class target for generative modeling. We further propose a vision-language framework that predicts PatternGSL specifications directly from a single image and decodes them into garments using lightweight deterministic validity handling, without optimization-based refinement or manual cleanup. In addition, we introduce PatternGSLData, the first large-scale image-to-GSL paired dataset comprising 300K samples with complete sewing pattern annotations, enabling supervised VLM training for structured garment reconstruction. Experiments demonstrate improved pattern accuracy over prior baselines, explicit sewing-structure recovery, reliable cloth simulation, and pattern-level editing through the same deterministic decoding pipeline. Code and data-processing scripts will be released at https://github.com/PatternGSL/PatternGSL.
Authors: Antoine De Paepe, Alexandre Bousse, Dimitris Visvikis
Abstract: Sparse-view computed tomography (SVCT) reduces radiation exposure and acquisition time, but the limited number of projection views makes the reconstruction problem severely ill-posed and leads to streak artifacts when analytical methods are used. Plug-and-Play (PnP) methods provide an effective way to combine data fidelity with learned image priors, while stochastic PnP methods further improve robustness by matching the denoiser input distribution through re-noising. However, these methods often require many iterations to converge, which limits their practical efficiency. In this work, we propose a multilevel (ML) stochastic PnP method for SVCT that accelerates stochastic PnP reconstruction. We highlight that, in the stochastic setting, directly enforcing prior coherence across levels would require accurately estimating fine-level prior gradients through multiple denoiser function evaluations, which substantially increases the computational cost. Motivated by this observation, we perform the multilevel steps in multiresolution analysis (MRA) approximation spaces. This choice is supported by the structure of the wavelet decomposition, which causes the prior-coherence correction to vanish in expectation, thereby avoiding costly estimation of fine-level stochastic prior gradients for the coarse-level corrections. Experiments on SVCT reconstruction show that our method, called Multilevel Stochastic Plug-and-Play (ML-SPnP), achieves reconstruction quality comparable to state-of-the-art methods while substantially reducing runtime.
Authors: Julien Khlaut, Charles Corbi\`ere, Baptiste Callard, Amaury Prat, Leo Butsanets, Antoine Saporta, Th\'eo Danielou, Leo Machado, Korentin Le Floch, Tom Boeken, Pierre Manceron, Corentin Dancette
Abstract: Vision-language contrastive pretraining has become the dominant recipe for 3D medical foundation models, leveraging the large volumes of paired scans and reports produced in clinical practice. However, medical images usually span dozens of organs, and radiological reports are much longer than typical natural image captions and are composed of multiple structured sections. CLIP-style pretraining compresses this structure by encoding each modality into a single global token, at the risk of losing important details. We introduce ConQuer (Concept Queries), an image-text pretraining method that augments CLIP's global alignment with a set of localized alignments, one per concept. ConQuer splits the report into concept-specific sections and learns cross-attention queries that pool the matching image features without using any segmentation mask or spatial supervision. Contrastive learning is then applied independently for each concept. Concepts can be any unit of semantic localization; here, they are anatomical regions, one query per organ or gross body region. As a byproduct, each query learns attention maps focused on its concept, providing built-in spatial interpretability. We use ConQuer to train Jolia, a 3D CT foundation model on chest and abdominal CT. Jolia consistently outperforms a CLIP baseline on findings classification, report generation, and cross-center transfer, and sets a new state of the art across multiple public benchmarks. Jolia's weights are available at https://huggingface.co/raidium/Jolia
Authors: Nahuel Gonzalez, Marta Robledo-Moreno, Ivan DeAndres-Tame, Ruben Vera-Rodriguez, Ruben Tolosana
Abstract: Deep learning approaches to biometric verification are commonly trained by optimizing indirect objectives, creating a misalignment between the optimization process and the primary evaluation metric, typically the Equal Error Rate (EER). This paper introduces EERLoss: a subdifferentiable, arbitrarily accurate approximation to EER for training deep biometric models. Furthermore, this framework has the potential to be adapted to optimize any specific operating point on the DET curve, enhancing its generalizability. To validate this approach, EERLoss is evaluated on a particularly demanding behavioral biometric modality: keystroke dynamics verification. This task is characterized by its high intra-class and low inter-class variability. Experiments are conducted on the large-scale KVC-onGoing benchmark, incorporating data from over 185,000 subjects across different scenarios. A comprehensive ablation study initially demonstrates the superiority of EERLoss in comparison to existing state-of-the-art loss functions. It also converges substantially faster compared to other losses, reducing the overall training cost. Additionally, a comparison is made between the proposed loss and the KVC-winning architecture by re-training it with EERLoss, demonstrating that the proposed approach significantly outperforms the original SoTA, achieving a relative EER reduction of up to approx. 30\%. This improvement on a challenging, large-scale benchmark validates the effectiveness of EERLoss as a task-aligned training objective specifically suited for high-variance biometric traits.
Authors: Zhentao Guo, Chen Duan, Tongkun Guan, Zining Wang, Kai Zhou, Pengfei Yan
Abstract: Despite remarkable progress in multimodal understanding, current MLLMs still exhibit limitations in video text understanding, particularly when semantics emerge through the integration of temporally distributed textual cues across multiple frames. This perception challenge fundamentally differs from static image text understanding, yet existing datasets fail to capture: the vast majority of questions remain answerable from single frames, inadequately reflecting real-world video text comprehension demands. To address this, we present ViTexQA, a large-scale video-text QA dataset, and FrameThinker for robust multi-frame temporal reasoning. We build ViTexQA via a quality-controlled Chain-of-Thought (CoT) annotation pipeline boosted with temporal constraints; all its QA pairs demand cross-frame text fusion to solve, enforcing true temporal reliance. FrameThinker adopts two-stage training for explicit temporal modeling: CoT-Guided Supervised Fine-Tuning (SFT) generates frame-aware reasoning chains, followed by Temporally-grounded Reinforcement Learning (RL) optimized with multi-frame coherence rewards. Evaluations show our method outperforms SOTA baselines on ViTexQA, lifting ROUGE-L by 6.3%.
Authors: Wenxin Wang, Bo Zhang, Feng Chen, Zixuan Wang, Wen Li, Changsheng Li, Yinjie Lei
Abstract: Recent advancements have explored agentic zero-shot 3D understanding by reformulating it as video keyframe understanding with Multimodal Large Language Models (MLLMs). However, existing methods face an intrinsic bottleneck due to the finite observation perspectives inherent in videos and the implicit perception of 3D scenes. In this paper, we propose a collaborative multi-agent framework that assigns a Planning Agent to handle high-level viewpoint planning and supplement novel perspectives, and a Perception Agent to explicitly summarize the 3D scene into a structured holistic cognitive map. Specifically, Planning Agent first analyzes this cognitive map to determine query-relevant viewpoints and supplements missing critical perspectives to ensure comprehensive observation. Subsequently, Perception Agent documents object-level attributes from these views by assigning consistent instance identifiers across viewpoints, thereby integrating fragmented observations into the holistic cognitive map. In parallel, it provides feedback to filter out mismatched candidate objects and guide subsequent viewpoint planning. Through this closed-loop iterative process, two agents collaboratively figure out candidates until Perception Agent determines that sufficient information has been captured to complete the task. Extensive experiments demonstrate that our method achieves state-of-the-art performance on 6 benchmarks, with improvements of 11.1\% Acc@0.5 on ScanRefer, 14.6 BLEU-1 on 3D-assisted dialog, and 2.1 EM on SQA3D.
Authors: Jonas Klotz, Cassio F. Dantas, Pallavi Jain, Diego Marcos, Beg\"um Demir
Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence. We present a human-grounded evaluation framework that quantifies alignment between SAE latents and human-annotated concepts, without requiring user studies, and validate this matching through targeted attribute perturbations. To enable this intervention-style evaluation in vision, we construct synCUB and synCOCO, synthetic benchmarks of paired images that differ in exactly one attribute. We introduce Fully-Binary Matching Pursuit (FBMP), a coalition-based matching procedure that supports many-to-one mappings between SAE latents and annotated concepts, and consistently outperforms one-to-one baselines. For functional validation, we propose a Targeted Attribute Perturbation Alignment Score (TAPAScore), which tests whether matched concepts respond selectively and in the expected direction under targeted image-level attribute perturbations. Under sanity checks, our matching and TAPAScore are the only evaluated metrics that reliably distinguish trained SAEs from untrained ones. Across SAEs trained on CLIP and DINOv2 embeddings, we find that increased overcompleteness can reduce perturbation alignment, indicating a reduction in interpretability. Our evaluation framework suggests that moderate dictionary sizes provide the best trade-off, yielding the most interpretable SAEs. Code and datasets are available at https://github.com/JonasKlotz/sae-concept-eval.
Authors: Sheng Xia, Zhengqin Lai, Tianxiang Jiang, Kanghui Tian, Shoujun Zhou, Bin Li, Yi Wang
Abstract: Video MLLMs often struggle with fine-grained spatio-temporal reasoning, sometimes generating correct answers based on irrelevant frames or objects. Although outputting spatio-temporal evidence during reasoning is a promising direction, existing RL frameworks typically rely on geometry-only (IoU) rewards, which can be sensitive to boundary perturbations and overlook semantic alignment. To address this, we propose Semantic Evidence Reward (SER), which reformulates spatio-temporal evidence grounding as a constrained verification task. Instead of computing pixel-level overlap, SER uses a referee VLM as a local checker to evaluate model-generated evidence claims across two dimensions: relevance and localization quality, combined with a temporal penalty. This design reduces the reliance on dense box annotations and enables training directly on standard video QA data. On the V-STAR benchmark, SER achieves 49.6% mLGM, improving by 3.0 points over the strong evidence-grounded baseline Open-o3-Video, demonstrating its potential in enhancing both answer accuracy and evidence grounding.
Authors: Gargi Panda, Soumitra Kundu, Saumik Bhattacharya, Aurobinda Routray
Abstract: Light field (LF) image denoising is challenging due to the high-dimensional structure of LF data. While noise is independent across sub-aperture images, scene content exhibits strong cross-view correlations. We introduce VSANet, a view-aware sparse attention network for LF denoising. Specifically, we propose a view-aware sparse attention (VSA) block that represents the 4D LF feature map as a unified spatial-angular token space and performs cross-view aggregation via locality-sensitive hashing-based sparse attention. This enables global feature interactions with linear complexity, effectively exploiting LF correlations across views and spatial locations. In addition, we design a feature refinement (FR) block to emphasize informative features in spatial, angular, and epipolar subspaces. The VSA and FR blocks are integrated within a sequential attention refinement module, forming the core of VSANet. Experiments demonstrate VSANet outperforms stateof-the-art LF denoising methods.
Authors: Jiaxiang Liu, Tianxiang Hu, Juwei Guan, Yujie Wu, Yusong Wang, Yao Mu, Zuozhu Liu, Mingkun Xu
Abstract: Recent advances in vision-language models (VLMs) such as CLIP have demonstrated strong generalization across natural-image domains. However, adapting these models to biomedical imaging is non-trivial: full-model fine-tuning is computationally expensive, while medical data are often scarce and exhibit subtle, fine-grained inter-class differences, making parameter-efficient adaptation particularly critical. Visual Reprogramming (VR) offers a parameter-efficient alternative by injecting learnable perturbations into the input space, but existing VR approaches for VLMs mainly focus on positive class prompts and overlook confusing negatives, leading to miscalibrated predictions in fine-grained medical scenarios. We present BioMedVR, the first VR-based framework for biomedical imaging, enabling few-shot adaptation of pretrained VLMs through compact learnable VR modules. To mitigate class confusion, we introduce a Confusion Minimization Mechanism that leverages LLM-generated confusion-aware attributes together with a Confusion-Suppression Loss to explicitly reduce false-positive alignment. Moreover, the designed Mixture-of-Prompt Experts combines a positive expert for main-class discrimination and a negative expert for confusion suppression, balanced via adaptive gating. Extensive experiments on 18 datasets, including 11 biomedical datasets and 7 natural image benchmarks, demonstrate that BioMedVR achieves superior accuracy and generalization, effectively bridging VR and VLMs in biomedical domains.
Authors: Mohammed Yusuf Mujawar, Noorbakhsh Amiri Golilarz
Abstract: Few-shot image recognition requires models to adapt to new classes from a small labeled support set. Hebbian fast-weight memory can provide temporary associative information during an episode, but fixed memory behavior may not be appropriate for every few-shot task. In this work, we propose Adaptive Hebbian Routing for few-shot Vision Transformers. The method uses a lightweight MLP router to control the contribution of Hebbian memory, the strength of memory updates, and the retention of previous memory from support-set features. We study Adaptive Placement, Adaptive Plasticity, and Fully Adaptive Hebbian Routing. Experiments use ViT-Small, DeiT-Small, and Swin-Tiny under 5-way 1-shot evaluation on Omniglot, CIFAR-FS, and cross-domain transfer from CIFAR-FS to Omniglot. In the direct Swin comparison, fixed and adaptive Hebbian variants use the same memory location. Adaptive Plasticity improves the fixed Hebbian result from 96.74\% to 96.92\%, while Fully Adaptive Routing achieves the best result at 96.94\%. The fully adaptive Swin model also reduces inference time from 16.51 ms to 14.05 ms relative to fixed Hebbian Swin. On CIFAR-FS, adaptive variants improve performance across all three backbones, and the multi-shot evaluation shows that these gains remain useful as the number of support examples increases. These results show that adaptive plasticity and adaptive memory activation can improve few-shot Transformer representations beyond fixed Hebbian behavior.
Authors: Xiaowei Gao, Pengxiang Li, Yitai Cheng, Ruihan Xu, James Haworth, Stephen Law, Yun Ye
Abstract: Recent multimodal large language models (MLLMs) have shown strong potential for autonomous driving scene understanding, yet existing methods still face a fundamental trade-off between temporal reasoning and spatial precision. Models that rely on single-frame or low-resolution inputs often miss small, distant, or partially occluded hazards, while language-centric driving models frequently provide limited grounded evidence for their explanations. To address this gap, we propose UniDrive, a unified visual-language and grounding framework for interpretable risk understanding in autonomous driving. UniDrive combines a temporal reasoning branch that models scene dynamics from multi-frame visual input with a high-resolution perception branch that preserves fine-grained spatial details from the latest frame. The two branches are integrated through a gated cross-attention fusion module, enabling dynamic context to be aligned with precise spatial evidence. Based on the fused representation, UniDrive jointly generates natural-language risk descriptions and grounded bounding-box outputs for risk objects. Experiments on the DRAMA-Reasoning benchmark show that UniDrive outperforms representative image-based and video-based baselines in both captioning and risk-object grounding. In particular, UniDrive achieves the best overall performance on the validation split and demonstrates clear advantages in small-object localization, zero-shot generalization to NuScenes and BDD100K, and human-rated interpretability and trustworthiness. These results suggest that explicitly combining temporal semantics and high-resolution perception provides a stronger foundation for interpretable and safety-oriented autonomous driving systems. The code is available at https://github.com/pixeli99/unidrive-dev.
Authors: Zhaopeng Cui, Jiarui Hu, Jingbo Liu, Boming Zhao, Xiyue Guo, Boyin Feng, Haocheng Peng, Yujun Shen, Hujun Bao, Guofeng Zhang
Abstract: Indoor visual relocalization plays a critical role in emerging spatial and embodied AI applications. However, prior research was predominantly devoted to low-level vision schemes, struggling to perceive scene semantics and compositions, which limits both interpretability and applicability. In this paper, we explore the issue of how to organize rich object information in a scene, including semantics, layout, and geometry, into a structured map representation, thereby utilizing object units exclusively to drive the camera relocalization task. To this end, we propose OpenReLoc, a camera relocalization system designed to provide scene understanding and accurate pose estimation capabilities. Leveraging recent foundation models, we first introduce a multi-modal mechanism to integrate open-vocabulary semantic knowledge for effective 2D-3D object matching. Additionally, we design object-oriented reference frames as position priors, paired with a reference frame selection strategy based on the Distance-IoU (DIOU), enabling extension to scalable scenes. Moreover, to ensure stable and accurate pose optimization, we also propose a dual-path 2D Iterative Closest Pixel loss guided by object shape. Experimental results demonstrate that OpenReLoc achieves superior relocalization recall and accuracy across various datasets. Our source code will be released upon acceptance.
Authors: Zhihao Zhu, Hongyi Tang, Yi Yang, Ahmed Abbasi
Abstract: Vision-Language Large Models (VLLMs) trained on massive crawled corpora raise pressing copyright and data-provenance concerns. These concerns are particularly acute in healthcare, where patient medical images paired with clinical reports demand rigorous privacy safeguards. However, existing training data detection methods either fail in cross-modal scenarios or rely on superficial output signals with insufficient discriminative power. We introduce GradAudit, a gradient-based auditing framework that examines internal optimization dynamics rather than treating VLLMs as black boxes. Our approach builds on a key observation: model parameters converge to regions where gradients on training samples become stable and well-aligned, whereas gradients on non-training samples remain noisy and inconsistent. By analyzing these gradient signatures, GradAudit achieves strong separability and detects genuine image-text associations learned during training, not merely individual modality membership. Empirically, across both medical and general-domain datasets, GradAudit substantially outperforms state-of-the-art baselines in both pretraining and fine-tuning VLLMs. In a case study employing copyrighted content, we show that existing training data detection methods not only underestimate the extent of unauthorized data usage, but that this underestimation becomes more pronounced as models become more recent and more advanced.
Authors: Daniel Lengerer, Mathias Pechinger, Klaus Bogenberger, Carsten Markgraf
Abstract: High-resolution aerial imagery has recently emerged as a complementary modality for automated driving perception and has shown potential to improve birds-eye-view (BEV) scene understanding when fused with onboard sensors. Prior work demonstrated performance gains for online high-definition (HD) map construction through aerial-onboard fusion; however, conventional end-to-end fusion does not fully exploit the structural information contained in aerial representations. In this work, we introduce AerialFusionMapNet, a fusion-based mapping framework with a structured two-stage training strategy that explicitly enhances the contribution of aerial features within a unified pipeline. The proposed training scheme enables more effective integration of structural aerial priors. On the nuScenes geographic split, AerialFusionMapNet achieves up to 54.7 mAP, improving over prior aerial-onboard fusion baselines from 48.8 mAP by +5.9 absolute and +12.1% relative. The results suggest that structured training design, rather than increased architectural complexity, plays a more decisive role in unlocking the full potential of aerial imagery for online HD map construction. Code and trained models are available at https://github.com/DriverlessMobility/AerialFusionMapNet.
