VQA
-
EVADE: Evidence-Verified Agentic Diagnosis with Escape
2026-08-19 11:51:24Mohaimenul Azam Khan Raiaan, Nur Mohammad FahadAbstract
Medical vision-language models (VLMs) can achieve high accuracy but remain unreliable: they are systematically overconfident, benefit little from test-time reasoning, and lack the ability to reliably calibrate trust in their own responses. We introduce EVADE (Evidence-Verified Agentic Diagnosis with Escape), an inferential, non-training method that enhances the safety of deploying a single frozen VLM. EVADE responds and, when uncertain, localises the region most diagnostically relevant, re-answers on a zoomed view, and commits only when both the entire image and the zoomed view responses agree; otherwise, it abstains. To directly address verification hallucination in single-model self-checking, our main idea is to verify gate consistency across different image views rather than re-reading the model's own text. Experimental evaluation on VQA-RAD, SLAKE, and PathVQA using Qwen2.5-VL-7B reports that EVADE is the only method that simultaneously improves both calibration and selective risk while maintaining accuracy, reducing expected calibration error (ECE) by up to 45% compared to zero-shot. Chain-of-thought, self-consistency, and self-verification all fail at least one axis. A grounding analysis reports that self-proposed regions perform better at diagnostic structure localisation than centres or random crops. However, a 7B VLM cannot use this localisation to revise answers. Therefore, reliability gains come from the consistency gate and calibrated abstention.
Abstract (translated)
URL
https://arxiv.org/abs/2608.18833
PDF
-
CamWorldQA: Perceptual Quality Assessment of Camera-Controlled World Video Generation
2026-08-19 09:10:02Yunhe Li, Likun Wu, Sijing Wu, Xinyu Tian, Huiyu Duan, Yixuan Gao, Yunhao Li, Guangtao ZhaiAbstract
Recent advances in generative video models have enabled camera-controlled world video generation, allowing models to synthesize videos under user-defined camera trajectories. However, existing video quality assessment (VQA) methods are mainly developed for natural videos and fail to capture the unique perceptual characteristics of camera-controlled generation, such as viewpoint consistency, motion coherence, and content preservation. In this work, we introduce CamWorldQA, the first benchmark for perceptual quality assessment of camera-controlled world video generation. CamWorldQA contains 720 generated videos produced by 6 representative generation methods from 20 diverse source videos under 6 camera trajectories, where each video is annotated with a human-rated perceptual quality score through subjective experiments. Furthermore, we propose CWQA, a no-reference quality assessment network with three complementary branches that extract spatial features, temporal motion features and optical flow features to jointly predict quality scores. Extensive experiments demonstrate that CWQA achieves superior performance over existing quality assessment methods on the CamWorldQA dataset.
Abstract (translated)
URL
https://arxiv.org/abs/2608.18710
PDF
-
PerFact: Perception-Derived Fact Prompting for 3D Brain MRI Report Generation
2026-08-18 15:47:45Jianyu Sun, Zhenxuan Zhang, Guang Yang, Peter J. LallyAbstract
Radiology report generation has matured almost entirely on 2D chest radiographs, where the default route to better reports is a larger backbone or a pre-training one on medical data. We revisit that assumption on 3D multi-sequence brain MRI, a volumetric multi-disease regime, and find that the model is not the lever. Zero-shot medical and radiology vision-language models transfer poorly to brain MRI, with chest radiograph specialists failing most conspicuously, and five backbones fine-tuned identically across three model families and an order of magnitude in scale differ only marginally. What determines the quality of the report is the information injected into the prompt. We delegate perception to upstream 3D segmentation and classification, serialize their outputs into a structured fact sentence, and prompt a LoRA-adapted vision-language model with it; we call this \textbf{PerFact}. In a controlled study that fixes the backbone, data split, target reports, and adaptation while varying only the injected grounding, perception-derived facts outperform retrieved prior reports, retrieval becomes redundant once facts are present, and end-to-end predicted facts remain effective without any ground-truth annotation at inference. The residual gap between predicted and oracle facts is explained by the granularity of the facts rather than by the generator. Closed-ended visual question answering comes at no measurable cost to report quality, though the grounding source has little effect on it. On 3D brain MRI, grounding information, not model choice, is the dominant controllable factor in report quality.
