Visual Question Answering

Also known as VQA

Overview

The field asks how machines can connect a question to relevant visual evidence, read text and diagrams, and combine perception with commonsense or specialized knowledge. Approaches range from vision-language encoders and multimodal large language models to region and crop grounding, OCR and scene graphs, retrieval-augmented agents, and fine-tuning or reinforcement learning. Benchmarks cover everyday images and compositional reasoning, knowledge-based and text-rich questions, and document, video, medical, scientific, and multi-view settings. A central challenge is that correct-sounding answers may lack reliable visual grounding: models still miss small details and spatial relations, struggle to combine evidence across views or long documents, and may fail to recognize when they should abstain.

Latest papers

272 papers22 papers in the last four weeks, down 44% on the four weeks before. 0.2% of all new papers.

Sep 22, 2026

Reading Right, Answering Wrong: How Visual Configuration Changes Affect Evidence Use in VLMs

Vision-language models (VLMs) have achieved strong performance on tasks such as visual question answering, yet small image resizes can turn correct answers into errors. We investigate whether changes in visual configuration, such as image tiling and token arrangement, contribute to this instability. Across seven checkpoints and four benchmarks, equally small resizes cause more correctness flips when they switch configurations. Surprisingly, in over half of these cases, models answer the question incorrectly but can still read the correct answer when told what to read. Furthermore, attention interventions in LLaVA-NeXT suggest that configuration changes can weaken the use of readable information during answering. We therefore guide models using field cues and their own transcriptions. With annotation assistance, these forms of guidance together correct 97.2% of errors with readable information. These findings show that configuration changes can affect how models use information they can still read.
Sep 21, 2026

A2^2Safe: Counterfactual Evidence-Aligned Adaptive Agent Collaboration for Safe and Effective Visual Question Answering

Visual Question Answering (VQA) with Multimodal Large Language Models (MLLMs) requires not only producing safe and effective responses, but also grounding safety decisions in the multimodal evidence that determines risk. Recent safety-alignment methods improve refusal behavior and contextual risk awareness, yet correct safety outcomes may still rely on superficial textual or visual correlations, particularly when risk emerges from interactions between individually benign image and question content. To address this issue, we propose A2^2Safe, a counterfactual evidence-aligned adaptive agent collaboration framework for safe and effective VQA. A2^2Safe organizes localized visual observations, textual intent, and cross-modal risk relations through a Grounded Safety Evidence Board, making the basis of safety decisions explicit. Counterfactual safety evidence alignment enforces invariance to safety-irrelevant changes while requiring appropriate safety-state and response-mode transitions when risk-critical evidence is minimally altered. The resulting evidence state further supports adaptive collaboration, enabling direct answering when grounded evidence is sufficient and invoking policy critique and response revision when evidence is risky, uncertain, or conflicting. Under complementary safety-critical and general VQA protocols, A2^2Safe achieves a 95.72 SIUO safety score, reduces the benign refusal rate on MOSSBench to 14.67%, and maintains an average general VQA score of 78.34 with 27.8% token overhead. These results support counterfactual evidence-aligned adaptive collaboration for safe and effective multimodal question answering.
Sep 20, 2026

Pay More Attention To Text In High-Resolution MLLMs

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 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.
Sep 18, 2026

Beyond Exact Match: Task-Aware GRPO for Cross-Domain PCBA Visual Question Answering

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.
Sep 17, 2026

DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering

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 https://aimagelab.github.io/DocAttriBench/.
Sep 16, 2026

Sim-to-Real Traffic Scene Understanding by Decoupling Semantics from Caption Generation with V-JEPA

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.
Sep 15, 2026

AgenTeeth: A Model-Agnostic Framework for Suppressing Hallucination in Frozen Vision-Language Models on Dental X-Rays via Tool Evidence Injection

