VQA
-
Pay More Attention To Text In High-Resolution MLLMs
2026-09-20 09:30:05Zhongkuan Mao, Wenzhuo Zhao, Xianjie Liu, Yidong Wang, Zhao Gao, Ronghao Xian, Yao Jiang, Yi Zhang, Liangjian Wen, Keren FuAbstract
Failures of high-resolution MLLMs are commonly attributed to a visual problem, motivating zooming, cropping, and related visual interventions to recover fine-grained evidence or suppress interference. Yet recent studies suggest that relevant visual evidence is already encoded in intermediate representations, indicating that visual-side improvements alone insufficient. This raises a natural question: does the remaining bottleneck lie in the text that guides visual search? We identify a previously overlooked linguistic bottleneck: questions formulated for answering do not necessarily specify the visual evidence required for localization. To address this mismatch, we introduce EviSpec, a training-free compiler that derives complementary evidence specifications while preserving the original question for final reasoning. We further validate it through matched-control experiments that isolate the roles of evidence specification and localization. With the search budget fixed, structured evidence specifications yield an 8.6% relative gain over generic requests. With evidence geometry matched, the evidence localized by EviSpec yields a 14.8% relative gain over random evidence. Together, these controls isolate the benefit of specifying what evidence to seek rather than merely expanding visual access. Across all five MLLMs, EviSpec consistently improves upon the corresponding baseline on each of the three benchmarks, yielding average relative gains of \textbf{10.4%, 8.8%, and 12.4%} on V\textsuperscript{*}Bench, HR-Bench-4K, and HR-Bench-8K, respectively. Beyond high-resolution reasoning, EviSpec also achieves state-of-the-art performance on VQA and hallucination-focused benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23495
PDF
-
QwenVLConnector: A Fast, Unified Medical VLM Chatbot for Fine-Grained Clinical Perception and Text Generation
2026-09-19 17:09:50Le Thien Phuc Nguyen, Thien Nguyen, Thanh-Huy Nguyen, Gia Minh Hoang, Anh Mai Vu, Ulas BagciAbstract
Most medical vision-language models (VLMs) excel at open-ended report generation and VQA but provide limited support for structured, fine-grained clinical perception within a unified interface. We present QwenVLConnector, a Qwen2.5-VL-based medical chatbot that unifies classification, multi-label classification, textualized detection, counting, regression, and free-form report generation under a single next-token objective. Our key component is a lightweight dense multi-layer Connector that aggregates low- and high-level visual features, aligns them through the pretrained vision Merger, and fuses them with the final visual representation without increasing sequence length. This design enriches visual tokens with complementary spatial and semantic cues while preserving efficiency. On FLARE-2D, QwenVLConnector improves detection F1 from 0.55 to 0.85, raises single-label classification from 0.37 to 0.51, and boosts report-generation GREEN by up to 18.3 points over the Qwen2.5-VL baseline. We further explore multimodal in-context learning for report generation, showing additional improvements without updating model parameters. Overall, QwenVLConnector offers a unified and efficient framework for combining structured medical perception with open-ended clinical text generation. Our code can be found at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23139
PDF
-
An Evolutionary Agentic Approach for Open-ended Image Quality Perception
2026-09-19 10:42:32Zhenchen Tang, Bo Peng, Zichuan Wang, Songlin Yang, Leilei Cao, Fengjie Zhu, Jing DongAbstract
Generative models are rapidly expanding image quality assessment (IQA) beyond traditional fidelity factors to emerging dimensions such as physical plausibility and text-rendering correctness. However, existing IQA models rely on fixed definitions and heavy supervision, making them difficult to extend to open-ended perceptual dimensions. We identify holistic bias as an important limitation: when scoring an unseen dimension, models reuse generic quality priors, leading to scoring errors and rank inversion. To address this, we propose PACE (Perceptual Agentic Collaborative Evolution), a training-free multi-agent framework that formulates open-ended IQA as explicit protocol construction. Given a target dimension, PACE uses collaborative agents to construct an evaluation protocol composed of verifiable Visual Question Answering (VQA) probes, grounding evaluation in concrete visual evidence rather than holistic impressions. The resulting protocol is calibrated using only four human-annotated images per dimension, while a dual-track scoring mechanism aligns model perception with human scoring scales. Across traditional IQA, structural fidelity, context-aware aesthetics, and newly defined open-ended dimensions, PACE consistently improves its MLLM backbone, achieving competitive performance across diverse IQA settings, and reduces the Holistic Override Rate (HOR) from 44.4\% to 8.6\%.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22942