Abstract (translated)
URL
https://arxiv.org/abs/2608.17926
PDF
-
Counterfactual Anatomy-guided Spatial-Temporal Decoding for Annotation-Free Hallucination Mitigation in Medical VLMs
2026-08-18 06:45:08Yifan Lu, Adinath Dukre, Abhijit Das, Ziyun Zou, Haolin Yang, Yutong Xie, Imran RazzakAbstract
Medical vision-language models (Med-VLMs) have demonstrated strong performance on medical visual question answering, yet they remain prone to hallucination, generating clinically unsupported statements that are insufficiently grounded in image evidence. Mitigation methods applied during decoding offer a practical solution, but they typically lack anatomical awareness or rely heavily on ground truth annotations, which limits their applicability. We propose Counterfactual Anatomy-guided Spatial-Temporal decoding (CAST), a framework that operates entirely during inference and requires no manual annotations for anatomically grounded hallucination mitigation. CAST automatically discovers anatomical regions relevant to the given query through broad medical segmentation. It then selects a compact, causally informative area using counterfactual intervention based on the drop in answer likelihood under occlusion. Guided by this chosen region, CAST performs a unified contrastive decoding process, combining classifier-free guidance to correct spatial attention with stepwise temporal contrast to regulate generation dynamics. Experiments on the SLAKE and MIMIC-CXR datasets across three Med-VLMs demonstrate that CAST consistently outperforms strong baselines and surpasses decoding strategies reliant on ground truth. Our results indicate that compact, automatically selected regions provide highly effective contrastive guidance without expert annotations, offering a practical and generalizable solution for improving spatial grounding and reducing hallucinations. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.17427
PDF
-
PROBE: Manipulation-Grounded Visual Question Answering with VLM Agents
2026-08-17 21:03:31Vineet Bhat, Siyi Chen, Alex Zook, Xuning Yang, Stan Birchfield, Valts Blukis, Jonathan TremblayAbstract
Vision-language Models (VLMs) excel at 2D grounding, spatial reasoning and agentic tool-based planning in static scenes. However, consider asking a home robot "Is my medication still in the cabinet?" The answer may be physically hidden behind a row of containers that must first be moved aside. Answering such questions in real-world cluttered environments requires reasoning in dynamic scenes: distractors must be manipulated to reveal occluded objects, and each action changes the scene the model must reason over. We formalize this setting as Manipulation-Grounded Visual Question Answering (MG-VQA) and introduce PROBE, a framework for benchmarking and finetuning VLM agents on such tasks. We first develop PROBE-Sim, a high-fidelity tabletop simulator with everyday objects and a robot manipulator equipped with grasping and pushing tools. PROBE-Sim is used to create PROBE-Bench: an evaluation suite of 150 tasks across 6 question types on cluttered tabletop scenes, where a VLM perceives, picks up or pushes objects before answering. We observe consistent trend across all frontier VLMs: agentic tool-based methods outperform their perception-only baselines (8.0% on average) across all task types. We further design PROBE-Agent, a finetuning recipe to distill successful trajectories from a powerful teacher foundation model to a smaller open-weight model using a mixed data recipe that encourages manipulation-efficient question answering. PROBE Agent finetuned models outperform their off-the-shelf agent baseline (11.5% on average) and demonstrate positive transfer to unseen objects and a held-out task. We validate sim-to-real transfer by deploying PROBE-Agent finetuned policies in real-world tabletop environments.