URLs: https://github.com/DriverlessMobility/AerialFusionMapNet.
Authors: Dimitri Gominski, Maurice Mugabowindekwe, Qiue Xu, Xiaowei Tong, Martin Brandt, Hieu Le, Rasmus Fensholt, Dimitris Samaras, Loic Landrieu
Abstract: Counting individual trees is a fundamental task for environmental monitoring, yet remains largely unexplored with satellite imagery. At these resolutions, isolated trees may still be identifiable, but crown boundaries become ambiguous in dense forests, making the notion of an individual tree inherently ill-defined. Moreover, large-scale manual annotations of individual trees are prohibitively expensive. While scalable supervision can be derived from airborne LiDAR, the resulting annotations are noisy and difficult to exploit effectively. We address these challenges by formulating tree counting as a spatial density matching problem supervised through Unbalanced Optimal Transport. This formulation naturally accommodates both precise localization of isolate trees and robust density estimation in dense forests. We further introduce a self-correction mechanism that leverages transport residuals to progressively refine noisy supervision during training. We evaluate our approach on TinyTrees, a new benchmark spanning three continents and three satellite sensors, comprising over 215 million tree annotations (including 773K manually verified instances) across 23,000 sq.km. Our method consistently outperforms detection-based, regression-based, and transport-based distribution-matching baselines, demonstrating the effectiveness of unbalanced transport and reliability-aware supervision for large-scale tree counting from satellite imagery. Code, data and models are available at https://github.com/dgominski/treematch.
Authors: Leshu Li, Jie Peng, Yang Zhao
Abstract: 3D Gaussian Splatting (3DGS) has garnered significant attention in Simultaneous Localization and Mapping (SLAM) due to its advances in capturing fine-grained geometry features and synthesizing novel views. For SLAM in large-scale scenes, such as autonomous driving, 3DGS-SLAM faces a critical limitation: memory consumption increases continuously over time as Gaussian points accumulate, leading to poor memory efficiency and limiting its applicability. In this work, we propose a rendering-area-aware pruning strategy that selectively removes Gaussians based on their contribution to the effective rendering area, rather than solely relying on Gaussian-level heuristics such as opacity or gradient magnitude. This perspective directly targets the sources of memory redundancy, effectively reducing the peak memory footprint of 3DGS-SLAM during runtime. Evaluations on the EuRoC and KITTI datasets demonstrate that our method consistently outperforms existing pruning approaches in large-scale outdoor scenes, achieving over 60% memory reduction and more than 2 times FPS improvement while preserving localization and mapping accuracy. These results highlight rendering-area-aware pruning as a promising direction for scaling 3DGS-SLAM to real-world autonomous driving scenarios. Our code is publicly available at https://github.com/UMN-ZhaoLab/Pocket-SLAM.git.
Authors: Linpeng Huang, Weixing Chen, Zexin Chen, Yang Liu, Liang Lin
Abstract: Recent advances in Video Large Language Models (Video-LLMs) have yielded promising performance on video question answering (VideoQA). Nevertheless, existing benchmarks are predominantly evaluated through answer correctness, while the grounding of predictions in relevant video evidence remains largely unexamined. This disconnect between answer generation and evidence understanding motivates the construction of the Evidence-Grounded Video Question Answering Benchmark (EG-VQA), an open-ended evaluation protocol in which each QA pair is explicitly annotated with supporting temporal evidence, thereby requiring joint reasoning and precise evidence localization. EG-VQA is comprised of 2,067 videos and 11,838 QA pairs with fine-grained evidence annotations. To evaluate predicted evidence, Evidence-Grounded F1 (EG-F1) is introduced as a unified metric in which temporal alignment and semantic consistency against ground-truth evidence are jointly measured. Experimental evaluation reveals that even strong proprietary models struggle to accurately ground their predictions, exposing a fundamental discrepancy between answer correctness and faithful evidence localization. To bridge this gap, EG-Reasoner, an evidence-grounded reasoning model trained with explicit supervision, is proposed. State-of-the-art performance is achieved among open-source models, with results competitive against proprietary systems, particularly pronounced gains are observed on reasoning-intensive tasks such as counterfactual questions. These findings demonstrate that scaling alone is insufficient for robust video understanding and that structured evidence supervision is essential for the development of more reliable and interpretable VideoQA systems.
Authors: Chenrui Fan, Paolo Favaro
Abstract: Generic text-to-video models can be used as rich open-world scene priors. Despite the high quality of today's generated videos, they do not directly yield reliable 3D assets: camera motion is difficult to control, view coverage is partial, and frames often contain inconsistencies across time. We introduce OrbitForge, an adapter built from frozen video priors and per-prompt Gaussian Splatting reconstruction optimization that converts a single text-generated video into a canonical closed-orbit 3D Gaussian Splatting scene. We use 3D reconstruction as an anchor to improve the 3D consistency of the generated video. We obtain a preliminary 3D reconstruction from a first generated video via Deformable Gaussian Splatting with a robust MedianGS proxy. We render views from a prescribed orbit to detect missing viewpoints. OrbitForge uses the text-to-video model to complete only the missing views, and reconstructs the completed orbit into a final Gaussian Splatting scene. This design requires no task-specific video or multiview fine-tuning, avoids per-prompt score-distillation optimization, and does not progressively generate views one step at a time. We further argue that this setting demands coverage-aware evaluation: local smoothness alone rewards methods that never attempt a full orbit. On a frozen 300-prompt T3Bench-derived audit, OrbitForge reconstruction attains a 359.0-degree measured median span, raises originally unsupported-bin Q10 ImageReward from 8.07 to 16.36 relative to MedianGS-only reconstruction, while remaining competitive with VideoMV on the coverage-quality.
Authors: Shiyi Mu, Zichong Gu, Zhiqi Ai, Yilin Gao, Shugong Xu
Abstract: Stereo-based 3D object detection still faces two critical safety challenges: real-time performance and open-set generalization. Existing stereo 3D methods typically achieve twice the accuracy of monocular methods but suffer from significantly lower inference speeds, making them unsuitable for real-time applications. Meanwhile, recent advances in open-world detection have introduced open-set and open-vocabulary algorithms in monocular 2D and 3D settings, yet stereo-based open-set detection remains largely unexplored. To bridge this gap, we propose DDStereo, a novel Dual-Decoder Stereo Transformer for real-time open-set 3D object detection. DDStereo features two lightweight decoder branches: one for open-set foreground 2D detection and the other for 3D attribute regression. These decoders share object-level queries to achieve unified target-level alignment. To enhance inference efficiency, we designed a compact disparity feature extractor and a streamlined decoder architecture. Experiments on public stereo 3D benchmarks demonstrate that DDStereo achieves state-of-the-art accuracy under both closed-set and open-set protocols. Notably, our method surpasses existing stereo 3D detectors in inference speed and, for the first time, achieves real-time performance comparable to monocular approaches.
Authors: Johannes Boehm, Bappaditya Dey
Abstract: Advanced semiconductor nodes drastically increased demand for Transmission Electron Microscopy (TEM), yet destructive sample preparation, slow imaging and high costs severely limit the availability of diverse datasets needed for downstream machine learning (ML). Synthetic data generation is becoming essential, but current generative models often miss TEM-specific noise, structural detail, and stochastic variability crucial for evaluation. We present a Denoising Diffusion Probabilistic Model (DDPM) framework for synthetic TEM image generation under extreme data scarcity. A progressive patch-based training strategy scales from low-resolution patches to full images, enabling from-scratch training with only 15 samples. We integrate a custom TrivialAugment adaptation, cross-process domain transfer, classifier guidance, and RePaint-style inpainting, culminating in full-image generation that preserves global structural and spatial relationships in compliance with FAB metrology requirements. Beyond synthesis, we repurpose DDPM feature representations for segmentation, partitioning encoder feature maps to obtain coherent region masks. Our synthetic images achieve up to MS-SSIM > 0.98 and qualitative expert assessment consistent with structural similarity results, facilitating downstream ML training for defect detection, segmentation, and metrology while preserving statistical and physical realism.
Authors: Chenrui Fan, Paolo Favaro
Abstract: Camera-prompted text-to-video (T2V) models are increasingly used to synthesize virtual camera captures, such as orbiting objects or moving through static scenes. For these outputs, visual plausibility is insufficient: the generated frames should also provide coherent multi-view evidence for a single static 3D scene. We introduce GeoT2V-Bench, a reconstruction-based diagnostic benchmark for evaluating whether camera-prompted T2V clips can support explicit rigid 3D reconstruction. Our pipeline estimates per-frame camera intrinsics and poses with VGGT-style geometry estimation, fits DeformableGS, derives a static MedianGS proxy by temporal-median aggregation, and renders this proxy along the estimated camera path. Instead of producing a pass/fail label or a single scalar score, GeoT2V-Bench reports a continuous reconstruction profile covering apparent image motion, estimated trajectory behavior, MedianGS static rendering error, static-render flow agreement, and the gap between flexible and static fits. On a fair-format four-seed evaluation with 3,840 completed reconstructions from 12 open-weight model configurations and 80 GeCo-Eval static-scene prompts, we find that visible motion, static rendering error, flow agreement, and flexible-vs-static behavior often disagree. GeoT2V-Bench therefore captures complementary failure modes that emerge when generated videos are tested as global static-scene acquisitions.
Authors: Hongzhu Yi, Zhongtian Luo, Tong Li, Yiyan Fan, Jungang Xu
Abstract: One-step diffusion editors are fast because they avoid inversion and iterative optimization, but a single transport update must be aggressive enough to realize the target prompt and conservative enough to preserve the source image--and no fixed update strength satisfies both demands across edit types. We treat this tension as a post-hoc candidate-selection problem on top of energy-field transport rather than as a new editing model. Our proposed method, Riemannian Residual Line Search, first builds a stronger edit by estimating the local time curvature of the prompt-delta field and projecting the corrected direction back onto the update norm of the original first-order energy-field transport estimation. It then forms a small residual path from the source image to this strong edit, retains the original first-order output as one candidate, and picks the final image by maximizing target-prompt CLIP alignment. On a 700-sample PIE-Bench++ evaluation across 10 edit type IDs, our method achieves state-of-the-art (SOTA) performance among current one-step update algorithms.
Authors: Sahereh Obeidavi, Dieter Landes
Abstract: Omnidirectional stereo images provide full-surround perception but violate the geometric assumptions of classical disparity estimation: in spherical or fisheye views, epipolar correspondences follow curved great-circle paths, producing two-dimensional displacements that cannot be treated as single-axis disparity before geometric rectification. In this work, we adopt a standard spherical-to-equirectangular (ERP) projection as a preprocessing step, which straightens epipolar curves and restores a one-dimensional disparity structure - horizontal for left-right rigs and vertical for top-bottom rigs. Building on our previously introduced RAFT + Epipolar-Aligned Channel Selection (EACS) framework, originally developed for rectilinear and ERP stereo, we examine whether the same modular pipeline remains accurate when the input originates from spherical stereo imagery. After ERP projection, dense optical flow from RAFT is reduced to disparity by retaining only the baseline-aligned flow component. Experiments on synthetic fisheye stereo datasets show that this spherical-to-ERP-to-RAFT+EACS pipeline produces accurate, smooth, and structurally consistent disparity maps at real-time speed. These findings confirm that established ERP preprocessing can be effectively combined with our earlier RAFT+EACS method to enable practical, interpretable, and efficient disparity estimation from spherical stereo, providing a straightforward pathway for extending conventional stereo pipelines to 360 imaging.
Authors: Zixuan Li, Haokun Lin, Yicheng Xiao, Zhiwei Li, Xinyang Song, Zelong Zheng, Yong He, Heng Yao, Ke Ding, Chao Yu, Chuan Yuan, Qi Li, Zhenan Sun
Abstract: Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation quality, but still struggle with structure-aware prompt following, where object counts, spatial relations, attribute bindings, and coarse layouts must be preserved. We attribute this limitation in part to the entanglement of structural planning and appearance rendering within a single conditioning stream. To address this issue, we propose Implicit Visual Chain-of-Thought (IV-CoT), a latent visual reasoning framework for query-conditioned image generation. IV-CoT decomposes the visual conditioning queries into a structural-to-semantic cascade, where structural queries first form a latent visual plan and semantic queries then render appearance conditioned on this plan. To guide the structural queries, we introduce training-only sketch supervision, which encourages them to capture structure from sketches without requiring sketch extraction or intermediate decoding at inference time. IV-CoT performs implicit CoT reasoning in a single forward pass and achieves superior results on GenEval and T2I-CompBench. Visualizations and analyses demonstrate that the learned structural and semantic queries play complementary roles in structure-aware generation.
Authors: Haorui Ji, Weizhe Liu, Hongdong Li, Hengkai Guo
Abstract: Sparse voxel representation has emerged as a scalable foundation for image-to-3D Gaussian Splatting (3DGS) generation, yet current methods struggle to preserve high-frequency visual details of input images due to two structural bottlenecks. First, they adopt discriminative 2D features optimized for semantic abstraction to construct sparse voxel latents, which suppress reconstructive cues and induce a representation bottleneck. Second, in the generation stage, standard diffusion transformers lack effective mechanisms to align dense 2D image tokens with sparse 3D voxel latents, resulting in a cross-modal correspondence bottleneck. To address these issues, we propose FLUX3D, a scalable image-to-3DGS framework that boosts both representation learning and cross-modal alignment during generation. We first revisit 2D feature selection for sparse-voxel-based 3D representation learning, propose Diffusion-Aligned Structured Latents (DA-SLAT) and couple it with a decoder-only architecture to improve 3DGS reconstruction fidelity. We also design a sparse-structure-aware diffusion framework, which integrates the Sparse-structure Multimodal Diffusion Transformer (SMDiT) and Modal-Aware Rotary Positional Embedding (MARoPE) to achieve geometry-agnostic 2D-3D alignment. Extensive benchmark experiments demonstrate that FLUX3D yields substantial improvements in appearance fidelity and significantly outperforms all state-of-the-art (SOTA) methods in generating high-quality 3DGS assets.
Authors: Orest Kupyn, Goutam Bhat, Philipp Henzler, Fabian Manhardt, Christian Rupprecht, Federico Tombari
Abstract: Generating explorable 3D scenes from a single image requires strong generative priors and accurate geometric representations suitable for downstream use. Current video diffusion models offer high-quality generation and implicitly encode multi-view geometric structure in latent space. However, existing feedforward latent scene decoders typically output volumetric 3D Gaussians that lack a well-defined surface, limiting their use in simulation or standard graphics pipelines. This motivates decoding surface-aligned primitives that are not only renderable but also closer to explicit geometric assets. We ask whether compressed video diffusion latents can be mapped directly to explicit surface primitives in a single pass. To this end, we introduce FLAT and, for the first time, show that triangle splats can be decoded directly from video diffusion latents. Compared with decoding 3D Gaussians, predicting flat primitives is notoriously more challenging due to high sensitivity to primitive orientations, oftentimes leading to poor gradient flow. FLAT solves with two key ingredients: a ray-centered rotation parameterization for triangle regression and a novel product window function that improves gradient flow during differentiable triangle rendering. On standard benchmarks, FLAT achieves significantly better geometric accuracy while maintaining competitive visual quality compared to state-of-the-art feedforward baselines. We further show that a lightweight test-time refinement step converts the predicted triangle soup into a fully opaque, game-engine-ready representation that supports real-time rendering. By evaluating 3DGS, 2DGS, and triangle splatting variants under an identical training setup, we provide the first systematic analysis of representation tradeoffs in feedforward scene generation. The project page is available at https://flat-splat.github.io
Authors: Qi Chen, Wenxuan Li, Pedro R. A. S. Bassi, Xinze Zhou, Jakob Wasserthal, Ibrahim Ethem Hamamci, Sezgin Er, Ashwin Kumar, Yiwen Ye, Yuhan Wang, Yuyin Zhou, Akshay S. Chaudhari, Curtis Langlotz, Kang Wang, Yang Yang, Alan L. Yuille, Zongwei Zhou
Abstract: Artificial intelligence (AI) has achieved remarkable success in medical imaging, but it is widely recognized that these models often perform inconsistently across real-world clinical settings. Such inconsistencies occur when patient demographics and imaging protocols vary, for example, in detecting small tumors, analyzing scans from different contrast phases, or evaluating patients of different ages or sexes. To quantify these inconsistencies, we develop a large-scale, open benchmark of 85,355 CT scans that systematically evaluates 12 tumor-detection AI models across tumor size, location, patient subgroup, and imaging protocol. We leverage large language models (LLMs) to extract and organize subgroup information from clinical data, which makes the analysis both scalable and reproducible. Our benchmark reveals that current state-of-the-art AI models, optimized for average accuracy, perform poorly in rare or underrepresented subgroups, such as young, female African Americans. However, collecting sufficient annotated data for these rare cases is often impractical. The benchmark provides a foundation for building more reliable and robust AI models for tumor detection and highlighting the need for rigorous, subgroup-level evaluation in medical imaging and computer vision. Datasets, code
Authors: Xingjian Leng, Jaskirat Singh, Zhanhao Liang, Ethan Smith, Martin Bell, Aninda Saha, Yuhui Yuan, Liang Zheng
Abstract: Diffusion transformer (DiT) research on image generation has converged to a single evaluation setup: class-conditional generation on ImageNet. While methods improve the FID and related metrics, it is increasingly unclear whether they reflect real progress in generative modeling. The natural alternative, i.e., text-to-image (T2I) generation, is perceived as too costly or inconvenient to train and evaluate and is often skipped. We argue that this perception no longer holds. We introduce NanoGen, a unified DiT training and evaluation framework. NanoGen matches state-of-the-art DiT baselines on ImageNet and, with 12 lines of configuration change, also trains competitive text-to-image models. It currently supports RAE, VAE, pixel-space, and MeanFlow diffusion methods under both ImageNet and T2I setups. Under NanoGen, training T2I requires comparable compute to ImageNet. After training 21 latent diffusion models with NanoGen, we observe that method ranking shows no strong correlation between ImageNet and T2I generation: Pearson correlation is between -0.377 and -0.580 across three metrics. This suggests that a method which improves class-conditional ImageNet FID may show no corresponding improvement on T2I, clearly indicating the necessity of evaluating DiTs on both tasks. To this end, we summarize ImageNet and text-to-image results, which yields DiffusionBench, a holistic benchmark for DiT research. We recommend reporting DiffusionBench in place of ImageNet alone: methods that improve DiffusionBench are more likely to reflect broader progress.