PDF
-
Seeing is not Enough: Vision-Language Models Perceive Evidence but Fail to Act
2026-09-18 21:13:03Yuyang Dai, Bofei Huang, Hongbo Zhang, Haoran XieAbstract
Vision-language models (VLMs) perform strongly on visual question answering benchmarks, yet often make decisions that contradict visual evidence they have already identified correctly. We distinguish perceptual failure, where relevant evidence is not recognized, from process failure, where recognized evidence fails to constrain the final decision. We introduce VPAC-Bench, a benchmark spanning nine real-image process families, with each image annotated by its current activity stage and nearby stage transition. We also propose State-Relevance-Target (SRT), a family of structured process-prior interventions that requires models to connect visible evidence to the relevant process state before answering. Across multiple VLMs, process failure is widespread: models that correctly enumerate visual candidates still over-commit to a single answer in more than 95% of ambiguous cases. An explicit process-structured intervention reduces this rate to below 13% without degrading performance on unambiguous cases. However, the transfer of process priors is model-dependent, and generic SRT does not consistently outperform strong chain-of-thought baselines. When the relevant stage transition is known, boundary-aligned SRT substantially outperforms generic process prompting and all tested chain-of-thought baselines across assembly, physical state transition, navigation and traffic, and object-use affordance tasks. These results show that process priors are most useful when aligned with the scene's specific decision boundary, motivating boundary-aware prior selection for process-grounded visual reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22588
PDF
-
Beyond Exact Match: Task-Aware GRPO for Cross-Domain PCBA Visual Question Answering
2026-09-18 03:41:53Jia Li, Li Dai, Peng Jia, Zhenzhen Hu, Chee Seng Chan, Bingkun Bao, Richang HongAbstract
In automated Printed Circuit Board Assembly (PCBA) inspection, standards-guided decisions require systems to jointly reason over fine-grained visual cues, component semantics, and manufacturing knowledge. Although large vision-language models (VLMs) provide a promising foundation, their deployment is hindered by the domain shift between standards-derived samples and real-world production-line imagery, together with heterogeneous output spaces spanning choice-based and numerical counting tasks. To address these challenges, we propose a multimodal reasoning framework for cross-domain PCBA visual question answering. The framework converts standards-derived, real-world, and auxiliary PCB-domain data into a unified instruction format and constructs verified reasoning traces aligned with visual evidence, question semantics, candidate options, and ground-truth answers. We further introduce Task-Aware Group Relative Policy Optimization (GRPO), which moves beyond exact-match supervision by integrating multi-component semantic rewards for choice-based questions, distance-aware rewards for counting questions, and an auxiliary format reward for valid outputs. During inference, answer-option semantic consistency correction, self-consistency voting, and multi-model arbitration are combined to improve prediction robustness. The proposed system achieves an Overall Score of 83.24 on the official PCBA Standard-to-Real Grand Challenge leaderboard, demonstrating the effectiveness of task-aware reward design and robust inference for cross-domain PCBA visual question answering.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21276
PDF
-
DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering
2026-09-17 15:32:30Luca De Grandis (University of Modena and Reggio Emilia, Modena, Italy), Silvia Cappelletti (University of Modena and Reggio Emilia, Modena, Italy), William Raccagni (University of Modena and Reggio Emilia, Modena, Italy, University of Pisa, Pisa, Italy), Marcella Cornia (University of Modena and Reggio Emilia, Modena, Italy), Lorenzo Baraldi (University of Modena and Reggio Emilia, Modena, Italy), Rita Cucchiara (University of Modena and Reggio Emilia, Modena, Italy)Abstract
Answer grounding in document visual question answering remains an open challenge: most benchmarks lack grounding annotations or provide limited-quality labels, while constructing grounded datasets still requires costly manual effort. We introduce DocAttriBench (DAB), a large-scale benchmark for fine-grained, element-level source attribution in Document VQA, grounding answers to specific layout elements such as text blocks, tables, and images. To build DAB, we propose a Mask-based Perplexity-Derived Attribution method (MAPPET) that combines document layout and language modeling to identify the most informative element for each answer. MAPPET measures the increase in perplexity after masking candidate elements and attributes the answer to the element contributing most to model confidence. Applying MAPPET to multiple existing Document VQA datasets yields DAB, with 237k documents and 296k question-answer pairs with element-level grounding. We benchmark grounding-capable multimodal LLMs on DAB, evaluating answer accuracy, attribution accuracy, and overall answer quality. Results show that while larger models generally achieve higher answer accuracy, even the strongest models often fail to localize the supporting elements. DAB provides a scalable benchmark for developing grounded, verifiable, and trustworthy Document VQA models. Dataset and code are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.20574