Abstract (translated)
URL
https://arxiv.org/abs/2608.17129
PDF
-
The 10th AI City Challenge
2026-08-17 18:42:49Zheng Tang, Shuo Wang, David C. Anastasiu, Ming-Ching Chang, Anuj Sharma, Quan Kong, Munkhjargal Gochoo, Jun-Wei Hsieh, Tomasz Kornuta, Zhedong Zheng, Renran Tian, Judah Goldfeder, Fulgencio Navarro, Yuxing Wang, Yizhou Wang, Sameer Satish Pusegaonkar, Anqi Li, Nalin Dadhich, Ridham Kachhadiya, Dhanishtha Patil, Haoquan Liang, Jiajun Li, Han Zhang, Yilin Zhao, Zaid Pervaiz Bhat, Shuyu Yang, Ashutosh Kumar, Rong Wang, Rafael Martin Nieto, Peter Christiansen, Ahmed Abduljawad, Mohanrasu Shanmugam, Nadeem Shaik, Sujit Biswas, Xunlei Wu, Vidya Murali, Rama ChellappaAbstract
The 10th AI City Challenge, held with ECCV 2026, marks a decade of community benchmarking for intelligent transportation, smart cities, and physical AI. Since its 2017 start with vehicle detection, classification, and tracking, the challenge has grown into a broad benchmark suite for multi-camera perception, multimodal reasoning, synthetic-to-real learning, generative forecasting, and privacy-preserving evaluation. The 2026 edition continued this growth with 325 registered teams, up from 245 in 2025, and participation from 26 countries and regions, up from 15. Its six primary tracks cover multi-camera 3D perception, transportation safety captioning and VQA, traffic anomaly reasoning, text-based person anomaly search, generative traffic video forecasting, and cross-city object detection. Track 3 further includes two out-of-domain leaderboards, submitted as Tracks 7 and 8, for fisheye traffic-violation understanding and pedestrian situated-intent VQA. This paper summarizes the challenge setup, datasets, evaluation protocols, leaderboard results, and workshop papers. Across tracks, successful systems combine foundation models with geometric grounding, retrieval or reranking, synthetic-data design, domain adaptation, and controlled inference.
Abstract (translated)
URL
https://arxiv.org/abs/2608.17044
PDF
-
RISE: Roadside Infrastructure Sequence Understanding across 3D Tracking and Structured Vision-Language Reasoning
2026-08-17 12:22:15Yanbo Jiang, Haotian Zheng, Jiahao Wang, Hanxiao Ren, Yitao Xu, Yining Xing, Zehong Ke, Hao Cheng, Yiqian Tu, Jinhao Li, Zhiyuan Xuan, Fang Zhang, Jianqiang WangAbstract
We present RISE (Roadside Infrastructure Sequence Understanding and Evaluation), a framework spanning metric 3D tracking and structured vision-language reasoning in roadside sequences. For metric tracking, our image-only method combines SAM3 video identities with calibration-guided mask agreement for multi-view identity association, recovering persistent 3D tracks without LiDAR or task-specific 3D training. Its calibration-conditioned geometry allows the procedure to be instantiated at different calibrated multi-camera intersections without layout-specific retraining. On 20 human-reviewed clips from six intersections, the generated tracks achieve 66.9 MOTA within the defined multi-view evaluation scope. For structured vision-language reasoning, a human-reviewed MLLM pipeline mines high-value clips and uses a constrained full-context Oracle to construct bbox-grounded predictive QA without exposing future evidence to evaluated models. The resulting RISE-VQA dataset contains 33,910 QA pairs from 557 clips across 16 intersections and 61 roadside views. Its intersection-held-out RISE-Bench evaluates semantic choices, coordinates, future boxes, and interaction sets with deterministic task-specific metrics. Experiments show consistent benefits from domain adaptation and generally from temporal context, while revealing persistent challenges in spatial grounding, future localization, and interaction reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2608.16480
PDF
-
Boosting Knowledge-based Visual Question Answering with Structured Context Reasoning
2026-08-17 06:33:55Qiyou Liu, Yong Zhang, Jianjie Luo, Zhenguo Yang, Yi YuAbstract
Knowledge-based Visual Question Answering aims to answer questions about an image by integrating external knowledge with visual and textual information. Recent approaches often rely on in-context learning to prompt Large Language Models (LLMs) with multimodal context in a zero-shot or few-shot manner. However, we observe that directly concatenating heterogeneous visual descriptions and retrieved knowledge into long, unstructured prompts often degrades reasoning performance, due to both excessive irrelevant context and the lack of explicit relational structure. In this paper, we propose an LLM-based Structured Context Reasoning (SCoRe) framework that infers both explicit and implicit relationships for prediction. SCoRe consists of three stages: Context Acquisition, which generates diverse visual notes and retrieves explicit knowledge via an efficient two-stage multimodal retrieval strategy; Context Selection, which filters relevant visual, explicit, and implicit knowledge using LLM-guided selection; and Context Compression, which performs Relational Logic Distillation (RLD) to transform raw text into explicit entity-relation triplets. These relational triplets serve as a concise and structured prompt for final answer prediction. Extensive experiments on the OK-VQA and A-OKVQA benchmarks demonstrate that SCoRe consistently outperforms state-of-the-art methods.