Authors: Yashkumar R Lukhi, Harsh Rameshbhai Moradiya, Radu Timofte, Dmitry Ignatov
Abstract: We present an automated large-scale search pipeline for heterogeneous 4-Expert Mixture-of-Experts (MoE4) architectures within the LEMUR neural network dataset ecosystem. Building on a hand-crafted heterogeneous MoE reference model, we replace manual design with a deterministic code-assembly generator that systematically combines base architecture families drawn from the LEMUR database into MoE4 ensembles, each governed by a convolutional gating network with temperature scaling, mixup augmentation, and cosine-annealed learning rate scheduling. Over a 28-day campaign on an NVIDIA RTX 4090, the pipeline generated 4,463 candidate models across 197 batches, of which 1,021 were evaluated successfully. A critical finding emerged from the campaign: due to alphabetical enumeration via itertools.combinations, the entire explored search space (4.8% of the theoretical 23,751 possible 4-family combinations) is anchored to a single family, AirNet. We characterise this coverage bias precisely, identify the root cause in the generator, and propose a stratified random sampling fix. Within the AirNet anchored scope, ShuffleNet and MobileNetV3 consistently co-produce the highest-accuracy ensembles (mean accuracy up to 0.632), while FractalNet and MNASNet are identified as low-yield families warranting exclusion in future campaigns. The pipeline, analysis artefacts, and corrected generator are released as part of the open-source NNGPT project at https://github.com/ABrain-One/nn-gpt
Authors: Reza Bozorgpour
Abstract: Deep learning has become an important tool in computational pathology, enabling automated analysis of histopathological images. While convolutional neural networks (CNNs) have traditionally dominated this field, transformer-based and hybrid architectures have recently demonstrated promising performance. However, comprehensive comparisons of these approaches for colorectal histopathology remain limited. This study evaluated twelve ImageNet-pretrained CNN, transformer, and hybrid architectures using the Kather colorectal histopathology dataset containing 5,000 image tiles from eight tissue classes. All models were trained using a standardized transfer-learning and fine-tuning protocol and assessed using multiple performance metrics, including accuracy, precision, sensitivity, specificity, F1-score, ROC-AUC, Cohen's kappa, and Matthews correlation coefficient. All evaluated models achieved high classification performance, with accuracies ranging from 93.2% to 97.1%. EVA-02 achieved the highest overall performance (97.1% accuracy, 97.0% F1-score), closely followed by ViT-B/16. Among CNNs, ResNet34 and ConvNeXt-Tiny demonstrated highly competitive performance, achieving accuracies of 96.4% and 96.3%, respectively. Transformer architectures generally produced the strongest results across evaluation metrics, although the performance gap between the best transformer and CNN models was relatively small. Per-class analysis showed consistently strong classification performance across all tissue categories, with Complex Stroma representing the most challenging class. Overall, transformer-based architectures achieved the highest predictive performance, whereas modern CNNs provided a favorable balance between accuracy and model complexity. These findings provide a comprehensive benchmark of major deep learning paradigms for colorectal histopathology classification.
Authors: Inioluwa Emmanuel, Zhuo Yang, Ho Yeung, Xinyao Zhang
Abstract: This work investigates the implementation of artificial intelligence and machine learning (AI/ML) for real-time monitoring in laser powder bed fusion (LPBF) additive manufacturing. We developed a binary image classification framework for distinguishing normal and abnormal melt pool images using a balanced dataset of 1,200 images collected from Nickel superalloy 625 on the NIST AMMT platform. The study evaluates accuracy and inference time based on control requirements and hardware limitations of open-architecture LPBF machines. We benchmark three transfer learning architectures (ResNet50, EfficientNetB0, and MobileNetV2) against two Random Forest approaches: one trained on EfficientNetB0 feature embeddings (hybrid) and one trained on raw pixel features (baseline). Images are stratified into 80/20 train-test splits, with a further 90/10 validation split on the training set, and undergo standardized resizing, normalization, and label-preserving data augmentation to emulate realistic process variability. Each model is evaluated using accuracy, precision, recall, F1 score, and area under the receiver operating characteristic curve (AUC), along with training time, inference latency, and CPU & GPU usage to capture deployability constraints relevant to factory-floor monitoring. The hybrid EfficientNetB0-plus-Random Forest approach achieves the best performance on the held-out test set, with an F1 score of 0.9451, accuracy of 0.9458, and AUC of 0.9904, while maintaining sub-millisecond per-image inference (1.15 ms). In contrast, purely deep learning models exhibit significantly higher inference times with lower accuracy. These results demonstrate that combining pre-trained convolutional features with classical ensemble methods provides a robust, computationally efficient route to real-time melt pool anomaly detection in data-limited additive manufacturing environments.
Authors: Qian Ma, Qiong Wu, Zhengyi Zhou, Yao Ma
Abstract: Knowledge-Based Visual Question Answering (KB-VQA) requires grounding visual queries to external knowledge beyond directly observable content in images. While recent multi modal large language models (MLLMs) show strong perceptual abilities, they struggle on KB-VQA tasks requiring groundings from both fine-grained entity and evidence levels. Most existing multi-modal retrieval augmented generation (MM-RAG) methods tightly couple entity discrimination and section-level evidence ranking into a single re-ranking stage, leading to high cost and limited generalization. In this work, we revisit existing MM-RAG solutions from a workflow perspective and argue both entity-level and fact-level groundings are key bottlenecks. We observe that although MLLMs often fail under open-ended entity naming, they can better identify the correct entity when selecting from a small set of candidate names. Based on this insight, we propose a simple and training-free identify-before-answer IBA framework that decouples entity identification from section-level re-ranking. Our approach prompts an MLLM to select high-confidence entities using only candidate names, followed by an off-the-shelf textual re-ranker for evidence selection. Experiments on Encyclopedic-VQA and InfoSeek show that our method consistently outperforms fine-tuned multi-modal re-ranking baselines while reducing training and inference complexity. Additional analyses reveal that the improvements arise not only from better entity identification, but also from selecting more informative evidence once correct entity is fixed. Our implementation is made public to ease reproducibility.
Authors: Sijing Li, Zhongwei Qiu, Zhuoya Wang, Boxiang Yun, Zhenyu Yi, Jianwei Xu, Wenqiao Zhang, Yingda Xia, Ling Zhang
Abstract: While Vision-Language Models (VLMs) show great promise in volumetric medical report generation, they frequently suffer from visual hallucinations and a lack of grounding in 3D CT data. Current Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) strategies typically optimize text fidelity alone, essentially rewarding correct diagnoses derived from language priors rather than genuine visual perception. To address this, we propose cross-view aligned Evidence-driven Multimodal Reinforcement Learning (Evidence-MRL, noted as E-MRL), a reliable RL reasoning framework that formulates the generation process as a Markov Decision Process of "diagnosis-localization-verification". Unlike standard approaches, our model is explicitly trained to identify a "key evidence slice" alongside the global diagnostic report, grounding its findings in verifiable visual evidence. Crucially, we introduce a novel cross-view consistency reward, which validates the semantic alignment between the golden-standard report and a local visual re-query of the selected key slice, providing additional rewards for correctly-localized reasoning. Experiments on large-scale 3D CT tumor datasets demonstrate that E-MRL significantly reduces hallucinations and improves diagnostic accuracy compared to SFT and RL baselines, offering a clinically interpretable solution for visually-grounded and tumor analysis.
Authors: Amirhossein Kardoost, Lion Gleiter, Tingying Peng, Carsten Marr
Abstract: Self-supervised learning in fluorescence microscopy often relies on 2D projections, despite the inherently three-dimensional nature of cells. We present a systematic comparison of 2D and 3D masked autoencoders (MAE-2D vs. MAE-3D) on volumetric microscopy data. Under matched architectures and training protocols, MAE-3D consistently outperforms 2D max-projection and slice-based variants on downstream single-cell tasks. We further align visual representations with a pretrained protein language model (ESM2) and show that cross-modal supervision yields larger gains for volumetric models. Channel cross-attention and frequency-domain regularization are critical for leveraging 3D spatial context. On a protein--protein interaction task, MAE-3D achieves a ROC--AUC of 0.865, outperforming prior methods by up to +0.025. For protein localization, our best 3D model attains state-of-the-art AUC$_{\text{micro}}$ (0.952) and F1$_{\text{micro}}$ (0.742), improving over previous approaches by +0.003 and +0.010 absolute, respectively. Overall, these results demonstrate the advantages of native 3D modeling and multimodal alignment for representation learning in single-cell microscopy.
Authors: Rishabh Sharma, Stefano Martiniani
Abstract: We introduce cyclic denoising -- repeated forward and reverse diffusion at controlled noise amplitudes -- as an extraction attack for image diffusion models. Inspired by random organization in disordered solids, cyclic denoising exposes regions of the learned distribution that are largely inaccessible to standard sampling. The dynamics drive samples toward attractors with a broad stability spectrum. The deepest attractors are ultrastable: they regenerate after near-total corruption and persist through thousands of noising-denoising cycles. Many of these attractors correspond to memorized training images, including stock photographs, brand watermarks, and web-crawl artifacts. The attack requires only sampler-level control, with no gradients, weight inspection, prompts, captions, or prior knowledge of the training data. Unlike generate-and-filter attacks, which rely on large-scale prompted generation and post-hoc similarity or membership-inference filtering, our main protocol is fully unconditioned. We demonstrate the phenomenon in Stable Diffusion v1.4 and in a pixel-space DDPM, showing consistent behavior across latent- and pixel-space diffusion models. Across noise amplitudes, we observe a yielding-like transition: low-amplitude cycling produces trivial absorbing fixed points or limit cycles, while larger amplitudes induce rearrangements, basin hopping, and long-lived trapping in structured memorized attractor basins. We also observe hierarchical partial absorption, prompt-stabilized basins, and cross-initial-condition universality of the recovered attractor set. Our results therefore show that cyclic denoising is both a physics-inspired probe of generative landscapes and a practical tool for memorization auditing, with implications for privacy, copyright compliance, and model fingerprinting.
Authors: Yanghong Mei, Longteng Guo, Ming-Ming Yu, Guiyu Zhao, Xingjian He, Jing Liu
Abstract: Conventional visual navigation policies often struggle with myopic decision-making and mode collapse in complex environments. While world models offer a promising alternative, existing paradigms typically isolate perception, generation, and control, failing to capture their shared spatio-temporal dynamics. In this paper, we propose NavWM, a unified navigation world model that seamlessly integrates latent world reasoning, multimodal action prediction, and controllable visual generation. At its core, NavWM leverages latent world tokens to distill geometric and semantic priors, endowing the agent with robust structural understanding. To overcome the limitations of deterministic policies, we introduce an anchor-based multimodal trajectory forecasting framework that generates a diverse action space. This inherent diversity explicitly empowers the generative world model to act as a robust closed-loop planner, utilizing visual foresight to evaluate and select the optimal path. Extensive experiments across diverse robotics datasets demonstrate that NavWM significantly advances the state-of-the-art, delivering remarkable improvements in both high-fidelity future state generation and zero-shot navigation success.
Authors: Inam Ullah, Imran Razzak, Shoaib Jameel
Abstract: Automated diabetic retinopathy (DR) grading from colour fundus photographs can achieve strong predictive performance, but clinical interpretation requires more than an image-level label. It requires understanding how lesion evidence is distributed around retinal vessels and how this evidence relates to quantitative vascular biomarkers. We present a dual-edge spatial-Jacobian image graph for interpretable DR grading. Each fundus image is represented as a graph node with four aligned evidence streams: AutoMorph vessel information ($X_1$), DR-XAI-style lesion evidence maps ($X_2$), a 128-dimensional lesion-based contrastive image embedding ($X_3$), and AutoMorph morphometric biomarkers ($X_4$). The spatial edge branch ($X_{12}$) encodes vessel-lesion geometry, while the Jacobian branch ($X_{34}$) models embedding-biomarker sensitivity. Lightweight two-token attention fuses both edge families into a final image graph. On 2,910 matched non-augmented APTOS images, the full graph achieves 0.8076 accuracy, 0.8312 quadratic weighted kappa, 0.5915 macro-F1, and 0.9330 adjacent-grade accuracy; referable DR reaches 0.9055 accuracy and 0.9711 AUROC. The framework is positioned as an explainable representation-learning tool for lesion-biomarker hypothesis generation, rather than as a deployment-ready clinical classifier. The code is available at https://github.com/Inamullah-Colab/dual-edge-dr-graph-xai.
URLs: https://github.com/Inamullah-Colab/dual-edge-dr-graph-xai.
Authors: Weihao Li, Dianne Cook, Emi Tanaka, Susan VanderPlas, Klaus Ackermann
Abstract: Visual assessment of residual plots is a common approach for diagnosing linear models, but it relies on manual evaluation, which does not scale well and can lead to inconsistent decisions across analysts. The lineup protocol, which embeds the observed plot among null plots, can reduce subjectivity but requires even more human effort. In today's data-driven world, such tasks are well suited for automation. We present a new R package that uses a computer vision model to automate the evaluation of residual plots. An accompanying Shiny application is provided for ease of use. Given a sample of residuals, the model predicts a visual signal strength (VSS) and offers supporting information to help analysts assess model fit.
Authors: Yijing Chen, Wenhui Tan, Xiaoyi Yu, Yuyue Wang, Xin Cheng, Kaisi Guan, Hao Jiang, Xiangyang Li, Guojie Zhu, Ruihua Song
Abstract: Multimodal Large Language Models have achieved remarkable progress in short-form audio-video understanding, yet long-form audio-video comprehension remains challenged by limited context windows and severe information redundancy. To address these bottlenecks, we propose AVOC, a framework for long-form audio-video understanding in Omni-modal Large Language Models. AVOC introduces a learnable token compression module between the modality encoders and the LLM backbone. We reframe multimodal token compression as a top-$K$ retrieval problem: given a fixed context budget, the module must retrieve a compact subset of tokens that best supports answering the user query. We draw inspiration from three classical Information Retrieval criteria for selecting informative units from a large candidate pool: relevance, importance, and diversity. AVOC instantiates each criterion as a tailored mechanism for audio-video understanding, and integrates them into a unified retrieval-style compression pipeline. Experiments show that AVOC achieves state-of-the-art performance on long-form audio-video benchmarks, surpassing the second-best model by 4.9 and 5.5 points in average accuracy on OmniVideoBench and LVOmniBench, respectively. Moreover, AVOC maintains robust performance on Audio-Video Needle-in-a-Haystack task at durations up to one hour.
Authors: Deepak Bhatia, Saad Ahmad, Smiti Tripathy, Maria Camila Bustos Vivas, Lieselotte Kratzsch, Anika Knupfer, Jordina Aviles Verdera, Susanne Schulz-Heise, Matthias May, Jana Hutter
Abstract: Standardized assessment of uterine MRI remains challenging due to anatomical variability, observer dependence, and the lack of workflow-integrated automated analysis tools. This work presents Female-RHINO: (R)eproductive (H)ealth (I)maging A(N)alysis T(O)ol, a real-time AI-assisted framework for automated quantitative uterine MRI analysis and structured reporting during image acquisition. We present an end-to-end system that integrates inline communication with the MRI scanner and deep learning-based analysis to derive quantitative uterine biomarkers from sagittal T2-weighted pelvic MRI. The framework combines segmentation and anatomical landmark detection models trained and evaluated on more than 500 multi-center datasets spanning diverse protocols, vendors, and patient populations. It performs volumetry, detects and quantifies common incidental findings such as fibroids and Nabothian cysts, and extracts six anatomical landmarks for biometric assessment. Results are compiled into a structured clinician-oriented report with integrated visualizations, without manual interaction. Evaluation on independent retrospective and prospective cohorts demonstrated robust performance across varying acquisition settings. Mean Dice similarity coefficients were 0.82 for the uterus and 0.80 for fibroids, with lower but consistent agreement for Nabothian cysts. Landmark detection achieved a mean radial error of 3.7 mm. End-to-end processing was completed in under 70 seconds, enabling availability of results during the ongoing scan. Prospective deployment yielded immediate, standardized, and reproducible analyses supported by inter-observer agreement. The proposed system enables real-time scanner-integrated AI for automated uterine MRI analysis and reporting, with potential to improve standardization, efficiency, and clinical workflow in pelvic imaging.
Authors: Pranjal Mishra, Ren\'e Zurbr\"ugg, Max Wilder-Smith, Marco Hutter, Marc Pollefeys, Zuria Bauer, Hermann Blum
Abstract: Deploying robots in unstructured real-world environments needs accurate, interactive models of the objects. Constructing these models at scale remains a critical bottleneck for robotic system integration. We present ArtiTwinSplat, a framework that automatically constructs articulated, photo-realistic digital twins of objects directly from RGB-D videos, requiring no CAD models, simulation assets, or manual annotations. Our method is built on 3D Gaussian Splatting that preserve geometric fidelity and photometric realism, coupled with an unsupervised articulation discovery pipeline that recovers part structure and joint kinematics from observed motion alone. With tracking and optimization stages our method provides stable, queryable digital twins that support real-time rendering, viewpoint control, and interactive manipulation. Unlike prior methods confined to simulation, ArtiTwinSplat operates directly on real-world observations and produces twins that are immediately usable by downstream robot planning and learning systems. This method offers a practical, scalable pathway toward digital twin construction, lowering the integration barrier for articulated object manipulation in embodied AI and human-robot collaboration contexts.