PDF
-
SkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback
2026-09-17 14:20:45Ziqiao Shang, Ling-Yue Ge, Lan-Zhe GuoAbstract
External skills provide domain procedures without parameter updates, but existing methods often edit skills directly from failed rollouts without structured routing from an observed failure to an editable location; existing skill graphs also underuse semantic boundaries, object addresses, and topological dependencies for skill retrieval, targeted updating, and scoped validation. We introduce SkillAA (Skill Abductive Attribution), a structured skill-optimization framework for frozen language models. It represents skill applicability, execution, and composition in a unified graph, allowing the same structure to support skill selection, attribution-guided repair, and update validation. SkillAA contrasts successful and failed executions to route candidate repairs to specific graph objects, updates only the selected local structure, and uses Local and Big Gates to screen candidate changes before commitment. With gpt-5.6-sol, SkillAA reaches 81.5%, 66.7%, and 91.2% on SearchQA, LiveMath, and DocVQA, respectively, and attains the highest observed mean in every main setting. These results support the utility of attribution-guided graph editing and graph-scoped validation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.20455
PDF
-
A Multi-Modal Generative Model for Tomato Disease Leaves Understanding
2026-09-17 01:25:57Khang Nguyen Quoc, Minh-Phuoc Tran, Gia-Han Truong, Luyl-Da QuachAbstract
Artificial intelligence for plant disease analysis has advanced from task-specific classifiers to multi-modal models capable of jointly interpreting visual and textual information. However, practical deployment in precision agriculture remains limited because most existing approaches treat disease understanding as isolated prediction tasks, failing to capture the complementary relationships among symptom recognition, severity assessment, and question-driven diagnostic reasoning. In tomato pathology, accurate interpretation of diseased leaves requires more than label prediction; it demands integrating visual symptoms with semantic context to support a comprehensive and explainable understanding. Here, we present SOLAR, a multimodal generative model that understands tomato disease spanning six question-answering tasks. SOLAR learns to align visual features with task-aware language representations by Fusion Expert module based on mixture-of-expert, enabling it to generate contextually relevant answers across diverse diagnostic tasks. By formulating tomato disease analysis as a generative Visual Question Answering (VQA) task, SOLAR provides a flexible framework that supports multi-task inference within a single model while improving performance and cross-task knowledge sharing. We evaluate SOLAR on $41,677$ images, including $216,209$ Question-Answering (QA) pairs to understand tomato leaf disease under both closed and open-ended QA settings. Experimental results show that SOLAR consistently outperforms state-of-the-art vision-only, vision-language, and task-specific models across all tasks, demonstrating superior accuracy, robustness, and multimodal reasoning. These findings highlight the potential of generative multimodal modeling as an effective direction for understanding of plant disease. The code for this study is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.19555
PDF
-
Sim-to-Real Traffic Scene Understanding by Decoupling Semantics from Caption Generation with V-JEPA
2026-09-16 12:21:06Nguyen Hoai Thuong Bui, Thanh Nguyen Vo, Trinh Tra Giang Nguyen, Ha Duc BuiAbstract
Track 2 of the AI City Challenge 2026 requires both visual question answering (VQA) and traffic event description generation under a challenging synthetic-to real domain shift. Existing vision-language approaches often entangle semantic understanding with language generation, making them susceptible to hallucination and inconsistent reasoning across event phases. In this work, we propose a decoupled semantic understanding framework that first resolves predefined traffic questions into structured semantic facts and subsequently uses these facts to guide caption generation. A frozen V-JEPA encoder extracts predictive scene representations, while a lightweight Llama-based predictor produces answers for VQA queries. To improve reliability, we introduce a training-free structured refinement mechanism that exploits statistical priors, inter-question relationships, and temporal event consistency to correct prediction errors. The refined semantic facts are then provided to Qwen3-VL-8B to generate pedestrian and vehicle descriptions for each traffic event. Experimental results on the official 2026 AI City Challenge Track 2 benchmark show that the proposed method achieves 87.09% VQA accuracy and an overall S2 score of 60.0853, ranking first among all participating teams. These results demonstrate that predictive world representations combined with structured semantic refinement enable more accurate and reliable traffic understanding, leading to higher-quality lan guage generation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.18562