Abstract (translated)
URL
https://arxiv.org/abs/2608.21431
PDF
-
TractoGraphVLM: A Unified Vision-Language Framework for White Matter Tractography
2026-08-16 16:14:48Gurucharan Marthi Krishna Kumar, Janine Dale Mendola, Amir ShmuelAbstract
Vision language models have transformed 2D medical imaging, yet extending them to 3D white matter tractography remains challenging due to the complex topology of fiber bundles. We introduce TractoGraphVLM, a unified framework for four tasks, bundle classification, text-to-tract retrieval, anatomical captioning, and visual question answering, built on a shared GPS architecture, training procedure, and read-out design. Fiber bundles are represented as streamline graphs whose nodes encode 3D position and tangent orientation. A General, Powerful, Scalable (GPS) graph transformer produces bundle embeddings aligned with a frozen BiomedBERT text encoder via contrastive learning, while a BioGPT decoder with visual prefix tokens generates captions and answers. A single shared encoder and decoder is trained jointly across all four tasks and evaluated from one checkpoint. Trained on HCP Young Adult subjects, TractoGraphVLM achieves 91.8% bundle classification accuracy, 84.7% retrieval R@1, BLEU-4=20.1, ROUGE-L=66.8, and 66.4% VQA accuracy on a held-out test set. The same checkpoints transfer zero-shot to HCP Aging subjects, with a modest drop on discriminative tasks and a larger drop on generative tasks, showing robustness to age and acquisition shift. Language supervision yields richer representations than label-only training, recovering structure like hemisphere and fiber family, carried by captions but never given as a label. Swapping only the visual encoder, graphs preserving fiber orientation outperform volumetric baselines, with GPS giving the best balance. Generative metrics measure consistency with a structured knowledge base rather than independent clinical text; even so, TractoGraphVLM shows that classifying, retrieving, describing, and answering questions about a white matter bundle can be served by one jointly trained model that learns transferable neuroanatomy from language alone.
Abstract (translated)
URL
https://arxiv.org/abs/2608.18166
PDF
-
AlignJEPA: Predictive Vision-Language Alignment for Remote Sensing Foundation Models
2026-08-16 00:27:07Md Aminur Hossain, Omkumar Vaghasiya, Rajeev Ranjan Dwivedi, Vinod Kurmi, Biplab BanerjeeAbstract
Remote sensing (RS) foundation models provide transferable Earth observation representations across sensors, resolutions, and geographies, yet most remain weakly aligned with natural language, limiting natural-language archive search, image-text retrieval, and question-conditioned analysis. We propose AlignJEPA, a JEPA-inspired predictive vision-language alignment framework for remote sensing foundation models. AlignJEPA uses a pretrained AnySat visual encoder and a RemoteCLIP text encoder while training only a lightweight predictive alignment network. Instead of relying on global image--text contrastive alignment alone, the framework predicts remote-sensing text embeddings from masked visual foundation-model tokens. Its mask-aware multi-scale predictive aligner aggregates visible tokens at fine, regional, and global scales, jointly models them with a cross-scale Transformer, and projects the resulting representation into the text space using learned query pooling. Training combines semantic prediction with bidirectional contrastive retrieval. We train and evaluate AlignJEPA on this http URL for natural-language Sentinel retrieval, evaluate cross-dataset adaptation on RSICD, and use RSVQA only as a closed-set representation probe. AlignJEPA provides a parameter-efficient route for aligning Earth observation foundation models with language.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15456
PDF
-
Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs
2026-08-15 07:04:53Yihang Du, Juhao Liang, Zhengzhao Lai, Siyu Li, Yan HuAbstract