Authors: Mingkui Tan, Zhuangwei Zhuang, Sitao Chen, Rong Li, Kui Jia, Qicheng Wang, Yuanqing Li
Abstract: We study multi-sensor fusion for 3D semantic segmentation that is important to scene understanding for many applications, such as autonomous driving and robotics. Existing fusion-based methods, however, may not achieve promising performance due to the vast difference between the two modalities. In this work, we investigate a collaborative fusion scheme called perception-aware multi-sensor fusion (PMF) to effectively exploit perceptual information from two modalities, namely, appearance information from RGB images and spatio-depth information from point clouds. To this end, we project point clouds to the camera coordinate using perspective projection, and process both inputs from LiDAR and cameras in 2D space while preventing the information loss of RGB images. Then, we propose a two-stream network to extract features from the two modalities, separately. The extracted features are fused by effective residual-based fusion modules. Moreover, we introduce additional perception-aware losses to measure the perceptual difference between the two modalities. Last, we propose an improved version of PMF, i.e., EPMF, which is more efficient and effective by optimizing data pre-processing and network architecture under perspective projection. Specifically, we propose cross-modal alignment and cropping to obtain tight inputs and reduce unnecessary computational costs. We then explore more efficient contextual modules under perspective projection and fuse the LiDAR features into the camera stream to boost the performance of the two-stream network. Extensive experiments on benchmark data sets show the superiority of our method. For example, on nuScenes test set, our EPMF outperforms the state-of-the-art method, i.e., RangeFormer, by 0.9% in mIoU. Our source code is available at https://github.com/ICEORY/PMF.
Authors: Yuxiang Zhang, Chengguo Yuan, Xiao Wang, Bo Jiang, Jin Tang
Abstract: Sampled point and voxel methods are usually employed to downsample the dense events into sparse ones. After that, one popular way is to leverage a graph model which treats the sparse points/voxels as nodes and adopts graph neural networks (GNNs) to learn the representation of event data. Although good performance can be obtained, however, their results are still limited mainly due to two issues. (1) Existing event GNNs generally adopt the additional max (or mean) pooling layer to summarize all node embeddings into a single graph-level representation for the whole event data representation. However, this approach fails to capture the importance of graph nodes and also fails to be fully aware of the node representations. (2) Existing methods generally employ either a sparse point or voxel graph representation model which thus lacks consideration of the complementary between these two types of representation models. To address these issues, we propose a novel dual point-voxel absorbing graph representation learning for event stream data representation. To be specific, given the input event stream, we first transform it into the sparse event cloud and voxel grids and build dual absorbing graph models for them respectively. Then, we design a novel absorbing graph convolutional network (AGCN) for our dual absorbing graph representation and learning. The key aspect of the proposed AGCN is its ability to effectively capture the importance of nodes and thus be fully aware of node representations in summarizing all node representations through the introduced absorbing nodes. Extensive experiments on multiple event-based classification benchmark datasets fully validated the effectiveness of our framework.
Authors: Yicheng Zhan, Liang Shi, Wojciech Matusik, Qi Sun, Kaan Ak\c{s}it
Abstract: Rendering holograms for holographic displays is often an iterative and computationally costly process. Emerging learned holography methods have alleviated this bottleneck by enabling fast hologram rendering with improved reconstruction quality. However, existing methods still depend on fixed display hardware and scene parameters, requiring retraining for each new configuration. This limits rapid adaptation to different visual needs, including scene brightness, user focus preference, and hardware compatibility. We introduce Configurable Holography, a learned CGH framework in which a single model adapts to diverse display-scene parameters through explicit conditioning, eliminating the need for retraining. As a prototype, we present a configurable structure and derive a family of models that continuously adapt to propagation distance, volume depth, peak brightness, pixel pitch, and wavelength. To further improve efficiency, we incorporate auxiliary monocular depth estimation for depth-aware 3D hologram synthesis from RGB-only inputs and apply knowledge distillation for interactive inference. Our extensive simulation and hardware experiments on three holographic display prototypes with different combinations of configurations show on-par reconstruction quality with existing methods, offering up to 2x speed-up in fp32. Our work represents an initial step toward flexible, general-purpose learned holography systems that can seamlessly adapt across diverse hardware and user-specific visual requirements.
Authors: Xiaojie Li, Yibo Yang, Jianlong Wu, Yue Yu, Ming-Hsuan Yang, Liqiang Nie, Min Zhang
Abstract: Few-shot class-incremental learning (FSCIL) aims to incrementally learn novel classes from limited examples while preserving knowledge of previously learned classes. Existing methods face a critical dilemma: static architectures rely on a constant parameter space to learn from data that arrive sequentially, making them prone to overfitting to the current session, while dynamic architectures continually expand the parameter space, leading to increased complexity. In this study, we explore the potential of Selective State Space Models (SSMs) for FSCIL. Mamba leverages its input-dependent parameters to dynamically adjust its processing patterns and generate content-aware scan patterns without session-wise projector expansion. This enables it to configure distinct processing for base and novel classes, helping preserve existing knowledge while adapting to new ones. To leverage Mamba's potential for FSCIL, we design two key modules: First, we propose a dual selective SSM projector that generates input-conditioned state-space parameters from intermediate features for dynamic adaptation. The dual design structurally decouples base and novel-class processing, employing a frozen base branch to maintain stable base-class features and a dynamic incremental branch that adaptively learns distinctive feature shifts for novel classes. Second, we develop a class-sensitive selective scan mechanism to guide dynamic adaptation of the incremental branch. It reduces the disruption to base-class representations caused by training on novel data, and meanwhile, encourages the selective scan to perform in distinct patterns between base and novel classes. Extensive experiments on miniImageNet, CIFAR-100, and CUB-200 demonstrate that Mamba-FSCIL achieves state-of-the-art performance.
Authors: Ying Liu, Yijing Hua, Haojiang Chai, Yanbo Wang, TengQi Ye
Abstract: Open-vocabulary detectors are proposed to locate and recognize objects in novel classes. However, variations in vision-aware language vocabulary data used for open-vocabulary learning can lead to unfair and unreliable evaluations. Recent evaluation methods have attempted to address this issue by incorporating object properties or adding locations and characteristics to the captions. Nevertheless, since these properties and locations depend on the specific details of the images instead of classes, detectors can not make accurate predictions without precise descriptions provided through human annotation. This paper introduces 3F-OVD, a novel task that extends supervised fine-grained object detection to the open-vocabulary setting. Our task is intuitive and challenging, requiring a deep understanding of Fine-grained captions and careful attention to Fine-grained details in images in order to accurately detect Fine-grained objects. Additionally, due to the scarcity of qualified fine-grained object detection datasets, we have created a new dataset, NEU-171K, tailored for both supervised and open-vocabulary settings. We benchmark state-of-the-art object detectors on our dataset for both settings. Furthermore, we propose a simple yet effective post-processing technique. Our data, annotations and codes are available at https://github.com/tengerye/3FOVD.
Authors: Akash Jadhav, Michael Greenspan
Abstract: We propose DLTPose, a novel method for 6DoF object pose estimation from RGBD images that combines the accuracy of sparse keypoint methods with the robustness of dense pixel-wise predictions. DLTPose predicts per-pixel radial distances to a set of minimally four keypoints, which are then fed into our novel Direct Linear Transform (DLT) formulation to produce accurate 3D object frame surface estimates, leading to better 6DoF pose estimation. Additionally, we introduce a novel symmetry-aware keypoint ordering approach, designed to handle object symmetries that otherwise cause inconsistencies in keypoint assignments. Previous keypoint-based methods relied on fixed keypoint orderings, which failed to account for the multiple valid configurations exhibited by symmetric objects, which our ordering approach exploits to enhance the model's ability to learn stable keypoint representations. Extensive experiments on the benchmark LINEMOD, Occlusion LINEMOD and YCB-Video datasets show that DLTPose outperforms existing methods, especially for symmetric and occluded objects. The code is available at https://anonymous.4open.science/r/DLTPose_/ .
Authors: Chao Wang, Wei Lu, Xiang Li, Jian Yang, Lei Luo
Abstract: Single-source remote sensing object detection using optical or SAR images struggles in complex environments. Optical images offer rich textural details but are often affected by low-light, cloud-obscured, or low-resolution conditions, reducing the detection performance. SAR images are robust to weather, but suffer from speckle noise and limited semantic expressiveness. Optical and SAR images provide complementary advantages, and fusing them can significantly improve the detection accuracy. However, progress in this field is hindered by the lack of large-scale, standardized datasets. To address these challenges, we propose a new comprehensive dataset for optical-SAR fusion object detection, named Multi-resolution, Multi-polarization, Multi-scene, Multi-source SAR dataset (M4-SAR). It contains 112,174 instance-level aligned image pairs and nearly one million labeled instances with arbitrary orientations, spanning six key categories. To enable standardized evaluation, we develop a unified benchmarking toolkit that integrates six state-of-the-art multi-source fusion methods. Additionally, we propose E2E-OSDet, a novel end-to-end multi-source fusion detection framework that mitigates cross-domain discrepancies and establishes a robust baseline for future studies. Extensive experiments on M4-SAR demonstrate that fusing optical and SAR data can improve mAP by 5.7\% over single-source inputs, with particularly significant gains in complex environments. The dataset and code are publicly available at https://github.com/wchao0601/M4-SAR.
Authors: Zhongpai Gao, Benjamin Planche, Meng Zheng, Anwesa Choudhuri, Van Nguyen Nguyen, Terrence Chen, Ziyan Wu
Abstract: Photorealistic volumetric rendering of CT scans greatly benefits clinical workflows, yet neural approaches such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) require prohibitive per-scan optimization (hours for NeRF, about 30 minutes for 3DGS), making them impractical in clinical settings. We propose Render-FM, a feedforward model that eliminates this bottleneck by directly regressing 6D Gaussian Splatting (6DGS) parameters from a CT volume in a single 2.8-second forward pass, a 500x speedup over per-scan optimization. To bridge the domain gap between natural scene reconstruction and medical volumetric rendering, we introduce Anatomy-Guided Priming (AGP), which incorporates segmentation masks and transfer functions as structural and appearance priors, information that existing Gaussian splatting methods overlook. Built on an nnU-Net-inspired 3D U-Net trained on diverse CT scans, Render-FM predicts per-voxel 6DGS parameters and supports immediate real-time rendering. Unlike per-scan methods, it generalizes to unseen anatomies, novel transfer functions, and enables compositional organ visualization with zero additional preparation time. Optional 89-second fine-tuning further improves quality, surpassing per-scan optimized baselines. Project page: https://gaozhongpai.github.io/renderfm/.
Authors: Hugo Porta, Emanuele Dalsasso, Jessica L. McCarty, Devis Tuia
Abstract: Canada experienced in 2023 one of the most severe wildfire seasons in recent history, causing damage across ecosystems, destroying communities, and emitting large quantities of CO2. This extreme wildfire season is symptomatic of a climate-change-induced increase in the length and severity of the fire season that affects the boreal ecosystem. Therefore, it is critical to empower wildfire management in boreal communities with better mitigation solutions. Wildfire probability maps represent an important tool for understanding the likelihood of wildfire occurrence and the potential severity of future wildfires. The massive increase in the availability of Earth observation data has enabled the development of deep learning-based wildfire forecasting models, aiming at providing precise wildfire probability maps at different spatial and temporal scales. A main limitation of such methods is their reliance on coarse-resolution environmental drivers and satellite products, leading to wildfire occurrence prediction of reduced resolution, typically around $\sim 0.1${\deg}. This paper presents a benchmark dataset: CanadaFireSat, and baseline methods for high-resolution: 100 m wildfire forecasting across Canada, leveraging multi-modal data from high-resolution multi-spectral satellite images (Sentinel-2 L1C), mid-resolution satellite products (MODIS), and environmental factors (ERA5 reanalysis data). Our experiments consider two major deep learning architectures. We observe that using multi-modal temporal inputs outperforms single-modal temporal inputs across all metrics, achieving a peak performance of 60.3% in F1 score for the 2023 wildfire season, a season never seen during model training. This demonstrates the potential of multi-modal deep learning models for wildfire forecasting at high-resolution and continental scale.
Authors: Nisreen Albzour, Sarah S. Lam
Abstract: Cervical cancer remains a significant global health concern and a leading cause of cancer-related deaths among women. Early detection through Pap smear tests is essential to reduce mortality rates; however, the manual examination is time consuming and prone to human error. This study proposes a deep learning framework that integrates U-Net for segmentation and a classification model to enhance diagnostic performance. The Herlev Pap Smear Dataset, a publicly available cervical cell dataset, was utilized for training and evaluation. The impact of segmentation on classification performance was evaluated by comparing the model trained on segmented images and another trained on non-segmented images. Experimental results showed that the use of segmented images marginally improved the model performance on precision (about 0.41 percent higher) and F1-score (about 1.30 percent higher), which suggests a slightly more balanced classification performance. While segmentation helps in feature extraction, the results showed that its impact on classification performance appears to be limited. The proposed framework offers a supplemental tool for clinical applications, which may aid pathologists in early diagnosis.
Authors: Elena Camuffo, Francesco Barbato, Mete Ozay, Simone Milani, Umberto Michieli
Abstract: Personalized object detection aims to adapt a general-purpose detector to recognize user-specific instances from only a few examples. Lightweight models often struggle in this setting due to their weak semantic priors, while large vision-language models (VLMs) offer strong object-level understanding but are too computationally demanding for real-time or on-device applications. We introduce MOCHA (Multi-modal Objects-aware Cross-arcHitecture Alignment), a distillation framework that transfers multimodal region-level knowledge from a frozen VLM teacher into a lightweight vision-only detector. MOCHA extracts fused visual and textual teacher's embeddings and uses them to guide student training through a dual-objective loss that enforces accurate local alignment and global relational consistency across regions. This process enables efficient transfer of semantics without the need for teacher modifications or textual input at inference. MOCHA consistently outperforms prior baselines across four personalized detection benchmarks under strict few-shot regimes, yielding a +10.1 average improvement, with minimal inference cost.
Authors: Guanjie Wang, Zehua Ma, Han Fang, Weiming Zhang
Abstract: The rapid progress of image-guided video generation (I2V) has raised concerns about its potential misuse in misinformation and fraud, underscoring the urgent need for effective digital watermarking. While existing watermarking methods demonstrate robustness within a single modality, they fail to trace source images in I2V settings. To address this gap, we introduce the concept of Robust Diffusion Distance, which measures the temporal persistence of watermark signals in generated videos. Building on this, we propose I2VWM, a cross-modal watermarking framework designed to enhance watermark robustness across time. I2VWM leverages a video-simulation noise layer during training and employs an optical-flow-based alignment module during inference. Experiments on both open-source and commercial I2V models demonstrate that I2VWM significantly improves robustness while maintaining imperceptibility, establishing a new paradigm for cross-modal watermarking in the era of generative video. \href{https://github.com/MrCrims/I2VWM-Robust-Watermarking-for-Image-to-Video-Generation}{Code Released.}
URLs: https://github.com/MrCrims/I2VWM-Robust-Watermarking-for-Image-to-Video-Generation
Authors: Hojun Choi, Youngsun Lim, Jaeyo Shin, Hyunjung Shim
Abstract: Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-language models to generate pseudo-labels using image-text alignment, allowing detectors to generalize to unseen classes without explicit supervision. However, these methods depend heavily on single-step image-text matching, neglecting the intermediate reasoning steps crucial for interpreting semantically complex visual contexts, such as crowding or occlusion. In this paper, we introduce MSPL, a framework that incorporates multi-step visual reasoning into the pseudo-labeling process for OVD. It decomposes complex scene understanding into three interpretable steps-object localization, category recognition, and background grounding-where these intermediate reasoning states serve as rich supervision sources. Extensive experiments on standard OVD evaluation protocols demonstrate that MSPL achieves state-of-the-art performance with superior pseudo-labeling efficiency, outperforming the strong baseline by 9.4 AP50 for novel classes on OV-COCO and improving box and mask APr by 3.2 and 2.2, respectively, on OV-LVIS. Code and models are available at https://github.com/hchoi256/mspl.
Authors: Yunfan Lu, Nico Messikommer, Xiaogang Xu, Liming Chen, Yuhan Chen, Nikola Zubic, Davide Scaramuzza, Hui Xiong
Abstract: Hybrid event-frame sensors integrate an Event Vision Sensor (EVS) and an Active Pixel Sensor (APS) within a single chip, combining the high dynamic range and low latency of the EVS with the rich spatial intensity information from the APS. While this tight integration offers compact and temporally precise imaging, the complex circuit architecture introduces nontrivial noise patterns that remain poorly understood and unmodeled. In this work, we present the first unified statistics-based imaging noise model that jointly describes the noise behavior of APS and EVS pixels. Our formulation explicitly incorporates photon shot noise, dark current noise, fixed-pattern noise, and quantization noise, and links EVS noise to illumination level and dark current. Based on this formulation, we further develop a calibration pipeline to estimate noise parameters from real data and provide a detailed analysis of both APS and EVS noise behaviors. Finally, we propose H-ESIM, a statistically grounded simulator that generates RAW frames and events under realistic jointly calibrated noise statistics. Experiments on two hybrid sensors validate our model across multiple imaging tasks, including video frame interpolation and deblurring, demonstrating strong transfer from simulation to real data.
Authors: Kaixing Yang, Xulong Tang, Ziqiao Peng, Xiangyue Zhang, Puwei Wang, Jun He, Hongyan Liu
Abstract: Music-to-dance generation aims to translate auditory signals into expressive human motion, with broad applications in virtual reality, choreography, and digital entertainment. Despite promising progress, the limited generation efficiency of existing methods leaves insufficient computational headroom for high-fidelity 3D rendering, thereby constraining the expressiveness of 3D characters during real-world applications. Thus, we propose FlowerDance, which not only generates refined motion with physical plausibility and artistic expressiveness, but also achieves significant generation efficiency on inference speed and memory utilization. Specifically, FlowerDance combines MeanFlow with Physical Consistency Constraints, which enables high-quality motion generation with only a few sampling steps. Moreover, FlowerDance leverages a simple but efficient model architecture with BiMamba-based backbone and Channel-Level Cross-Modal Fusion, which generates dance with efficient non-autoregressive manner. Meanwhile, FlowerDance supports motion editing, enabling users to interactively refine dance sequences. Extensive experiments on AIST++ and FineDance show that FlowerDance achieves state-of-the-art results in both motion quality and generation efficiency. Code will be released upon acceptance.