PDF
-
Understanding Dynamic Scenes at Gigapixel Scale: Wide-Area Spatio-Temporal Perception from UAVs
2026-09-16 06:41:36Yuhang Zhu, Meiyi Zhu, Yunkai Dang, Zhangnan Li, Yuxuan Wang, Wenbin Li, Hongbing PanAbstract
UAV-borne imaging has advanced from megapixel to gigapixel sensors, shifting aerial perception from recognizing individual targets to understanding entire dynamic scenes. We characterize this demand as Wide-area Spatio-temporal Scene Understanding (WSTU), which requires wide-area coverage, per-target resolution, and temporal continuity at once, a combination existing datasets lack. To fill this gap, we introduce an ultra-High-resolution (12768x9564) Airborne Remote-sensing Dataset (HARD) annotated at three levels for object detection, multi-object tracking, and scene-level visual question answering. Ultra-high-resolution imagery raises per-frame processing time to seconds. At that scale latency can no longer be ignored in evaluation. Thus, we propose a latency-aware metric for multi-object tracking called streaming-HOTA (s-HOTA). Extensive baseline experiments show how ultra-high-resolution processing reshapes each task. For detection, the end-to-end pipeline affects accuracy and speed as much as the detector itself does. For tracking, high latency charges the association axis far more unevenly than the detection axis, and association is where pipelines diverge. As a result, the pipeline that performs best offline can lose its lead under s-HOTA. For VQA, vision-language models remain weak at cross-frame identity binding and cannot transfer their single-frame gains to it. Together these findings show that the baselines we evaluate fall short of WSTU. HARD provides the data and the systematic baselines to advance it.
Abstract (translated)
URL
https://arxiv.org/abs/2609.18210
PDF
-
EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing
2026-09-16 00:25:31Sihao Ding, Santosh Vasa, Aditi Ramadwar, Thomas MonningerAbstract
Vision-Language Models (VLMs) can produce Natural Language Explanations (NLEs) that sound plausible yet remain inconsistent with the visual evidence they cite. We present Explanation-Driven Counterfactual Testing (EDCT), an intervention-based protocol that extracts visual concepts cited in a model's explanation, applies verified minimal edits to them, and tests whether the resulting answer and explanation remain consistent with the edited image. Using this protocol, we create EDCT-Bench, a comprehensive benchmark spanning three complementary domains: knowledge-intensive visual question answering (OK-VQA), safety-critical driving (DriveLM), and 3D spatial reasoning (3DSRBench). Across the evaluated VLMs, EDCT reveals substantial faithfulness gaps, with models frequently producing responses inconsistent with verified visual changes. Finally, our fine-tuning study suggests that EDCT-generated counterfactuals provide high-impact training signals.
Abstract (translated)
URL
https://arxiv.org/abs/2609.17953
PDF
-
AgenTeeth: A Model-Agnostic Framework for Suppressing Hallucination in Frozen Vision-Language Models on Dental X-Rays via Tool Evidence Injection
2026-09-15 20:10:43Ahmed Rafid, Fariya Ahmed, Rumman Adib, Mehedi Ahamed, Ajwad Abrar, Tareque Mohmud ChowdhuryAbstract
Vision-language models (VLMs) remain largely unreliable on panoramic dental radiographs and can rely on learned anatomical priors rather than evidence in the image. This is particularly problematic for tooth localization and spatial reasoning, and fine-tuned dental VLMs can retain the same spatial biases. We present AgenTeeth, a model-agnostic, tool-augmented framework that grounds frozen VLMs using seven specialized dental vision experts. A question-aware orchestrator selects the relevant tools, whose detections are mapped to FDI tooth numbers or anatomical regions and returned as structured findings together with annotated image overlays. A fresh synthesis call then answers the question using this evidence, without fine-tuning the underlying VLM. On MMOral-OPG-Bench, AgenTeeth improves four backbone VLMs by 12.9-23.0 percentage points over their baselines. Our strongest configuration reaches 65.66% on open-ended VQA, compared with 45.35% for OralGPT-Plus. The advantage also holds at matched scale: a frozen Qwen2.5-VL-7B-Instruct with AgenTeeth reaches 48.11%, exceeding OralGPT-Plus built on the same backbone after supervised fine-tuning and reinforcement learning for tool use. We release the framework, all seven expert models, and a dentist-annotated dataset for alveolar bone-loss detection in panoramic radiographs.