Multimodal large language models (MLLMs) exhibit substantial performance degradation in non-English visual reasoning, despite the strong multilingual competence of their text-only backbones. While mechanistic evidence from text-only models suggests that non-English inputs are routed through an English-centric latent space, the multimodal implications of this phenomenon remain unexplored. Through rigorous mechanistic analysis, we identify the \textbf{Ghost Anchor} phenomenon: a temporal modality asynchrony where linguistic translation to the English semantic manifold completes in early layers, while visual semanticization remains immature. Consequently, visual signals are physically present yet functionally invisible during the early alignment window. To rectify this, we propose \textbf{ANCHOR}, a training framework employing Proactive Visual Anchoring (PVA) to accelerate early visual semantic emergence, ensuring visual representations proactively guide linguistic translation. Mechanistic interventions confirm that ANCHOR successfully restores the causal influence of visual signals during early translation. Furthermore, extensive experiments on XMMMU, MaXM, and CVQA demonstrate that ANCHOR consistently outperforms standard baselines, achieving robust visual reasoning across both fine-tuned and zero-shot languages.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15085
PDF
-
GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG
2026-08-15 06:02:23Zafar Ali, Asad Khan, Aalia Malik, Pavlos KefalasAbstract
Multimodal retrieval-augmented generation (RAG) systems often rely on long unstructured contexts or aggressively expanded evidence graphs, which can introduce noisy evidence, weaken multi-hop reasoning, and increase unsupported generation. We present GraphLoom, a reliability-calibrated multimodal knowledge-graph RAG framework for compact and faithful evidence routing. Given a question and its associated multimodal input, GraphLoom constructs an instance-level multimodal knowledge graph from grounded scene descriptions, extracted relational triples, and external commonsense knowledge. Instead of injecting all retrieved evidence into the generator, GraphLoom performs reliability-aware subgraph retrieval with bounded expansion and selectively routes high-utility evidence through hierarchical graph memory slots and joint graph-sequence attention in a frozen language model. To improve robustness in complex reasoning settings, GraphLoom further combines interleaved retrieval with budgeted corrective retrieval, enabling adaptive multi-hop evidence refinement under noisy retrieval conditions. We evaluate GraphLoom on ScienceQA, MultiModalQA, and OK-VQA, including large distractor evidence pools that approximate noisy external knowledge retrieval. Experimental results show consistent gains in answer quality and evidence faithfulness over strong multimodal RAG, graph-retrieval, and open-source vision-language baselines, with improved retrieval quality on MultiModalQA and stable performance under noisy evidence pools. Additional analyses using MiniCheck-based verification, human evaluation, and latency profiling show that reliability-calibrated graph evidence routing provides an effective alternative to long-context multimodal evidence injection.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15056
PDF
-
What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering
2026-08-14 19:29:42Guanchen Wu, Jiayuan Ding, Subhabrata Mukherjee, Carl YangAbstract
Long-document visual question answering (VQA) over documents of tens to hundreds of pages mixing text, tables, charts, and figures typically follows retrieve-then-read pipelines. In our setting, the bottleneck shifts from retrieval recall to reranker-side evidence selection: on MMLongBench-Doc, BGE-M3 reaches Recall@20 = 0.86 but only F1@5 = 0.254, and even the visual retriever ColPali reaches only F1@5 = 0.332; a text-only rerank LLM seeing only raw snippets misses table, chart, and layout evidence even when the upstream retriever encoded images. We propose Trident, with two complementary components: Trident-R, a retriever-agnostic LLM reranker that converts each candidate into an LLM-readable semantic record, including a visual caption, section path, entity tags, multi-axis concept hits, and a text snippet, then performs a single adaptive-K rerank call; and Trident-S, a generation-side module that prompts the VLM under topical, entity, and structural lenses before synthesis. On two long-document datasets, the annotation+rerank protocol substantially improves retrieval F1 across five heterogeneous pools, with every reranked pool exceeding the strongest adaptive-K baseline PageIndex. An LLM rerank without the annotation barely changes first-hit ranking, indicating the lift comes from the structured annotation. Trident-S targets open-ended synthesis questions by design, adding up to 6.6 points in generation accuracy on these questions. The best Trident configuration is the strongest downstream QA pipeline in our evaluation, with rankings consistent across two LLM judges (kappa = 0.913).