Authors: Junwei Zhou, Yu-Wing Tai
Abstract: Generating complete 3D objects under partial occlusions (i.e., amodal scenarios) is a practically important yet challenging problem, as large portions of object geometry are unobserved in real-world scenarios. Existing approaches either operate directly in 3D, which ensures geometric consistency but often lacks generative expressiveness, or rely on 2D amodal completion, which provides strong appearance priors but does not guarantee reliable 3D structure. This raises a key question: how can we achieve both generative plausibility and geometric coherence in amodal 3D modeling? To answer this question, we introduce GENA3D (GENarative Amodal 3D), a framework that integrates learned 2D generative priors with explicit 3D geometric reasoning within a conditional 3D generation paradigm. The 2D priors enable the model to plausibly infer diverse occluded content, while the 3D representation enforces multi-view consistency and spatial validity. Our design incorporates a novel View-Wise Cross-Attention for multi-view alignment and a Stereo-Conditioned Cross-Attention to anchor generative predictions in 3D relationships. By combining generative imagination with structural constraints, GENA3D generates complete and coherent 3D objects from limited observations without sacrificing geometric fidelity. Experiments demonstrate that our method outperforms existing approaches in both synthetic and real-world amodal scenarios, highlighting the effectiveness of bridging 2D priors and 3D coherence in generating plausible and geometrically consistent 3D structures in complex environments.
Authors: Tian Liu, Anwesha Basu, James Caverlee, Shu Kong
Abstract: Semi-supervised few-shot learning (SSFSL) resembles real-world applications such as auto-annotation, as it aims to learn a model from a few labeled and abundant unlabeled task-specific examples to annotate the unlabeled ones. Despite the availability of powerful open-source Vision-Language Models (VLMs) and open-world data, existing SSFSL literature largely neglects these resources. In contrast, the related area few-shot learning (FSL) has already exploited them to boost performance. Arguably, to solve real-world auto-annotation, SSFSL should leverage such open resources. To bridge this gap, we explore established SSL methods to finetune a VLM. Unexpectedly, they significantly underperform FSL baselines that do not use unlabeled data. Our in-depth analysis reveals the root cause of failure: VLMs produce flat distributions of softmax probabilities, resulting in zero utilization of unlabeled data and weak supervision signals. To address this challenge, we propose an embarrassingly simple solution that uses temperatures to sharpen the softmax output, which not only increases the confidence scores of pseudo-labels to improve the utilization of unlabeled data, but also strengthens training supervision for effective finetuning. Furthermore, we exploit task-relevant open data, e.g., those retrieved from VLMs' publicly available pretraining set. To mitigate the imbalance and domain gaps in retrieved data, we employ a stage-wise training strategy. Building on the successful finetuning of VLMs and the exploitation of open data, we present a simple yet effective SSFSL method, Stage-Wise Finetuning with Temperatures (SWIFT). Across five benchmarks, SWIFT outperforms recent FSL and SSL methods by $\sim$5 accuracy points. SWIFT even rivals supervised learning, which finetunes a VLM assuming unlabeled data having ground-truth labels!
Authors: Yuyang Hu, Mojtaba Sahraee-Ardakan, Arpit Bansal, Kangfu Mei, Chenyang Qi, Peyman Milanfar, Mauricio Delbracio
Abstract: Pre-trained image restoration models often fail on out-of-distribution (OOD) real-world degradations. Adapting to these domains is challenging as real-world data lacks paired ground truth, and unsupervised methods often require unstable architectural changes. We propose Generative Manifold Distillation (GMD), which reframes domain adaptation as geometric manifold alignment. GMD operates in a strictly unpaired setting, requiring only low-quality (LQ) target observations. By leveraging the flow-matching dynamics of a frozen text-to-image foundation model, GMD projects off-manifold restorations onto the natural image manifold to generate high-quality pseudo-targets. To ensure stability, a quality-gated manifold filter rejects off-manifold samples, while source-anchored trajectory regularization prevents error accumulation. Ultimately, GMD distills a powerful generative prior into an efficient restoration network. Experiments demonstrate that GMD seamlessly adapts to new distributions using only LQ inputs, drastically improving perceptual quality with zero architectural modifications or added inference latency.
Authors: Zhuoxiao Li, Wenzong Ma, Taoyu Wu, Jinjing Zhu, Shuai Zhang, Jing OU, Tongyan Hua, Yinrui Ren, Rongjun Qin, Hui Xiong, Wufan Zhao
Abstract: Recent advances in Neural Radiance Fields and 3D Gaussian Splatting have demonstrated strong potential for large-scale UAV-based 3D reconstruction tasks by fitting the appearance of images. However, real-world large-scale captures are often based on multi-temporal data capture, where illumination inconsistencies across different times of day can significantly lead to color artifacts, geometric inaccuracies, and inconsistent appearance. Due to the lack of UAV datasets that systematically capture the same areas under varying illumination conditions, this challenge remains largely underexplored. To fill this gap, we introduceSkyLume, a large-scale, real-world UAV dataset specifically designed for studying illumination robust 3D reconstruction in urban scene modeling: (1) We collect data from 10 urban regions data comprising more than 100k high resolution UAV images (four oblique views and nadir), where each region is captured at three periods of the day to systematically isolate illumination changes. (2) To support precise evaluation of geometry and appearance, we provide per-scene LiDAR scans and accurate 3D ground-truth for assessing depth, surface normals, and reconstruction quality under varying illumination. (3) For the inverse rendering task, we introduce the Temporal Consistency Coefficient (TCC), a metric that measuress cross-time albedo stability and directly evaluates the robustness of the disentanglement of light and material. We aim for this resource to serve as a foundation that advances research and real-world evaluation in large-scale inverse rendering, geometry reconstruction, and novel view synthesis.
Authors: Bingxuan Li, Yiming Cui, Yicheng He, Yiwei Wang, Shu Zhang, Longyin Wen, Yulei Niu
Abstract: Sound effects build an essential layer of multimodal storytelling, shaping the emotional atmosphere and the narrative semantics of videos. Despite recent advancement in video-text-to-audio (VT2A), the current formulation faces three key limitations: First, an imbalance between visual and textual conditioning that leads to visual dominance; Second, the absence of a concrete definition for fine-grained controllable generation; Third, weak instruction understanding and following, as existing datasets rely on brief categorical tags. To address these limitations, we introduce EchoFoley, a new task designed for video-grounded sound generation with both event level local control and hierarchical semantic control. Our symbolic representation for sounding events specifies when, what, and how each sound is produced within a video or instruction, enabling fine-grained controls like sound generation, insertion, and editing. To support this task, we construct EchoFoley-6k, a large-scale, expert-curated benchmark containing over 6,000 video-instruction-annotation triplets. Building upon this foundation, we propose EchoVidia a sounding-event-centric agentic generation framework with slow-fast thinking strategy. Experiments show that EchoVidia surpasses recent VT2A models by 40.7% in controllability and 12.5% in perceptual quality.
Authors: Wei Yu Chen, Ying Dai
Abstract: To address the limitations of existing open-vocabulary object recognition methods, including high system complexity, substantial training costs, and limited generalization capability, this paper proposes a novel Open-Vocabulary Object Recognition (OVOR) framework based on a streamlined two-stage strategy: object segmentation followed by recognition. The proposed framework eliminates the need for complex retraining procedures and labor-intensive annotation. After extracting object regions, object-level image embeddings and category-level text embeddings are generated using CLIP, enabling recognition over arbitrary vocabularies. To reduce dependence on CLIP and enhance encoding flexibility, we further introduce a CNN/MLP-based approach that extracts convolutional neural network (CNN) feature maps and employs a multilayer perceptron (MLP) to align visual features with text embeddings. The resulting embeddings are then concatenated for cross-modal matching. Finally, object recognition is performed through similarity matching between image and text embeddings. Experiments on COCO, Pascal VOC, and ADE20K demonstrate that CLIP-based image encoding achieves the highest average AP, outperforming current state-of-the-art methods. Meanwhile, the results reveal the potential of CLIP-independent image encoding as a promising alternative for OVOR.
Authors: Ashim Dahal, Rabab Abdelfattah, Nick Rahimi
Abstract: Anchor-driven 4D Gaussian streaming methods such as Instant Gaussian Stream (IGS) update a dynamic scene each frame from a compact set of Gaussian anchors, chosen by default with Farthest Point Sampling (FPS) at a fixed budget of $8{,}192$. Because these anchors act as control points that drive the whole scene through linear blend skinning, the rule used to choose them ought to affect reconstruction quality. We test this by holding the IGS pipeline fixed and changing only the sampler, comparing FPS, random, uniform, an opacity-scale heuristic, and a learned policy across budgets and refinement settings on N3DV and MeetingRoom. At deployment budgets the sampler has no measurable effect: a cheap random or uniform sampler at $4{,}096$ anchors matches FPS@8192 within measurement error, the default budget is over-provisioned, and the result holds on a second backbone (3DGStream). The learned policy is mixed rather than consistently better: it can improve the N3DV validation set at tight budgets, but does not give a stable cross-dataset rule, and selection is never the bottleneck because refinement dominates runtime. We will release our full sweep and evaluation protocol as a sampler benchmark.
Authors: Shaojie Zhuang, Lu Yin, Guangshun Wei, Yunpeng Li, Xilu Wang, Yuanfeng Zhou
Abstract: Automatic tooth segmentation and identification from intra-oral scanned 3D models are fundamental problems in digital dentistry, yet most existing approaches rely on task-specific 3D neural networks trained with densely annotated datasets, resulting in high annotation cost and limited generalization to scans from unseen sources. Thus, we propose TSegAgent, which addresses these challenges by reformulating dental analysis as a zero-shot geometric reasoning problem rather than a purely data-driven recognition task. The key idea is to combine the representational capacity of general-purpose foundation models with explicit geometric inductive biases derived from dental anatomy. Instead of learning dental-specific features, the proposed framework leverages multi-view visual abstraction and geometry-grounded reasoning to infer tooth instances and identities without task-specific training. By explicitly encoding structural constraints such as dental arch organization and volumetric relationships, the method reduces uncertainty in ambiguous cases and mitigates overfitting to particular shape distributions. Experimental results demonstrate that this reasoning-oriented formulation enables accurate and reliable tooth segmentation and identification with low computational and annotation cost, while exhibiting strong generalization across diverse and previously unseen dental scans.
Authors: Ruicheng Yuan, Zhenxuan Zhang, Anbang Wang, Liwei Hu, Xiangqian Hua, Yaya Peng, Jiawei Luo, Guang Yang
Abstract: Pathology reports are structured, multi-granular documents encoding diagnostic conclusions, histological grades, and ancillary test results across one or more anatomical sites; yet existing pathology vision-language models (VLMs) reduce this output to a flat label or free-form text. We present HiPath, a lightweight VLM framework built on frozen UNI2 and Qwen3 backbones that treats structured report prediction as its primary training objective. Three trainable modules totalling 15M parameters address complementary aspects of the problem: a Hierarchical Patch Aggregator (HiPA) for multi-image visual encoding, Hierarchical Contrastive Learning (HiCL) for cross-modal alignment via optimal transport, and Slot-based Masked Diagnosis Prediction (Slot-MDP) for structured diagnosis generation. Trained on 749K real-world Chinese pathology cases from three hospitals, HiPath achieves 68.9% strict and 74.7% clinically acceptable accuracy with a 97.3% safety rate, outperforming all baselines under the same frozen backbone. Cross-hospital evaluation confirms generalisation with only a 3.4pp drop in strict accuracy while maintaining 97.1% safety.
Authors: Rongkang Dong, Cuixin Yang, Cong Zhang, Yushen Zuo, Kin-Man Lam
Abstract: Facial Expression Recognition (FER) is essential for human-machine interaction, as it enables machines to interpret human emotions and internal states from facial affective behaviors. Although deep learning has significantly advanced FER performance, most existing deep-learning-based FER methods rely heavily on discriminative classifiers for fast predictions. These models tend to learn shortcuts and are vulnerable to even minor distribution shifts. To address this issue, we adopt a conditional generative diffusion model and introduce the Emotion Diffusion Classifier (EmoDC) for FER, which demonstrates enhanced adversarial robustness. However, retraining EmoDC using standard strategies fails to penalize incorrect categorical descriptions, leading to suboptimal recognition performance. To improve EmoDC, we propose margin-based discrepancy training, which encourages accurate predictions when conditioned on correct categorical descriptions and penalizes predictions conditioned on mismatched ones. This method enforces a minimum margin between noise-prediction errors for correct and incorrect categories, thereby enhancing the model's discriminative capability. Nevertheless, using a fixed margin fails to account for the varying difficulty of noise prediction across different images, limiting its effectiveness. To overcome this limitation, we propose Adaptive Margin Discrepancy Training (AMDiT), which dynamically adjusts the margin for each sample. Extensive experiments show that AMDiT significantly improves the accuracy of EmoDC over the baseline model with standard denoising diffusion training under 100-step evaluations. Additionally, AMDiT-enhanced EmoDC has better generalization and robustness than state-of-the-art discriminative classifiers.
Authors: Merveilles Agbeti-Messan, Pierrick Tranouez, St\'ephane Nicolas, Cl\'ement Chatelain, Thierry Paquet
Abstract: End-to-end OCR for historical newspapers remains challenging, as models must handle long text sequences, degraded print quality, and complex layouts. While Transformer-based recognizers dominate current research, their quadratic complexity limits efficient paragraph-level transcription and large-scale deployment. We investigate linear-time State-Space Models (SSMs), specifically Mamba, as a scalable alternative to Transformer-based sequence modeling for OCR. We present to our knowledge, the first OCR architecture based on SSMs, combining a CNN visual encoder with bi-directional and autoregressive Mamba sequence modeling, and conduct a large-scale benchmark comparing SSMs with Transformer- and BiLSTM-based recognizers. Multiple decoding strategies (CTC, autoregressive, and non-autoregressive) are evaluated under identical training conditions alongside strong neural baselines (VAN, DAN, DANIEL) and widely used off-the-shelf OCR engines (PERO-OCR, Tesseract OCR, TrOCR, Gemini). Experiments on historical newspapers from the Bibliotheque nationale du Luxembourg, with newly released >99% verified gold-standard annotations, and cross-dataset tests on Fraktur and Antiqua lines, show that all neural models achieve low error rates (~2% CER), making computational efficiency the main differentiator. Mamba-based models maintain competitive accuracy while halving inference time and exhibiting superior memory scaling (1.26x vs 2.30x growth at 1000 chars), reaching 6.07% CER at the severely degraded paragraph level compared to 5.24% for DAN, while remaining 2.05x faster. We release code, trained models, and standardized evaluation protocols to enable reproducible research and guide practitioners in large-scale cultural heritage OCR available at https://github.com/MarcoPerson/ssm-ocr-benchmark.
Authors: Jiahui Peng, He Yao, Jingwen Li, Yanzhou Su, Sibo Ju, Yujie Lu, Jin Ye, Hongchun Lu, Xue Li, Lincheng Jiang, Min Zhu, Junlong Cheng
Abstract: Contrastive Language-Image Pre-training (CLIP) has demonstrated outstanding performance in global image understanding and zero-shot transfer through large-scale text-image alignment. However, the core of medical image analysis often lies in the fine-grained understanding of specific anatomical structures or lesion regions. Therefore, precisely comprehending region-of-interest (RoI) information provided by medical professionals or perception models becomes crucial. To address this need, we propose MedP-CLIP, a region-aware medical vision-language model (VLM). MedP-CLIP innovatively integrates medical prior knowledge and designs a feature-level region prompt integration mechanism, enabling it to flexibly respond to various prompt forms (e.g., points, bounding boxes, masks) while maintaining global contextual awareness when focusing on local regions. We pre-train the model on a meticulously constructed large-scale dataset (containing over 6.4 million medical images and 97.3 million region-level annotations), equipping it with cross-disease and cross-modality fine-grained spatial semantic understanding capabilities. Experiments demonstrate that MedP-CLIP significantly outperforms baseline methods in various medical tasks, including zero-shot recognition, interactive segmentation, and empowering multimodal large language models. This model provides a scalable, plug-and-play visual backbone for medical AI, combining holistic image understanding with precise regional analysis.
Authors: Kangyi Wu, Pengna Li, Kailin Lyu, Xi Lin, Lin Zhao, Qingrong He, Jinjun Wang, Jianyi Liu
Abstract: Vision-Language Navigation(VLN) requires an agent to navigate through 3D environments by following natural language instructions. While recent Video Large Language Models(Video-LLMs) have largely advanced VLN, they remain highly susceptible to State Drift in long scenarios. In these cases, the agent's internal state drifts away from the true task execution state, leading to aimless wandering and failure to execute essential maneuvers in the instruction. We attribute this failure to two distinct cognitive deficits: Progress Drift, where the agent fails to distinguish completed sub-goals from remaining ones, and Memory Drift, where the agent's history representations degrade, making it lose track of visited landmarks. In this paper, we propose a Dual-Anchoring Framework that explicitly anchors the instruction progress and history representations. First, to address progress drift, we introduce Instruction Progress Anchoring, which supervises the agent to generate structured text tokens that delineate completed versus remaining sub-goals. Second, to mitigate memory drift, we propose Memory Landmark Anchoring, which utilizes a Landmark-Centric World Model to retrospectively predict object-centric embeddings extracted by the Segment Anything Model, compelling the agent to explicitly verify past observations and preserve distinct representations of visited landmarks. Facilitating this framework, we curate two extensive datasets: 3.6 million samples with explicit progress descriptions, and 937k grounded landmark data for retrospective verification. Extensive experiments in both simulation and real-world environments demonstrate the superiority of our method, achieving a 15.2% improvement in Success Rate and a remarkable 24.7% gain on long-horizon trajectories. To facilitate further research, we will release our code, data generation pipelines, and the collected datasets.
Authors: Agnieszka Anna Tomaka, Krzysztof Domino, Micha{\l} Tarnawski, Dariusz Pojda
Abstract: Patient-specific occlusal positioning splints can be regarded as physical realisations of planned mandibular transformations. However, the achieved mandibular pose may differ from the planned one because of acquisition, registration, fabrication, and positioning errors. This study presents a transformation-based biomedical engineering framework for quantifying mandibular positioning accuracy and propagating the resulting error to a simulated temporomandibular joint configuration. Multimodal 3D data, including CBCT, facial motion acquisition, and dental scans, were integrated in a common coordinate system. Positioning splints corresponding to selected mandibular poses were designed and fabricated, and their realised positions were evaluated using repeated scans of plaster models. Discrepancies between planned and achieved positions were represented as rigid-body error transformations and analysed in SE(3), together with surface-distance metrics. The estimated transformations were propagated to CBCT-derived TMJ structures to quantify changes in condyle-fossa distance maps. The results demonstrate a systematic translational component and anisotropic variability of mandibular positioning error, with measurable propagation to simulated TMJ-space changes. The proposed framework provides an objective method for documenting planned and achieved mandibular configurations and for analysing positioning uncertainty in patient-specific splint workflows.