Abstract (translated)
URL
https://arxiv.org/abs/2609.17800
PDF
-
Tables Decoded: DELTA for Structure, TARQA for Understanding
2026-09-15 16:59:42Jahanvi Rajput, Dhruv Kudale, Saikiran Kasturi, Utkarsh Verma, Ganesh RamakrishnanAbstract
Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering (TabVQA). While recent approaches predominantly rely on vision- language models (VLMs) operating on table images, we propose a more scalable and effective alternative based on structured textual representations. These representations are easier to process, align more naturally with LLMs, and eliminate the need for language-specific visual encoders, making them particularly suitable for multilingual documents. We present DELTA, which separates physical structure recognition, logical structure recognition, and OCR to extract both layout and content accurately. DELTA outputs tables in Optimised Table Structure Language (OTSL), a compact and unified format that encodes cell arrangements and textual content. On table structure recognition (TSR), DELTA achieves TEDS- Structure scores comparable with state-of-the-art methods across FinTabNet, PubTabNet, and PubTables-1M. We further establish its robustness on non-English tables through our curated Hindi benchmark, TORQUE. Building on this, we introduce TARQA, an LLM fine-tuned on OTSL sequences. Our approach yields gains of 9.3 p.p. on WTQ (TabQA) and 9.2 p.p. on FinTabNetQA (TabVQA), respectively. On TORQUE, our method ranks second among all VLMs and DELTA + LLM variants. We release our code, models, and benchmark at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.17458
PDF
-
BrainFocus: EEG-Guided ROI Selection for Efficient Vision-Language Models
2026-09-15 16:51:13Yihui Peng, Guorui Lu, Qinyu ChenAbstract
Vision-language models (VLMs) achieve strong visual question answering (VQA) performance, but processing large cluttered images is computationally expensive when only a small region is relevant. Electroencephalography (EEG) signals, which capture human neural responses to visual stimuli, can provide a human-derived semantic cue about the region of interest (ROI). However, EEG-guided visual category decoding remains imperfect, making direct ROI routing unreliable. In this work, we propose BrainFocus, a reliable EEG-guided efficient VLM framework for VQA. An EEG classifier predicts a target category, and a YOLO detector localizes the matching ROI. The VLM receives the cropped ROI only when both predictions pass confidence thresholds; otherwise, it processes the full image. For evaluation, we build on EEG-ImageNet to construct a 40-class benchmark comprising generated cluttered images and real object-centric images, with target-ROI annotations and 600 English visual question-answer pairs. Across Qwen3.5-VL 2B, 4B, and 9B models, BrainFocus improves VQA accuracy by 4.14-9.87 percentage points (pp) on cluttered scenes while reducing input tokens and total tokens by 23.2%-39.4% and 23.2%-39.3%, and end-to-end floating-point operations (FLOPs) by 23.2%-39.5%. These results demonstrate that EEG can guide efficient VLM inference even when its semantic decoding is imperfect.