Abstract (translated)
URL
https://arxiv.org/abs/2608.14841
PDF
-
Seeing Red, Thinking Bad: Color Bias in Vision Language Models
2026-08-14 13:14:58Kohsuke Ide, Ryousuke Yamada, Yoshihiro Fukuhara, Hirokatsu Kataoka, Yutaka SatohAbstract
Vision language models (VLMs) are increasingly used in industrial decision-making systems, such as recruitment support and recommendation. This motivates careful analysis of how VLMs process visual and textual information. In this work, we study how VLMs interpret text rendered as an image, and investigate the influence of visual styling biases. To this end, we introduce Stealth Visual Prompts, which subtly change visual styling of text, such as color and contrast, while preserving semantic content. Using these prompts, we systematically control the visual styling of words in text and measure their impact on the analysis performed by VLMs. We further analyze how such visual perturbations affect the latent representations of the vision encoder. From our experiments, we observed that coloring positive words in green consistently shifts sentiment predictions toward a positive direction. As a result, VLMs often fail to properly account for negative words present in the text. Our analysis suggests that this behavior is correlated with changes in the latent representations of the vision encoder induced by color variations. In addition, we show that reducing text--background contrast increases reliance on visually salient cues and leads to more incorrect Visual Question Answering (VQA) outputs. These results suggest that the visual styling of rendered text can guide VLMs' interpretation in ways that diverge from human semantic understanding. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.14286
PDF
-
A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images
2026-08-14 08:34:33Jennifer D'Souza, Fahad Ahmed, Cecilia Andrea Bustamante Andrade, Lina Frolova, Poorani Gnanasambandan, Dilshad Hussain, Muhammad Uzair Khan, Nkembeng Kevin Nkengfoa, Paul Praveen J., Fabio Priante, Sjoerd Franciscus van der Werf, Thomas Frederik Jan van RoedenAbstract
Scientific figures and tables encode essential experimental evidence, yet remain difficult for digital libraries and multimodal AI systems to retrieve and interpret. The ALD/E-ImageMiner benchmark and ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching Scientific Figures provide 1,951 figures from 205 publications, expert-annotated for classification, data table extraction, summarization, and visual question answering. In these companion proceedings, we present a forward-looking perspective on how the benchmark can guide future scientific-image challenges. We examine how its tasks probe capabilities from visual and quantitative reading to domain-grounded reasoning and evidential justification, and how Bloom-informed question design can support deeper scientific understanding. We propose "scientific conceptual understanding from images" as a long-term benchmark objective, with future directions including broader domains and figure types, contextual and cross-document synthesis, hypothesis evaluation, provenance, uncertainty, counterfactual grounding, and open-ended multimodal research. This perspective connects the ICDAR 2026 challenge to a broader agenda for machine-actionable scientific visual knowledge and verifiable multimodal scientific AI.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14075
PDF
-
CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification
2026-08-14 04:19:33Bingxin Yu, Xueli Wang, Jerry Zhou, Wenyan Wang, Li Wen, Lan Huang, Xin Feng, Fengfeng Zhou, Kewei LiAbstract
Ultrasound is the primary imaging modality for assessing thyroid nodules, and the ACR TI-RADS framework standardizes diagnosis through five ultrasound feature categories that are aggregated into five risk levels (TR1-TR5). Although widely adopted in clinical practice, most deep learning approaches focus on binary malignancy classification, while multi-class prediction and explicit utilization of feature-level supervision remain underexplored, largely due to limited annotated data. In this study, we introduce the STN dataset of 600 thyroid nodules with paired transverse and longitudinal ultrasound images, bounding box annotations, and complete labels for all five TI-RADS feature categories. Following the clinical decision process, we investigate how structured feature information can guide representation learning during training while requiring only images at inference. We demonstrate that text embeddings derived from standardized feature descriptions form a stable surrogate representation for TI-RADS risk levels. Based on this observation, we propose CMCNet, which aligns image embeddings to fixed textual embeddings via a Center-Margin Contrastive Loss that simultaneously promotes intra-class compactness and inter-class separation. Experimental results show that this embedding alignment strategy is more data-efficient and robust than direct multitask learning, and consistently outperforms InfoNCE, center loss, a strong multitask baseline, and a VQA-style multimodal model, particularly in imbalanced settings. The dataset is freely available at doi: https://doi.org/10.5281/zenodo.19125693 and the source code is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13939
PDF
-
When Is a Task Vector Enough? An Empirical Theory of Implicit Multimodal ICL
Abstract
Implicit multimodal in-context learning compresses demonstrations into internal interventions, ranging from static task vectors to query-conditioned transformations and attention routing. Despite their common goal, these methods differ substantially in how the intervention depends on the query and where it modifies the model, leaving unclear which additional complexity is necessary for a given task. We propose the Selection--Realization Hypothesis. It views demonstrations as inducing a compact family of internal changes from which the query selects, while the model's computation constrains how the selected change can be implemented. We evaluate this account using controlled multimodal tasks in which query dependence varies without changing the underlying task primitives or prompt format. By contrasting correct demonstrations with matched counterfactuals, we measure the structure of explicit M-ICL and test whether it predicts intervention behavior. We find that the success of a static task vector is closely tied to how much of the demonstration-induced change is shared across queries. Additional intervention complexity becomes useful when explicit M-ICL contains query-specific or distributed structure that a local additive shift cannot recover. These relationships extend to natural VQA benchmarks and support cost-aware method selection without access to test performance. Our results provide a unified empirical theory of when demonstrations can be compressed into a task vector and when a more expressive intervention is warranted.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13385
PDF
-
Reasoning for Social Audio-Visual Question Answering: Where Do We Stand?