Authors: Harshvardhan Saini, Samyak Jha, Yiming Tang, Dianbo Liu
Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input. We investigate the root causes of these failure modes with a mechanistic analysis focusing on the decoder-based VLMs. We trace these failure modes to a geometric over-alignment: to bridge the modality gap required by attention mechanisms, decoder-based VLMs over-align visual embeddings with the text manifold, injecting a statistical linguistic bias that systematically overshadows fine-grained visual evidence. While prior work either aggressively closes this gap or suppresses hallucinations through expensive black-box decoding strategies, none addresses the underlying geometric cause. We provide the first quantitative characterization of this over-alignment, demonstrating that linguistic bias concentrates in the top principal components of a universal, dataset-agnostic text subspace. Building on this insight, we propose two complementary remedies: a training-free inference strategy and a bias-aware fine-tuning paradigm, both of which explicitly project out this subspace from visual representations. Our methods significantly reduce hallucinations across POPE, CHAIR, and AMBER benchmarks, and improve CLAIR scores on long-form captioning tasks, with the training-free variant adding no computational overhead over the base model.
Authors: Feng Chen, Xianghui Wang, Yuxuan Chen, Boying Li, Yefei He, Zeyu Zhang, Yicheng Wu
Abstract: Vision-Language-Action (VLA) models predominantly adopt action chunking, i.e., predicting and committing to a short horizon of consecutive low-level actions in a single forward pass, to amortize the inference cost of large-scale backbones and reduce per-step latency. However, committing these multi-step predictions to real-world execution requires balancing success rate against inference efficiency, a decision typically governed by fixed execution horizons tuned per task. Such heuristics ignore the state-dependent nature of predictive reliability, leading to brittle performance in dynamic or out-of-distribution settings. In this paper, we introduce A3, an Adaptive Action Acceptance mechanism that reframes dynamic execution commitment as a self-speculative prefix verification problem. A3 first computes a trajectory-wise consensus score of actions via group sampling, then selects a representative draft and prioritizes downstream verification. Specifically, it enforces: (1) consensus-ordered conditional invariance, which validates low-consensus actions by judging whether they remain consistent when re-decoded conditioned on high-consensus actions; and (2) prefix-closed sequential consistency, which guarantees physical rollout integrity by accepting only the longest continuous sequence of verified actions starting from the beginning. Consequently, the execution horizon emerges as the longest verifiable prefix satisfying both internal model logic and sequential execution constraints. Experiments across diverse VLA models and benchmarks demonstrate that A3 eliminates the need for manual horizon tuning while achieving a superior trade-off between execution robustness and inference throughput.
Authors: Daniel Lengerer, Mathias Pechinger, Klaus Bogenberger, Carsten Markgraf
Abstract: Bird's-eye-view (BEV) representations derived from multi-camera input have become a central interface for online high-definition (HD) map construction. However, most approaches rely solely on ego-centric supervision, requiring large-scale scene structure to be inferred from incomplete observations, occlusions, and diminishing information density at long range, where perspective effects and spatial sparsity hinder consistent structural reasoning. We introduce Cross-View Supervision (CVS), a representation learning paradigm that transfers geometric and topological priors from an ego-aligned overhead perspective into camera-based BEV encoders. Rather than adding auxiliary semantic losses, CVS aligns representations in a shared BEV feature space and distills globally consistent structural knowledge from a perspective-privileged teacher into the ego-centric backbone. This supervision enhances structural coherence without modifying the inference architecture or requiring overhead input at test time. Experiments on nuScenes using ego-aligned aerial imagery from the AID4AD cross-view extension demonstrate consistent improvements over StreamMapNet while maintaining identical camera-only inference. CVS yields +3.9mAP in the standard $60\times30\,\mathrm{m}$ region and +9.9mAP in the extended $100\times50\,\mathrm{m}$ setting, corresponding to a 44% relative gain at long range. These results highlight perspective-privileged structural supervision as a promising training principle for improving BEV representation learning in HD map construction.
Authors: Chengshuai Yang, Lei Xing, Keyaan Zawad Alam, Gregory Entin, Roopa Vemulapalli, Lisa Casey, Raiyan Tripti Zaman
Abstract: Background. RGB-trained classifiers for wireless capsule endoscopy (WCE) conflate hemoglobin contrast with bile staining and illumination falloff, limiting sensitivity to small-vessel vascular findings such as Lymphangiectasia. We introduce a physics-informed framework that injects an analytic, Monte-Carlo-inspired hemoglobin prior into a standard classifier purely at training time -- to our knowledge the first use of an explicit optical light-transport prior in WCE classification. Methods. On Kvasir-Capsule (47,238 frames, 43 patients, 11 evaluable classes; patient-disjoint split) we test, across 6 seeds against an RGB-only EfficientNet-B0 baseline: (i) a 5-channel input-fusion variant feeding the prior P_blood alongside RGB; (ii) a distillation variant that runs on plain 3-channel RGB at inference; and (iii) a three-stream extension adding a temporal Transformer and an autoencoder-residual stream. We replicate across ResNet-18 and ConvNeXt-Tiny and report cross-vendor zero-shot transfer on the public Galar cohort. Results. Input fusion lifts cross-seed macro-AUC 0.760 -> 0.783 (5/6 seeds positive); distillation reaches 0.773; the three-stream model reaches 0.804 (+0.044 over baseline, paired DeLong p < 1e-4). Lymphangiectasia AUC rises 0.238 -> 0.337, sign-consistent across all 6 seeds. A four-variant ablation reveals a parameterization-mechanism boundary: only the spatial-channel form lifts. Cross-vendor zero-shot on Galar retains ~60% of the ConvNeXt-Tiny lift.
Authors: Danish Ali, Ajmal Mian, Naveed Akhtar, Ghulam Mubashar Hassan
Abstract: Accurate brain tumor segmentation using multi-parametric MRI is critical for effective treatment planning. However, in clinical settings, complete acquisition of all MRI sequences is not always possible. The absence of certain MRI modalities results in substantial performance degradation in existing segmentation methods, which typically rely on naive feature concatenation or direct fusion strategies. To address this limitation, we propose a novel segmentation model D3Seg which is designed to maintain stable performance under missing-modality settings. D3Seg introduces Multi-hop Modality Graph Fusion (MMGF) to model higher-order inter-modality dependencies, a lightweight diffusion-based imputation mechanism to compensate for missing T1ce and FLAIR feature representations in latent space, and probability-space decision refinement to mitigate dominant-class overconfidence and improve delineation of underrepresented tumor subregions. We evaluate the proposed D3Seg model on BraTS 2023 Glioma as the primary benchmark and further test it on a subset of the external BraTS 2023 Meningioma cohort to assess generalization across tumor pathologies. The results are compared with the state-of-the-art models under different missing-modality conditions. The proposed model achieves approximately 1.5-2.0% Dice improvement on enhancing tumor (ET) and around 1.0% on tumor core (TC) across multiple missing-modality configurations compared to the current state-of-the-art model on BraTS Glioma dataset. Cross-cohort evaluation on BraTS Meningioma dataset demonstrates the generalizability of the proposed model, showing consistent improvements in the challenging TC and ET regions, with approximately 1.5-3.0% and 1.5-6.5% gains respectively across several missing-modality configurations.
Authors: Phuoc-Nguyen Bui, Van-Vi Vo, Duc-Tai Le, Junghyun Bum, Van-Nguyen Pham, Ki-Young Kim, Seung-Young Yu, Hyunseung Choo
Abstract: Long-term visual acuity (VA) outcomes after anti-VEGF therapy are central to patient counseling, expectation setting, and follow-up planning in diabetic macular edema (DME). However, in clinical practice, physicians must often estimate long-term visual trajectories based only on early post-treatment findings, making reliable prognostication difficult. Although prior OCT-based learning approaches have largely focused on short-term response or single-endpoint prediction, modeling VA trajectories across multiple future time points from early longitudinal observations remains insufficiently explored. In this study, we assembled a real-world cohort of 188 anti-VEGF--treated DME patients with paired baseline and month-1 OCT scans, along with tabular OCT-derived biomarkers and non-imaging clinical variables. Using only these early data, we formulate a multi-horizon VA forecasting problem aimed at predicting visual outcomes at 3, 6, 12, 18, and 24 months, reflecting clinically meaningful follow-up intervals. We propose \textbf{ReVA}, a response-aware multimodal framework that integrates structural features from baseline and month-1 OCT with the tabular variables to capture baseline disease status and early treatment response. ReVA uses spatial attention to preserve localized prognostic imaging features and a dependency-aware tabular encoder to model interactions among clinical variables. These multimodal representations are fused to predict patient-specific long-term visual acuity trajectories. The proposed framework achieves MAE $=0.1246$, RMSE $=0.1621$, and $R^2=0.6064$ for 24-month VA prediction, with consistent performance across all forecast horizons. Our findings show that incorporating early treatment-response signals enables clinically meaningful long-term visual acuity forecasting, supporting data-driven decision support for routine anti-VEGF management.
Authors: NVIDIA, :, Aditi, Niket Agarwal, Arslan Ali, Jon Allen, Martin Antolini, Adeline Aubame, Alisson Azzolini, Junjie Bai, Maciej Bala, Yogesh Balaji, Josh Bapst, Aarti Basant, Mukesh Beladiya, Mohammad Qazim Bhat, Zaid Pervaiz Bhat, Dan Blick, Vanni Brighella, Han Cai, Tiffany Cai, Eric Cameracci, Jiaxin Cao, Yulong Cao, Mark Carlson, Carlos Casanova, Ting-Yun Chang, Yan Chang, Yu-Wei Chao, Prithvijit Chattopadhyay, Roshan Chaudhari, Chieh-Yun Chen, Junyu Chen, Ke Chen, Qizhi Chen, Wenkai Chen, Xiaotong Chen, Yu Chen, An-Chieh Cheng, Click Cheng, Xiu Chia, Jeana Choi, Chaeyeon Chung, Wenyan Cong, Yin Cui, Magdalena Dadela, Nalin Dadhich, Wenliang Dai, Joyjit Daw, Alperen Degirmenci, Rodrigo Vieira Del Monte, Robert Denomme, Sameer Dharur, Marco Di Lucca, Ke Ding, Wenhao Ding, Yifan Ding, Yuzhu Dong, Nicole Drumheller, Yilun Du, Aigul Dzhumamuratova, Aleksandr Efitorov, Hamid Eghbalzadeh, Naomi Eigbe, Imad El Hanafi, Hassan Eslami, Benedikt Falk, Jiaojiao Fan, Jim Fan, Amol Fasale, Sergiy Fefilatyev, Liang Feng, Francesco Ferroni, Sanja Fidler, Xiao Fu, Vikram Fugro, Prashant Gaikwad, TJ Galda, Katelyn Gao, Yihuai Gao, Wenhang Ge, Sreyan Ghosh, Arushi Goel, Vivek Goel, Akash Gokul, Rama Govindaraju, Jinwei Gu, Miguel Guerrero, Elfie Guo, Aryaman Gupta, Siddharth Gururani, Hugo Hadfield, Song Han, Ankur Handa, Zekun Hao, Mohammad Harrim, Ali Hassani, Nathan Hayes-Roth, Yufan He, Chris Helvig, Cyrus Hogg, Madison Huang, Michael Huang, Sophia Huang, Yufan Huang, Jacob Huffman, DeLesley Hutchins, Suneel Indupuru, Boris Ivanovic, Arihant Jain, Joel Jang, Ryan Ji, Yanan Jian, Dongfu Jiang, Jingyi Jin, Atharva Joshi, Nikhilesh Joshi, Pranjali Joshi, Andy Ju, Jaehun Jung, Weiwei Kang, Scott Kassekert, Jan Kautz, Ashna Khetan, Julia Kiczka, Slawek Kierat, Gwanghyun Kim, Kuno Kim, Sunny Kim, Kezhi Kong, Xin Kong, Zhifeng Kong, Tomasz Kornuta, Egor Krivov, Hui Kuang, Saurav Kumar, Chia-Wen Kuo, George Kurian, Wojciech Kutak, JF Lafleche, Himangshu Lahkar, Omar Laymoun, Jayjun Lee, Sanggil Lee, Gabriele Leone, Boyi Li, Freya Li, Jiajun Li, Jinfeng Li, Ling Li, Pengcheng Li, Shangru Li, Tingle Li, Xiaolong Li, Xuan Li, Zhaoshuo Li, Zhiqi Li, Hao Liang, Maosheng Liao, Chen-Hsuan Lin, Tsung-Yi Lin, Ming-Yu Liu, Sifei Liu, Zihan Liu, Hai Loc Lu, Xiangyu Lu, Alice Luo, Ruipu Luo, Wenjie Luo, Jiangran Lyu, Martin Ding Ma, Nic Ma, Qianli Ma, Dawid Majchrowski, Louis Marcoux, Miguel Martin, Qing Miao, Ashkan Mirzaei, Shreyas Misra, Kaichun Mo, Durra Mohsin, Hyejin Moon, Pawel Morkisz, Saeid Motiian, Kirill Motkov, Seungjun Nah, Yashraj Narang, Deepak Narayanan, Thabang Ngazimbi, Julian Ouyang, Shubham Pachori, David Page, Yatian Pang, Sehwi Park, Mahesh Patekar, Mostofa Patwary, Marco Pavone, Trung Pham, Wei Ping, Soha Pouya, Shrimai Prabhumoye, Varun Praveen, Delin Qu, Hesam Rabeti, Morteza Ramezanali, Marilyn Reeb, Xuanchi Ren, Kristen Rumley, Wojciech Rymer, Jun Saito, Yeongho Seol, John Shao, Piyush Shekdar, Tianwei Shen, Humphrey Shi, Min Shi, Stella Shi, Kevin Shih, Mohammad Shoeybi, Mateusz Sieniawski, Shuran Song, Alexander Sotelo, Amir Sotoodeh, Sunil Srinivasa, Vignesh Srinivasakumar, Bartosz Stefaniak, Rahul Heinrich Steiger, Shangkun Sun, Jiaxiang Tang, Shitao Tang, Yangyang Tang, Yue Tang, Tolou Tavakkoli, Kayley Ting, Krzysztof Tomala, Wei-Cheng Tseng, Jibin Varghese, Sergei Vasilev, Thomas Volk, Raju Wagwani, Roger Waleffe, Andrew Z. Wang, Boxiang Wang, Haoxiang Wang, Qiao Wang, Shihao Wang, Shijie Wang, Ting-Chun Wang, Yan Wang, Yu Wang, Rohit Watve, David Wehr, Fangyin Wei, Xinshuo Weng, Jay Zhangjie Wu, Kedi Wu, Hongchi Xia, Summer Xiao, Tianjun Xiao, Kevin Xie, Daguang Xu, Jiashu Xu, Mengyao Xu, Ruqing Xu, Xingqian Xu, Yao Xu, Dinghao Yang, Dong Yang, Hans Yang, Xiaodong Yang, Xuning Yang, Yichu Yang, Yurong You, Zhiding Yu, Hao Yuan, Simon Yuen, Xiaohui Zeng, Pengcuo Zeren, Cindy Zha, Haotian Zhang, Jenny Zhang, Jing Zhang, Liangkai Zhang, Paris Zhang, Shun Zhang, Xuanmeng Zhang, Zhizheng Zhang, Ann Zhao, Yilin Zhao, Yuliya Zhautouskaya, Charles Zhou, Fengzhe Zhou, Shilin Zhu, Yuke Zhu, Dima Zhylko, Artur Zolkowski
Abstract: We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI -- effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 License at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3.
URLs: https://github.com/nvidia/cosmos, https://huggingface.co/collections/nvidia/cosmos3., https://research.nvidia.com/labs/cosmos-lab/cosmos3.
Authors: Dilakshan Srikanthan, Amoon Jamzad, Paul Wilson, Nooshin Maghsoodi, Robert Policelli, Gabor Fichtinger, John F. Rudan, Parvin Mousavi
Abstract: Whether attention maps from pathology foundation models capture genuine biology remains unknown, yet this question is critical for clinical trust and regulatory approval. We propose a spatial transcriptomics-based framework for orthogonal, hypothesis-free evaluation of attention and apply it to five pathology foundation models (CONCH v1.5, UNI v2, Virchow2, GigaPath, H-Optimus-1) and a ResNet50 baseline. Using attention-based multiple instance learning, we train single-task and multi-task models to predict five molecular alterations in glioblastoma on the CPTAC cohort, validate on an independent TCGA cohort, and evaluate biological coherence of attention maps against 87 transcriptional signatures using co-registered Visium spatial transcriptomics data from 18 samples. Internally, no single encoder dominates across all tasks, and external validation inverts internal performance rankings. Attention maps show a five-fold enrichment gradient from pathways (Cohen's d=0.329) to individual genes (d=0.055), indicating that attention captures emergent multi-gene transcriptional programs rather than individual molecular events. Spatially smooth attention maps do not imply biological coherence, and different encoders attend to distinct biological compartments. Our framework provides objective, quantitative assessment of what foundation models learn from histopathology, moving the field beyond qualitative saliency map review.
Authors: Nicol\`o Savioli, Luca Del Tongo
Abstract: Every new clinical imaging device creates a domain shift where dense gland masks are expensive yet cheap clinical signals -- eyelid outlines, Pult grades, morphometric ratios -- are routinely recorded. We present TopoPult-SSL, a two-stage framework for cross-device meibomian gland segmentation. Stage 1 adapts a source-trained model without target gland masks in the training loss, using four weak-prior anchors driven by target eyelid masks and clinical metadata only. Stage 2, when target gland masks are available, distils complementary Stage-1 teachers into a single compact student via supervised self-distillation. We develop and validate the technique on the public MGD-1k to CAMG research benchmark (1,000 to 100 images, different device), where the distilled model achieves Dice 0.716+/-0.006 (best 0.726), surpassing UA-MT (0.710) and the ensemble teacher (0.720) -- with a single pass. The gland-mask-free Stage-1 variant reaches Precision 0.694 vs. 0.30-0.34 for SAM/MedSAM (p<0.001), enabling deployment without dense gland contouring. Code and reproducibility scripts are released.