Abstract (translated)
URL
https://arxiv.org/abs/2609.17443
PDF
-
Semantic-Spatial Agreement Verification for Mitigating Object Hallucination in Multimodal Large Language Models
2026-09-15 14:48:48Ziheng Ren, Qian Gao, Jun Fan, Guohui Ding, Zhenyu Yang, Yuteng XiaoAbstract
Multimodal large language models generate natural-language responses from visual inputs, yet may mention objects absent from an image. In medication assistance, accessible perception, and environmental decision-making, such hallucinations can create real-world safety risks. We propose Semantic-Spatial Agreement Verification (SSAV), a training-free method for verifying object claims. A visually grounded claim should remain stable across semantically equivalent queries and repeatedly localize to the same image region. SSAV aggregates multiple prompts to estimate semantic support and reduce sensitivity to query wording. Query-Induced Regional Verification (QIRV) combines cross-query region persistence, spatial overlap, and relative candidate dominance to identify isolated high responses and dispersed localizations. A geometric mean fuses semantic and spatial evidence, lowering the verification score when either branch lacks support. Experiments on three base models and multiple evaluation protocols show that SSAV effectively mitigates object hallucination. On LLaVA-1.5-7B, accuracy averaged across COCO, A-OKVQA, and GQA improves by 1.81 and 3.17 percentage points under POPE Popular and Adversarial, respectively, while CHAIRs decreases from 49.40% to 32.80%. These results show that cross-query semantic stability and regional consistency provide interpretable external visual evidence for object claims.
Abstract (translated)
URL
https://arxiv.org/abs/2609.17269
PDF
-
DriveMCP: An Agentic AI framework for Advanced Driver Assistance System
2026-09-15 14:29:18Farzad Nadiri, Mehdi Cina, Ahmad B. RadAbstract
An agentic AI driver-assistance framework that integrates perception, compliance reasoning, vehicle-state interpretation, and safety arbitration into a modular and auditable pipeline. The architecture, referred to as DriveMCP, incorporates a sensor-like perception stack alongside DriveLM as the vision-language front end to generate a graph-structured scene understanding (Graph Visual Question Answering) and language-grounded driving information. Key compliance elements in world_state, including posted speed limits and jurisdiction cues, are derived from DriveLM outputs through a structured parsing layer rather than being injected as simulator ground truth. A stateful orchestration layer coordinates specialized experts exposed as Model Context Protocol (MCP) servers: (i) a Rules server that performs retrieval-augmented compliance reasoning over jurisdiction-specific traffic codes and sign conventions, (ii) a Weather server that estimates traction risk and contextual speed advisories, and (iii) an MCP-CAN server that surfaces Controller Area Network (CAN)/On-Board Diagnostics (OBD) telemetry and diagnostic context for health-aware risk shaping. These outputs are fused to generate a structured decision that prompts a recommended course of action. The outcome is then further filtered by a Responsibility-Sensitive Safety (RSS)-inspired guardrail that arbitrates speak versus act decisions under bounded online adaptation. In CARLA simulation across multilingual, cross-border, and dynamic speed-limit scenarios, DriveMCP reduces traffic infractions and overspeed relative to the VLM-Direct, VLM-Direct+RAG, and VLM-Tools-NoArbiter baselines, while improving hazard response time and maintaining sub-second advisory latency.
Abstract (translated)
URL
https://arxiv.org/abs/2609.17247
PDF
-
Not Another Text Benchmark: Putting the 'Visual' Back in Visual Question Answering for Large Video Models
2026-09-15 12:41:08Rwiddhi Chakraborty (Oliver), Yinong (Oliver), Wang, Cheng Zhang, Fan Bai, Zhuoran You, Michael Kampffmeyer, Yong Jae Lee, Fernando De la Torre, Robert JenssenAbstract
Large video models have exhibited impressive performance on a wide range of visual question answering tasks, owing to the rise of powerful, pretrained text and vision encoders. The usefulness of such models have also been demonstrated on a wide range of benchmarks, with an important caveat - the dominant approach in these benchmarks evaluates multiple choice reasoning via text options. This is a natural way to test text-based reasoning in these models, and has led to significant insights regarding model behavior in the community. In this work, we ask a different question - what happens when the evaluation modality is visual, rather than text? We introduce three new vision-centric evaluation benchmarks in temporal frame retrieval, video future prediction, and causal memory distortion, all designed around evaluating visual understanding capabilities in large video models. Our approach complements the existing approaches to evaluate video understanding in frontier models. We show that current frontier models exhibit significant weakness when attempting to reason through visual queries, rather than text. We conclude with an extended analysis section that provides pointers for future improvements in visual understanding for large video models.