2026-08-13 13:44:35Koen P. de Vries, Xavier Alameda-Pineda, Estefan\'ia Talavera, St\'ephane Lathuili\`ereAbstract
Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought (CoT) reasoning has become the dominant approach, with HumanOmniV2 and its IntentBench benchmark as a prominent reference point. In this context, we report three findings. First, IntentBench is highly noisy: $\sim$7% of questions are broken and $\sim$23% are trivially answerable without the video input. We remove the affected questions and release Intentbench-Prime. Second, current reasoning approaches are expensive and surprisingly ineffective. A simple Vanilla SFT baseline matches or outperforms existing reasoning methods across three benchmarks at a fraction of the cost, establishing it as an essential baseline for evaluating novel fine-tuning techniques. Third, our analysis reveals that substantial priors can be learned solely from the text modality and that using a textual caption instead of the video yields performance on par with Vanilla SFT. These surprising findings reveal the limitations of current MLLMs when it comes to social understanding. IntentBench-Prime, Vanilla SFT model, and code are publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13239
PDF
-
UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations
2026-08-13 10:00:27Peng Li, Qianqian Xu, Shilong Bao, Yangbangyan Jiang, Qingming HuangAbstract
Traffic video understanding has become an important problem in intelligent transportation, as road videos provide direct evidence for accidents, violations, and interactions between vehicles and vulnerable road users. A useful system should explain how a traffic event develops, why it happens, and when the relevant interaction occurs, yet this remains difficult for multimodal large language models (MLLMs) because traffic videos contain sparse events and varied viewpoints. We introduce UniTraffic-Agent, the MR-CAS solution for Track~3 of the 10th AI City Challenge, which includes Traffic Anomaly Reasoning (TAR) and two out-of-domain evaluations: FETV for fisheye traffic events and PSI-VQA for pedestrian intention reasoning. UniTraffic-Agent follows an observe--reason--act--verify workflow that samples timestamped visual evidence, reasons over all questions from the same clip in one request, and converts responses through task-specific action adapters. On the official Public leaderboards, MR-CAS ranks 16th on TAR with a score of 0.5780, 2nd on FETV with 0.4884, and 4th on PSI-VQA with 64.4161. The code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13031
PDF
-
Polish Medical Visual Question Answering: Vision-Language Models Underutilize Visual Evidence
2026-08-13 08:07:22Jakub Pokrywka, {\L}ukasz Grzybowski, Antoni Lasik, Marek Kubis, Jeremi Ignacy Kaczmarek, Wojciech KusaAbstract
We introduce a Polish-language medical visual question answering (VQA) benchmark, built from Polish Board Certification Examination questions for licensed physicians and dentists pursuing specialist certification. The benchmark comprises image-containing questions spanning diverse medical specialties and visual domains, together with a text-only question answering (QA) control set. We evaluate Polish-oriented, general-purpose open-weight, and commercial vision-language models. The task remains challenging: the best model achieves 79.0\% accuracy on the full VQA set, and only GPT-5.6 surpasses the approximate human reference on the subset with available candidate responses; all other evaluated models perform worse than humans. To assess visual grounding, we compare complete inputs with configurations omitting the image, the question, or both, and categorize questions by image importance. Models derive more useful information from the question text than from the image and perform worse on image-dominant questions. Across both QA and VQA, they nevertheless achieve above-chance accuracy from the answer choices alone, showing that non-trivial performance can persist even when key task components are missing.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12928
PDF