Authors: Jianxu Shangguan, Jing Xu, Hang Ye, Xiaoxuan Ma, Yizhou Wang, Jenq-Neng Hwang, Wentao Zhu
Abstract: Creating lifelike digital humans with genuine social intelligence requires unifying cognitive reasoning and multimodal generation within a coherent framework. Current approaches treat these as separate tasks: Large Language Models excel at dialogue but lack embodied expression, while diffusion-based talking head models achieve visual fidelity but ignore social cognition. To bridge this gap, we propose a closed-loop dual-agent framework integrating perception, social reasoning, and expression into a continuous interaction cycle. The perception module analyzes partners' multimodal behaviors from video, while the social reasoning module infers hidden mental states through Theory of Mind and selects responses via an ensemble mechanism. The expression module then generates emotion-controllable videos that jointly synthesize speaker speech and facial expressions with listener reactive behaviors, capturing bidirectional dynamics absent in prior work. We further construct a hierarchical Persona-Scenario dataset with psychologically grounded personas and private social goals to support evaluation under information asymmetry. Experiments on this dataset demonstrate competitive or superior performance on both dialogue quality and video generation metrics. Notably, our method surpasses even the full-information Script mode on key dialogue quality dimensions, suggesting that explicit mental state inference under uncertainty can elicit more thoughtful dialogue than unrestricted information access. Project page: https://resonantminds.github.io/.
Authors: Kateryna Lutsai, Dana K\v{r}iv\'ankov\'a, Pavel Stra\v{n}\'ak, David Nov\'ak
Abstract: Purpose: Digitization projects in the humanities produce vast, heterogeneous archives of historical documents, making manual sorting impractical at scale. This work addresses the need for an automated system to classify scanned page images based on visual content type - text, tables, and graphics - enabling content-specific downstream processing such as Optical Character Recognition (OCR) or structured data extraction. Methods: An image classification system was developed and evaluated on a dataset of over 48,000 annotated historical page images from century-old Czech archaeological archives, refined through four successive annotation stages with domain-expert review. A Random Forest Classifier baseline was established using hand-crafted image features. Subsequently, deep learning architectures were fine-tuned and compared: Convolutional Neural Networks (EfficientNetV2, RegNetY), Vision and Document Image Transformers (ViT, DiT), and multimodal CLIP models. An 11-category label scheme was designed collaboratively with domain experts and evaluated via five-fold cross-validation. Results: The feature-based baseline achieved approximately 75% accuracy. Fine-tuned CNNs and Transformers substantially outperformed it, with RegNetY-16GF achieving 99.16% and ViT-large 99.12% Top-1 accuracy on the held-out test set. CLIP ViT-B/16 reached 99.14% with optimized text descriptions. Conclusion: Image-only models, particularly RegNetY-16GF, deliver near-perfect classification accuracy and produce consistent labels across 649,508 unlabeled archival pages with over 90% inter-model agreement. Fine-tuned CLIP, despite competitive test-set accuracy, showed under 65% agreement with image-only models on unlabeled data, making it less suitable for deployment. The final models, annotated dataset, and software are publicly available under open-source licenses.
Authors: Yuke Zhao, Wangbo Zhao, Weijie Wang, Zeyu Zhang, Dakai An, Akide Liu, Yinghao Yu, Jiasheng Tang, Fan Wang, Wei Wang, Bohan Zhuang
Abstract: We introduce WorldOlympiad, a benchmark for diagnosing video-based world models across physical faithfulness, geometric consistency, and interaction fidelity. While existing benchmarks often focus on visual quality, semantic alignment, or short-term temporal coherence, they provide limited insight into whether generated videos obey physical rules, preserve coherent 3D structure, and sustain controllable interactions over long horizons. To address this gap, WorldOlympiad decomposes world-model evaluation into three complementary dimensions. The physical track uses object segmentation and MLLM-as-judge to assess whether generated videos follow interpretable rules in mechanics, thermal phenomena, and material properties. The geometry track reconstructs generated videos with Gaussian splatting and evaluates structural consistency, cross-view coherence, and camera-trajectory alignment. The interaction track assesses whether generated rollouts follow complex action prompts and maintain smooth, coherent transitions across consecutive video chunks. WorldOlympiad further covers three major downstream scenarios, including gaming, robotics, and general real-world videos, capturing diverse challenges from interactive control and embodied manipulation to open-domain motion and camera dynamics. Together, these tracks and scenarios form a scalable and interpretable evaluation suite that exposes failure modes beyond generic video quality. Experiments on state-of-the-art models reveal substantial gaps in physical reasoning, 3D consistency, and long-horizon interaction, underscoring the need for more structured evaluation protocols for generative world models.
Authors: Palak Gupta, Shanmuganathan Raman
Abstract: Most existing approaches either fix the container in advance or optimize only a single container dimension through an outer search loop, leaving the remaining dimensions as a manual tuning problem. We present a differentiable packing framework that jointly optimizes all 6N object pose parameters and all three container side lengths inside a single gradient-based loop. The formulation combines six physics-inspired, differentiable loss terms computed directly on triangle meshes through axis-aligned bounding-box proxies. An adaptive squeezing mechanism periodically tightens the container whenever the overlap loss falls below a pair-count-scaled threshold, producing a large initial drop in container volume, followed by small refinements. All pairwise computations are written in tensor-broadcasting form, giving a 3.4 to 54 times speedup over a reference loop-based implementation. The pipeline is implemented in Python and PyTorch, with no physics engine, FFT library, or convex decomposition. On multiple object categories, the method produces containers that are 11 to 32 percent smaller than time-matched DBLF and simulated-annealing baselines at N =100, while running in under 4 minutes per instance on a single consumer GPU.
Authors: Siyi Chen, Shaowei Liu, Yixuan Jia, Zian Wang, Huan Ling, Qing Qu, Jun Gao
Abstract: Recent progress has shown promise in distilling multi-step video diffusion models into efficient few-step students. Among them, Distribution Matching Distillation (DMD) and its successor DMD2 achieved strong generation quality and fast convergence. However, due to the nature of the reverse Kullback--Leibler (KL) objective, these methods exhibit two persistent failure modes: a substantial drop in sample diversity, and visibly over-saturated outputs that deviate from real-video appearance. In this work, we propose Data-Forcing Distillation (DFD), a simple post-training framework that restores diversity and fidelity in DMD with only a single-line of code change. At its core is the teacher score discrepancy to guide the student toward the real-data distribution, pulling it to missing modes (mitigating mode collapse) and away from problematic modes absent in real data (avoiding over-saturation). We provide an in-depth theoretical analysis of our framework and validate our approach on text-to-video, image-to-video, and autoregressive video generation. With only 100--300 steps of finetuning, DFD effectively restores diversity and fidelity on both Wan2.1-1.3B and Cosmos-Predict2.5-2B model, resolving the over-saturation artifacts with significantly better video dynamics and appearance, and even outperforms the teacher model.
Authors: Yucheng Tang, Alexander Ng, Wen Yan, Natasha Thorley, Pawel Rajwa, Yipei Wang, Aqua Asif, Clare Allen, Louise Dickinson, Francesco Giganti, Shonit Punwani, Daniel Alexander, Veeru Kasivisvanathan, Yipeng Hu
Abstract: Clinical prostate multi-parametric MRI relies heavily on high-quality diffusion-weighted imaging (DWI), yet reading DWI is frequently compromised by geometric distortion, often caused by rectal air. Assessing quality via the PI-QUAL scoring system is an emerging clinical standard, but it is subjective, time-consuming and suffers from a class imbalance where low-quality cases are diverse and relatively scarce. Using the PRIME clinical trial as an example, there are $6\%$ images with PI-QUAL scores lower than 4, $87\%$ of DWI issues are due to distortion. Many of the other clinical quality issues are under-represented. To address this common dual-scarcity of annotated clinical data, we propose a few-shot biparametric prototypical network for automated image quality assessment (IQA). Our framework utilizes a dual-branch 3D ResNet to fuse T2-weighted and DWI features, providing anatomical context to distinguish true morphology from distortion. To handle real-world heterogeneity, we introduce feature-wise linear modulation (FiLM) and a gradient reversal layer (GRL) to align feature distributions conditioned on varying b-values while suppressing acquisition-related biases. We demonstrate that a model meta-trained solely on comparatively objective, readily obtainable distortion labels can effectively adapt to predicting complex, multi-factorial clinical quality scores such as PI-QUAL using only five representative samples. Experimental results on two datasets show that our method significantly outperforms few-shot learning baselines for this challenging IQA task, offering a practically feasible and data-efficient solution for standardizing prostate MRI quality control in clinical workflows.
Authors: Maciej Wozniak, Jesper Ericsson, Hariprasath Govindarajan, Truls Nyberg, Thomas Gustafsson, Patric Jensfelt, Olov Andersson
Abstract: Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD). However, current approaches typically treat VFMs as black-box teachers, relying exclusively on frame-wise feature similarity. Consequently, they do not fully exploit the teacher's layer-wise semantic structure and global context, as well as the rich spatiotemporal information inherent in LiDAR sequences. We propose HilDA, a self-supervised pretraining framework for LiDAR backbones that better captures the semantic what and geometric where needed for driving tasks. HilDA combines hierarchical distillation comprising multi-layer distillation for progressive semantic alignment and global context distillation for scene-level semantics, with a temporal occupancy diffusion objective promoting spatiotemporal consistency. Models pre-trained with HilDA achieve state-of-the-art results on cross-modal distillation benchmarks and outperform models trained via prior distillation approaches on 3D object detection, scene flow, and semantic occupancy prediction. Code available at: https://maxiuw.github.io/hilda.
Authors: Hiroki Sakuma, Masatoshi Okutomi
Abstract: Multi-view surface reconstruction is a core problem in computer vision. One prominent line of work represents the surface implicitly as a signed distance field (SDF), optimizing it based on the photometric loss between rendered and observed pixel colors. These approaches typically employ SDF-based volume rendering to obtain a differentiable relaxation of discontinuous visibility along rays, thereby reducing reliance on silhouette supervision. In this paper, we reformulate SDF-based volume rendering as probabilistic surface rendering, where each pixel color is modeled as a mixture distribution induced by the random first ray-surface intersection. To this end, we introduce Stochastic Signed Distance Processes (SSDP), which model the SDF along each ray as a stochastic process, inducing a first-passage-time distribution for each ray. We then derive the first-passage probability for each sampling interval based on Bayesian filtering, together with its practical approximation for parallel rendering. We further show that NeuS, an existing SDF-based volume rendering method, arises as a special case of our formulation. Experiments on the DTU and MobileBrick datasets demonstrate that our method outperforms baselines in both surface reconstruction and uncertainty quantification, supporting the effectiveness of our first-passage formulation. Our code is available at https://github.com/skmhrk1209/SSDP.
Authors: Wenhao Wang, Franziska Boenisch, Michael Backes, Adam Dziedzic
Abstract: Memorization in machine learning models enables high performance on rare in-distribution samples by capturing their atypical patterns. However, it also causes harmful retention of noise and outliers, degrading generalization. While memorization has been extensively studied in both supervised and self-supervised learning in the vision domain, it remains unexplored in multi-modal contrastive learning. We address this gap by introducing MultiMem, the first metric designed to quantify memorization in multi-modal contrastive learning. Through our systematic analysis, we demonstrate that cross-modal semantic misalignment has the strongest influence on memorization, with text being the dominant modality driving memorization, followed by video, image, and audio. We show that targeted augmentations applied across all modalities effectively reduce memorization as measured by our MultiMem metric and improve model performance. Overall, this work establishes the first framework for measuring and mitigating memorization in multi-modal contrastive learning, preventing harmful data retention and contributing to higher-performing models.
Authors: Yufei Zhang, Changhao Chen
Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural-language instructions in unseen scenes. While Large Models (LMs) have advanced VLN-CE, their performance remains severely degraded by real-world visual corruptions, a critical yet underexplored domain constraint. We introduce Temporal Conditional Flow Decorruptor (FlowDec), a novel image restoration framework tailored for LM-based VLN-CE. FlowDec integrates a hybrid temporal conditioning strategy to align the generative flow path with historical context and employs action-centroid guided filtering to dynamically assess and integrate outputs. Extensive experiments demonstrate that FlowDec outperforms state-of-the-art decorruption methods in both navigation accuracy and generation latency. Our approach establishes a robust, efficient paradigm for resilient embodied navigation in unpredictable real-world conditions.
Authors: Nicol\`o Savioli
Abstract: Modern Referring Image Segmentation (RIS) systems generate multiple candidate masks per expression but rely on a simple heuristic--typically the argmax detection score--to select the final output. We identify query selection as a failure-case bottleneck: although heuristic selection succeeds on 82-93% of samples, the residual 7-18% of failures dominate the error budget, leaving a best-query selection gap of 3-11% mIoU. We introduce Venice-H1, a lightweight, backbone-decoupled post-hoc re-ranking module that encodes each candidate through multi-scale grid signatures--compact spatial descriptors pooled onto 4x4, 8x8, and 16x16 grids--and feeds them to a Transformer-based re-ranker with a Failure Gate (ROCAUC 0.78-0.82) that intervenes only when the default choice is likely suboptimal. Instantiated on DeRIS-L and DeRIS-B, Venice-H1 achieves delta_fail of +1.40 and +0.89 mIoU with strictly positive 95% CIs on all 16/16 (split, backbone) pairs and harmful-switch rates below 0.53%. Zero-shot transfer to medical referring segmentation (MS-CXR, M3D-RefSeg-2D) yields +1.16 and +0.51 mIoU without RIS-backbone fine-tuning. The module adds approximately 11.3M parameters and under 1 ms latency.
Authors: Srinivas Venkatanarayanan, Clement Pakkam Isaac
Abstract: Vision-language models (VLMs) are increasingly used to read maps for logistics, delivery, and accessible navigation, where the output is an actionable decision (a route, a pin, a parking choice) that must respect the road network. Yet most map benchmarks grade free text or multiple-choice answers that cannot be verified against the underlying graph. We present MapReason-OSM, a benchmark and evaluation harness for graph-verifiable mobility decisions on self-rendered OpenStreetMap panels. We render fixed-style maps for ten U.S. downtowns at two aligned zoom scales, overlay a consistent marker grammar, and pair each panel with a hidden street graph and exact oracles, yielding 6,000 instances (12,000 panels across the two zooms) over 12 routing, facility-location, and visual disambiguation tasks. Models return structured decisions that we snap back to the graph and score for validity, legality, optimality, and constraint satisfaction, plus cross-zoom consistency. Across seven VLMs, models read maps and route simply but fail at graph cost reasoning (single-facility pin placement is near chance even for frontier reasoning models), and are frequently scale-inconsistent. We release the benchmark, harness, and deterministic generator. Code and data: https://github.com/Vi-Sri/mapreason-osm
Authors: Mohamed Nagy, Naoufel Werghi, Jorge Dias, Majid Khonji
Abstract: The tracking-by-detection paradigm in multi-object tracking (MOT) typically relies on static appearance descriptors to complement motion estimation. However, these descriptors are frame-independent, limiting their robustness as visual cues. Since such descriptors are often obtained from computationally intensive pretrained backbones, real-time MOT systems frequently abandon appearance cues altogether and rely solely on motion prediction and geometric association. In this work, we introduce Polycepta, an object-centric appearance state estimation framework that reformulates appearance modeling as a recursive estimation problem rather than a frame-wise matching task. Polycepta constructs and continuously updates an independent appearance state for each tracked object, enabling future appearance representations to be estimated from accumulated observations. Polycepta is encouraged to learn the appearance-state construction of object-specific representations rather than memorize them through a proposed learning strategy, enabling appearance estimation for unseen classes. A key property of Polycepta is that the quality of appearance estimation improves as object states evolve during inference. While conventional appearance descriptors remain static or degrade over time, Polycepta progressively refines appearance estimates as additional observations are accumulated. Extensive experiments on KITTI, the Waymo Open Dataset, and MOT17 demonstrate consistent reductions in identity switches and improvements in tracking performance when integrated into the tracking-by-detection pipelines. Polycepta operates at 90.57 Hz and delivers state-of-the-art performance on the KITTI benchmark when integrated into the RobMOT framework, achieving a MOTA of 92.27\%.
Authors: Peng Wang, Xiao Li, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, Qing Qu
Abstract: Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks perform hierarchical feature learning across layers. In this work, we attempt to unveil this mystery by investigating the structures of intermediate features. Motivated by our empirical findings that linear layers mimic the roles of deep layers in nonlinear networks for feature learning, we explore how deep linear networks transform input data into output by investigating the output (i.e., features) of each layer after training in the context of multi-class classification problems. Toward this goal, we first define metrics to measure within-class compression and between-class discrimination of intermediate features, respectively. Through theoretical analysis of these two metrics, we show that the evolution of features follows a simple and quantitative pattern from shallow to deep layers when the input data is nearly orthogonal and the network weights are minimum-norm, balanced, and approximate low-rank: Each layer of the linear network progressively compresses within-class features at a geometric rate and discriminates between-class features at a linear rate with respect to the number of layers that data have passed through. To the best of our knowledge, this is the first quantitative characterization of feature evolution in hierarchical representations of deep linear networks. Empirically, our extensive experiments not only validate our theoretical results numerically but also reveal a similar pattern in deep nonlinear networks which aligns well with recent empirical studies. Moreover, we demonstrate the practical implications of our results in transfer learning. Our code is available at https://github.com/Heimine/PNC_DLN.
Authors: Mingyuan Meng, Yuxin Xue, Dagan Feng, Lei Bi, Jinman Kim
Abstract: Dense prediction is a fundamental requirement for many medical vision tasks such as medical image restoration, registration, and segmentation. The most popular vision model, Convolutional Neural Networks (CNNs), has reached bottlenecks due to the intrinsic locality of convolution operations. Recently, transformers have been widely adopted for dense prediction for their capability to capture long-range visual dependence. However, due to the high computational complexity and large memory consumption of self-attention operations, transformers are usually used at downsampled feature resolutions. Such usage cannot effectively leverage the tissue-level textural information available only at the full image resolution. This textural information is crucial for medical dense prediction as it can differentiate the subtle human anatomy in medical images. In this study, we hypothesize that Multi-layer Perceptrons (MLPs) are superior alternatives to transformers in medical dense prediction where tissue-level details dominate the performance, as MLPs enable long-range dependence at the full image resolution. To validate our hypothesis, we develop a full-resolution hierarchical MLP framework that uses MLPs beginning from the full image resolution. We evaluate this framework with various MLP blocks on a wide range of medical dense prediction tasks including restoration, registration, and segmentation. Extensive experiments on six public well-benchmarked datasets show that, by simply using MLPs at full resolution, our framework outperforms its CNN and transformer counterparts and achieves state-of-the-art performance on various medical dense prediction tasks.