Abstract (translated)
URL
https://arxiv.org/abs/2609.17112
PDF
-
High-Fidelity Video Quality Assessment with VQA-Specific Saliency
2026-09-15 10:23:05Hakan Emre Gedik, Shashank Gupta, Alan BovikAbstract
No-reference video quality assessment (NR VQA) has recently seen promising progress with deep learning. However, video data is inherently large, and processing them with deep models incurs high computational cost. This challenge is particularly acute in VQA, where preserving original-resolution cues and dense temporal information is critical for accuracy. Existing efficiency-driven preprocessing strategies, such as fragmenting, reduce computation but alter the input data distribution, limiting effective reuse of pretrained video foundation models (ViFMs). To address these challenges, we propose \textbf{H}igh-\textbf{F}idelity \textbf{V}ideo \textbf{Q}uality \textbf{A}ssessment (\textbf{HFVQA}), a framework built on fixed-size spatio-temporal (ST) patches that is fully compatible with pretrained ViFMs. HFVQA samples ST patches across multiple scales, including the original resolution, with minimal temporal subsampling to preserve low-level quality cues and semantic context. To limit computation, HFVQA introduces a lightweight auxiliary network trained end-to-end with the ViFM encoder to learn \textit{VQA-specific saliency}. Distilled directly from quality supervision, this saliency captures task-specific importance patterns, reflecting that video quality perception is dominated by a small subset of spatio-temporal regions. By combining high-fidelity spatio-temporal cues with learned, task-specific saliency, HFVQA achieves SOTA performance on standard NR VQA benchmarks while processing as little as 12\% of candidate ST patches, making high-fidelity ViFM-based VQA computationally tractable.
Abstract (translated)
URL
https://arxiv.org/abs/2609.16946
PDF
-
Layers, Sinks, and Scaling: Adaptive Evidence Selection for Multimodal Large Language Models
2026-09-15 08:02:52Zhenbin Wang, Lei Zhang, Lituan Wang, Wei Huang, Yan Wang, Zhenwei ZhangAbstract
Multimodal large language models (MLLMs) can answer knowledge-intensive visual questions by combining visual evidence from images with facts retrieved from external sources. However, MLLMs may overlook relevant evidence in both modalities, attending weakly to the textual sentences or visual regions needed for the correct answer. Recent efforts address this by highlighting retrieved text and marking visual regions before generation, but apply a fixed, one-shot policy that cannot adapt to three sources of variation: whether highlighting is necessary, how much evidence different examples require, and when different textual evidence becomes relevant as the answer unfolds. We introduce Adaptive Relevance-guided Evidence Allocation (AREA), a training-free inference-time method that formulates evidence highlighting as adaptive allocation. AREA generates a single probe token to read visual and textual relevance from fixed backbone layers, then makes three decisions: i) whether to intervene (controlled by natural attention coverage and visual sink contamination), ii) how much evidence to expose (determined by relevance entropy), and iii) when to refresh text during generation (triggered by causal context-attention peaks). Across four KB-VQA and seven standard multimodal benchmarks with nine frozen MLLM checkpoints, establishes the best performance among training-free highlighting methods.
Abstract (translated)
URL
https://arxiv.org/abs/2609.16795
PDF
-
SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation
2026-09-15 03:53:32Zixiu Ding, Zilin Zhao, Yingjie He, Xinlang Kang, Guansu Wang, Wei ZhangAbstract
Multimodal large language models (MLLMs) have made strong progress on visual question answering and image captioning, yet they still produce fluent claims about objects, attributes, or relations that are not grounded in the image. Many remedies either modify decoding at test time, which adds latency, or fine tune with preferences such as DPO variants, which teach which answer is preferred but not when the model's own answer is unreliable. We argue that calibrated self assessment is the missing signal. We introduce Savor, a training framework that (i) augments the output schema with token and answer confidence, (ii) optimises the policy with a Group Relative Policy Optimisation (GRPO) objective that penalises calibration error and poor abstention decisions, and (iii) uses the learned confidence at inference time to revisit visual evidence only when the model is uncertain. Experiments on POPE, HallusionBench, AMBER and MMHal-Bench across two recent backbones (InternVL3-8B and Qwen3-VL-8B) show that Savor reduces hallucination while preserving general capability on MME and MMBench, with lower Expected Calibration Error than DPO and decoding baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2609.16601
PDF