Authors: Rustin Soraki, Huayu Wang, Sitong Liu, Joann G. Elmore, Linda Shapiro
Abstract: Cancer survival prediction from whole slide images (WSIs) is a challenging task in computational pathology due to the large size, irregular shape, and high granularity of the WSIs. These characteristics make it difficult to capture the full spectrum of patterns, from subtle cellular abnormalities to complex tissue interactions, which are crucial for accurate prognosis. To address this, we propose CrossFusion, a novel multi-scale feature integration framework that extracts and fuses information from patches across different magnification levels. By effectively modeling both scale-specific patterns and their interactions, CrossFusion generates a rich feature set that enhances survival prediction accuracy. We validate our approach across six cancer types from public datasets, demonstrating significant improvements over existing state-of-the-art methods. Moreover, when coupled with domain-specific feature extraction backbones, our method shows further gains in prognostic performance compared to general-purpose backbones. The source code is available at: https://github.com/RustinS/CrossFusion
Authors: Matteo Gambella, Manuel Roveri
Abstract: Incremental learning is a machine learning paradigm where a model learns from a sequential stream of tasks. This setting poses a key challenge: balancing plasticity (learning new tasks) and stability (preserving past knowledge). Neural Architecture Search (NAS), a branch of AutoML, automates the design of the architecture of Deep Neural Networks and has shown success in static settings. However, existing NAS-based approaches to incremental learning often rely on expanding the model at every task, making them impractical in resource-constrained environments. In this work, we introduce SEAL, a NAS-based framework tailored for data-incremental learning, a scenario where disjoint data samples arrive sequentially and are not stored for future access. SEAL adapts the model structure dynamically by expanding it only when necessary, based on a capacity estimation metric. Stability is preserved through cross-distillation training after each expansion step. The NAS component jointly searches for both the architecture and the optimal expansion policy. Experiments across multiple benchmarks demonstrate that SEAL effectively reduces forgetting and enhances accuracy while allocating additional capacity only when required. These results highlight the promise of combining NAS and selective expansion for efficient, adaptive learning in incremental scenarios.
Authors: James K Ruffle, Samia Mohinta, Guilherme Pombo, Asthik Biswas, Alan Campbell, Indran Davagnanam, David Doig, Ahmed Hammam, Harpreet Hyare, Farrah Jabeen, Emma Lim, Dermot Mallon, Stephanie Owen, Sophie Wilkinson, Sebastian Brandner, Parashkev Nachev
Abstract: Brain tumour MRI typically requires both pre- and post-contrast imaging, but gadolinium is not always desirable (frequent follow-up, renal impairment, allergy, paediatric patients). We developed and validated a deep learning model to predict tumour contrast enhancement from non-contrast MRI alone. We assembled 11,089 brain MRI studies (2006-2024) from 10 datasets across four countries and three continents, spanning adult and paediatric populations with glioma, meningioma, metastases, and post-resection appearances. Three architectures were trained to detect and segment enhancing tumour from T1w, T2w and FLAIR alone. Performance was assessed in a 1,109-study held-out test set (primary endpoint: patient-level enhancement detection; secondary: voxel-level Dice). Eleven expert radiologists attempted the same task on a 564-case subset (100 cases each), blinded to history, prior imaging, and referral. The best model, nnU-Net, achieved 83.0% balanced accuracy (95% CI 79.1-87.2; sensitivity 91.5%, specificity 74.4%) for detection, with R2 = 0.859 for enhancement volume. Of enhancing cases, 76.8% reached Dice >= 0.3, 67.5% >= 0.5, and 50.2% >= 0.7. Under blinded conditions, radiologists' majority vote was lower (71.7% balanced accuracy; sensitivity 77.6%, specificity 65.8%). The proportion reaching Dice >= 0.3 varied by pathology (meningioma 93%, presurgical glioma 76%, metastases 74%, postoperative glioma 74%) and was lowest for paediatric cases (45%). Deep learning can identify contrast-enhancing brain tumours from non-contrast MRI. These models show promise as a triage or decision-support adjunct, such as in flagging studies likely to enhance so that contrast can be added to a non-contrast protocol, and may reduce gadolinium dependence in neuro-oncology imaging. Future work should optimise these models with radiologists.
Authors: Jinda Du, Jieji Ren, Qiaojun Yu, Ningbin Zhang, Yu Deng, Xingyu Wei, Yufei Liu, Guoying Gu, Xiangyang Zhu
Abstract: Dexterous robotic hands are expected to perform complex, contact-rich object manipulation, but learning such skills remains challenging because high-dimensional hands require high-fidelity demonstrations. Imitation learning provides a practical route for acquiring dexterous manipulation skills from human demonstrations, yet collecting synchronized multimodal demonstrations with accurate hand actions and tactile observations remains a key bottleneck. We present MILE, a teleoperation-based data-collection system comprising the human-first MILE exoskeleton and the mechanically corresponding MILE-Tac robotic hand. The system integrates custom-designed and fabricated modular joint encoders and compact MILE fingertip visuotactile sensor modules. The exoskeleton is informed by human-hand anatomy and ergonomic constraints, while the robotic hand is co-designed to preserve the selected four-finger kinematic topology. This correspondence enables joint-space command transfer and reduces reliance on task-space IK-based retargeting. The system synchronously records task-specific visual observations, four fingertip visuotactile streams, robot-hand proprioception, and exoskeleton-derived action commands. We evaluate MILE through a four-task teleoperation benchmark against representative glove-based and vision-based interfaces, and through imitation-learning experiments that compare policies trained with and without fingertip tactile input. The project page is available at https://sites.google.com/view/mile-system.
Authors: Hyunsoo Kim, Ehsan Pajouheshgar, Sabine S\"usstrunk, Wenzel Jakob, Jinah Park
Abstract: We introduce Neural Particle Automata (NPA), a Lagrangian generalization of Neural Cellular Automata (NCA) from static lattices to dynamic particle systems. Unlike classical Eulerian NCA where cells are pinned to pixels or voxels, NPA model each cell as a particle with a continuous position and internal state, both updated by a shared, learnable neural rule. This particle-based formulation yields clear individuation of cells, allows heterogeneous dynamics, and concentrates computation only on regions where activity is present. At the same time, particle systems pose challenges: neighborhoods are dynamic, and a naive implementation of local interactions scale quadratically with the number of particles. We address these challenges by replacing grid-based neighborhood perception with differentiable Smoothed Particle Hydrodynamics (SPH) operators backed by memory-efficient, CUDA-accelerated kernels, enabling scalable end-to-end training. Across tasks including morphogenesis, point-cloud classification, and particle-based texture synthesis, we show that NPA retain key NCA behaviors such as robustness and self-regeneration, while enabling new behaviors specific to particle systems. Together, these results position NPA as a compact neural model for learning self-organizing particle dynamics.
Authors: Leo Lin, Shivansh Patel, Jay Moon, Svetlana Lazebnik, Unnat Jain
Abstract: We introduce CRAFT hand, a tendon-driven anthropomorphic hand with hybrid hard-soft compliance for contact-rich manipulation. The design is based on a simple idea: contact is not uniform across the hand. Impacts concentrate at joints, while links carry most of the load. CRAFT places soft material at joints and keeps links rigid, and uses rollingcontact joint surfaces to keep flexion on repeatable motion paths. Fifteen motors mounted on the fingers drive the hand through tendons, keeping the form factor compact and the fingers light. In structural tests, CRAFT improves strength and endurance while maintaining comparable repeatability. In teleoperation, CRAFT improves handling of fragile and low-friction items, and the hand covers 33/33 grasps in the Feix taxonomy. The full design costs under $600 and will be released open-source with visionbased teleoperation and simulation integration. Project page: http://craft-hand.github.io/
Authors: JunJia Guo (Joe), Yuhang Yao (Joe), Jiawei (Joe), Zhou, Jingdi Chen
Abstract: We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike prior code generation benchmarks that focus on algorithmic tasks, VISTA targets realistic UI-centric development, where agents must produce functional, visually coherent applications from underspecified inputs. We define five prompt-information conditions that vary along two axes, visual/structural fidelity and stack constraint: (1) text only with free stack choice, (2) text with reference screenshots under three specified stacks, (3) text with reference screenshots under free stack choice, (4) text with screenshots and pruned Figma structure under a single specified stack, and (5) text with screenshots and pruned Figma structure under free stack choice. To enable robust evaluation, each page in the benchmark is manually annotated with interactive UI components and around three visual anchor points, addressing the well-known limitations of script-based testing tools such as Playwright in open-ended code generation settings. Evaluation combines DOM-grounded reference matching, behavior-specific browser tests, and CLIP-based visual similarity, jointly measuring structural alignment, behavioral completeness, and overall visual fidelity. We use VISTA to assess four agent systems drawn from two model families and two harnesses, finding that visual fidelity and functional correctness are partially decoupled across both input conditions and agents, and that agent editing style varies sharply but is largely orthogonal to task quality. VISTA establishes a rigorous and reproducible foundation for advancing agent-based software engineering research. Code is available at https://github.com/kaboider/VISTA_Bench.
Authors: Jessica Wenninger, Gabriel Skantze
Abstract: Meaningful human-robot interaction (HRI) requires a robot to continuously assess user engagement through persistent user tracking. However, state-of-the-art Multi-Object Tracking models are heavily optimized for surveillance or autonomous driving. A social robot faces distinct egocentric challenges, such as humans moving in unpredictable nonlinear patterns, obstructing each other, or leaving and reentering the scene. These dynamics trigger frequent identity switches (IDSW), causing the robot to lose its footing mid-conversation. To address this, we introduce a focused, custom-annotated egocentric dataset collected via the Furhat robot. We present a systematic evaluation isolating detection errors from tracking logic, comparing face versus body tracking, and assessing the impact of extended memory and appearance re-identification (ReID). Results indicate that increasing temporal memory mitigates prolonged occlusions but fails on complex dynamic events. Integrating ReID resolves complex switches but exhibits opposing effects: it substantially improves body tracking stability, yet causes facial IDSW to spike due to profile angle sensitivity. Ultimately, our optimized pipeline reduces IDSW by 49% compared to a standard tracking-by-detection baseline, effectively mitigating interaction breakdowns. As standard benchmarks lack dense, close-quarter occlusions, this work highlights the critical need for natively captured social dynamics to truly validate HRI perception models.
Authors: Daniel Soliman
Abstract: AI governance for medical imaging is formalizing: the 2026 ACR-SIIM Practice Parameter recommends local acceptance testing and ongoing drift monitoring, and the ACR Assess-AI registry monitors AI outputs using DICOM metadata for context. We argue that a necessary, currently unmonitored layer sits beneath output metrics: whether incoming studies remain within the acquisition envelope a model was validated on. Using a LUNA16-trained MONAI RetinaNet lung-nodule detector, we test whether acquisition state behaves as a structured, measurable variable. On real paired CT differing only in reconstruction kernel (NLST B30f vs B80f), kernel alone shifted AI-measured diameter and flipped a Fleischner size category in 5.2% (8 of 155) of nodules at fixed patient and acquisition, while detection confidence was unchanged (Wilcoxon p=0.22). Under controlled LIDC-IDRI perturbations the effects dissociated by axis: the noise axis degraded detection confidence (p=5.9e-32, concentrated in nodules under 6 mm) but not measurement, while the frequency/kernel axis corrupted measurement (p=8.6e-13) but not detection. A 4-feature pixel fingerprint recovered reconstruction identity (patient-level AUC about 0.95 on real CT, 0.995 on a QIBA phantom) where the ConvolutionKernel DICOM tag was uninformative (identical labels across reconstructions). The kernel axis transported across four manufacturers (leave-one-vendor-out AUC 0.94-0.98, matching the within-vendor ceiling). Acquisition state thus maps to distinct AI failure modes, frequency content to measurement reliability and noise to detection sensitivity, and is not recoverable from metadata. Acquisition-aware, input-side validation is the missing layer for the acceptance-testing and drift-monitoring requirements now entering imaging-AI accreditation.
Authors: Jisang Han, Seonghu Jeon, Jaewoo Jung, Ren\'e Zurbr\"ugg, Honggyu An, Tifanny Portela, Marco Hutter, Marc Pollefeys, Seungryong Kim, Sunghwan Hong
Abstract: Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physical world. Recent vision-language-action models (VLAs) and video world-action models (WAMs) inherit strong semantic or temporal priors from large-scale foundation models, but they still operate primarily on 2D image frames or 2D-derived latent spaces, leaving implicit the 3D geometry required for contact-rich manipulation. We propose the Geometric Action Model (GAM), a language-conditioned manipulation policy that directly repurposes a pretrained geometric foundation model (GFM) as a shared substrate for perception, temporal prediction, and action decoding. GAM splits the GFM at an intermediate layer: the shallow layers serve as an observation encoder, and a causal future predictor inserted at the split layer forecasts future latent tokens conditioned on language, proprioception, and action history. The predicted future tokens are then routed through the remaining GFM blocks for feature propagation and decoding, allowing a single backbone to produce both future geometry and actions. This design equips the GFM with language-conditioned temporal world modeling through minimal architectural modification while preserving its rich geometric priors. Across a broad suite of simulation and real-robot manipulation benchmarks, GAM is more accurate, more robust, faster, and lighter than current foundation-model-scale baselines.
Authors: Wei-Cheng Tseng, Gashon Hussein, Yuzhu Dong, Allen Z. Ren, Lucy X. Shi, XuDong Wang, Sergey Levine, Zhaoshuo Li, Jinwei Gu, Florian Shkurti, Ming-Yu Liu, Quan Vuong
Abstract: Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world models offer a scalable alternative by simulating policy rollouts. Autoregressive rollouts accumulate compounding errors, observations across multiple camera views must remain mutually consistent, and the evaluator must generalize to policies whose behaviors lie outside the training distribution. We address these challenges with SC3-Eval, a self-consistent video generation recipe that adapts a pre-trained video foundation model into an accurate policy evaluator by enforcing three complementary forms of consistency. First, forward-inverse dynamics consistency jointly trains the model to predict frames from actions and to recover actions from frames, anchoring generated rollouts to a physically plausible action manifold and counteracting the drift a forward-only model cannot penalize. Second, cross-view consistency trains the model to inpaint each camera view from the other, keeping the multi-camera observation coherent over long rollouts without any explicit memory mechanism. Third, test-time consistency reuses the inverse dynamics mode at inference as a per-action-chunk uncertainty signal that terminates rollouts whose generated frames drift away from the requested actions. We also demonstrate SC3-Eval rollouts reproduce the failure modes that policies exhibit in real-world rollouts, supporting fine-grained diagnostic comparison rather than aggregate ranking alone. Across seven real-world vision-language-action policies, SC3-Eval attains a closed-loop Pearson correlation of $0.929$ and MMRV of $0.119$, outperforming three strong prior video-model-based baselines, and generalizes to new tasks.
Authors: Ling Chen, Ruinan Jin, Jun Luo, Hanliang Chen, Quirin Strotzer, Rongkai Yan, Yuan Xue, Luciano Prevedello, Dufan Wu
Abstract: Automated radiology report generation (RRG) has gained increasing attention because it can reduce the heavy workload of clinical report writing. However, most existing methods mainly optimize for natural language generation (NLG) metrics that focus on language fluency, while providing little control over clinically important factors such as precision and recall. As consequence, generated reports may be fluent but not well aligned with different clinical needs. To address this challenge, we propose a reinforcement learning framework for precision recall controllable RRG, where a control parameter explicitly adjusts the trade-off between clinical precision and recall during inference. This design allows the model to flexibly generate reports according to different clinical requirements. To ensure clinical correctness, we introduce a clinical reward into the training objective, which helps improve clinical efficacy (CE) beyond standard language-based optimization. In addition, we apply a group-relative training strategy that normalizes rewards within each training group, reducing reward variance and improving training stability. Extensive experiments on the MIMIC-CXR dataset show that our method consistently outperforms state-of-the-art approaches in both NLG and CE evaluation metrics, while providing reliable control over the CE precision recall trade-off.
Authors: Soyeon Kim, Kyowoon Lee, Jaesik Choi
Abstract: Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attributing model predictions to input features by integrating gradients along a path from a baseline to the input. However, the choice of the attribution path largely affects the quality of explanations, and existing approaches rely on fixed or hand-crafted paths that often produce noisy or distorted attributions. To address this limitation, we propose Diffusion Integrated Gradients (DiffIG), a novel method that reformulates path generation as a conditional generative modeling problem. DiffIG first trains a diffusion model to learn a distribution over paths generated from a Stick-Breaking Process, then employs guided sampling to embed user guidance during the sampling procedure. We demonstrate that DiffIG quantitatively matches or outperforms existing path-based methods, achieving perceptually aligned explanations. This work introduces a new generative perspective for flexible, inference-time controllable Explainable Artificial Intelligence (XAI) methods.
Authors: Yixin Gao, Xiaohan Pan, Lin Liu, Xin Li, Zhibo Chen, Qi Tian
Abstract: Recent generative video compression methods leverage powerful generative priors to achieve perceptually pleasing reconstructions. However, most existing approaches require additional training to adapt generative models to produce realistic reconstructions from compact representations. In this paper, we propose ZeroGVC, a zero-shot generative video compression framework that leverages pretrained autoregressive diffusion priors for low-delay video reconstruction. ZeroGVC encodes the first frame of each group of pictures (GOP) with an image codec and represents subsequent P-frames through Codebook-Guided Autoregressive Latent Compression. This design is motivated by our observation that the compression scheme of denoising diffusion codebook models is effective in few-step consistency sampling. By selecting compact combinations of reproducible codebook noise vectors, ZeroGVC steers the latent denoising trajectory toward the target P-frame while allowing the decoder to reproduce the same trajectory in only a few denoising steps. In addition, we design an optional bidirectional reference mode that mitigates error propagation by leveraging the next I-frame context without introducing any additional bitrate overhead. Extensive experiments on standard video compression benchmarks demonstrate that ZeroGVC achieves superior perceptual reconstruction quality at ultra-low bitrates without any additional training.