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.
Sep 15, 2026

BrainFocus: EEG-Guided ROI Selection for Efficient Vision-Language Models

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.
Sep 15, 2026

Counterfactual Reasoning for Robust Visual Question Answering

Modern Visual Question Answering (VQA) models often exploit spurious correlations in training data, leading to poor out-of-distribution (OOD) generalization due to language bias. Although counterfactual learning has shown promise, existing methods can be improved to better guide attention toward causal evidence and strengthen feature discrimination. To address this, we propose a novel training framework that enhances counterfactual contrastive learning for VQA. Our framework introduces three key contributions: (1) a three-stage curriculum for stable multi-objective optimization, (2) an enhanced Batch-Contrastive loss for more discriminative feature learning, and (3) two novel regularizers, Answer-Contrastive (AC) loss to refine the prediction space and Gradient-Discrepancy (GD) loss to enforce causal visual grounding. Our model achieves a competitive accuracy of 61.64% on the bias-sensitive VQA-CP v2 benchmark while maintaining 62.80% on the standard VQA v2 dataset, yielding a small generalization gap of 1.16%. This demonstrates a strong balance between OOD robustness and in-distribution performance.
Sep 15, 2026

Vision And Text Transformer For Predicting Answerability On Visual Question Answering

Answerability on Visual Question Answering is a novel and attractive task to predict answerable scores between images and questions in multi-modal data. Existing works often utilize a binary mapping from visual question answering systems into Answerability. It does not reflect the essence of this problem. Together with our consideration of Answerability in a regression task, we propose VT-Transformer, which exploits visual and textual features through Transformer architecture. Experimental results on VizWiz 2020 dataset show the effectiveness and robustness of VT-Transformer for Answerability on Visual Question Answering when comparing with competitive baselines.
Sep 14, 2026

NoteVQA: Benchmarking VLMs on Real-Life Questions from Human Communities

Vision-language models (VLMs) increasingly power consumer-facing AI search, yet evaluating them on the diversity of everyday visual questions remains challenging. Existing benchmarks often target predefined capabilities, such as multi-hop retrieval or long-form synthesis, whereas users ask photo-grounded questions spanning a long tail of everyday scenarios. Despite advances in VLMs, users on Xiaohongshu, a mainstream Chinese image-sharing platform, continue to turn to other people for help with everyday visual questions. Motivated by this behaviour, we curate NoteVQA from these questions, yielding 252 items across 12 topical categories and 7 user intents. Each item includes a concise reference distilled from expert community responses and a human-audited interleaved reference answer that combines textual explanations with supporting visual evidence. We evaluate both short-answer correctness and interleaved-answer quality. To support the latter, we introduce AgenticInterleave, a single-agent ReAct framework for retrieval-supported answer generation, together with IVR-12, a 12-dimensional rubric for assessing the content, presentation, and image quality of interleaved references and model outputs. Across 9 frontier VLMs, the highest short-answer accuracy is 52.8%, while adding agentic search to Qwen3.5-397B-A17B improves accuracy by only 2.0%. For interleaved answers, the same model running AgenticInterleave scores 3.52 under IVR-12, compared with 4.65 for the human-audited references, with the largest gap in content quality. These results highlight the challenges that everyday visual questions pose for current VLMs in both answer accuracy and the quality of visually grounded explanations.
Sep 14, 2026

Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language Models

Visual Question Answering (VQA) with Vision-Language Models (VLMs) is increasingly used in privacy-sensitive and bandwidth-constrained settings. Federated Learning (FL), Split Learning (SL), and U-Shaped Split Learning (USL) keep raw data local, but transmitting all visual tokens across a model partition remains costly and can expose private information. We propose QPriv-VL, a question-guided, privacy-aware token-pruning framework for FL, SL, and USL that prunes visual tokens before transmission based on task utility and privacy sensitivity. Its core component is a lightweight Dynamic Threshold Predictor (DTP) that jointly estimates a sample-specific pruning ratio and a token-level retention mask in one forward pass. DTP combines question relevance, computed from cross-modal similarity between visual patches and the pooled question embedding, with a sensitivity signal derived from frozen DINOv2 features. This allows the model to suppress potentially sensitive regions while preserving patches useful for answering the question, without requiring sensitivity labels. We evaluate QPriv-VL on GQA, OK-VQA, VQAv2, SLAKE, VQA-RAD, and PathVQA against four privacy attack families: FSHA, FORA, iDLG, and attribute-inference membership inference attacks. DTP matches or outperforms fixed-ratio pruning while using substantially fewer transmitted tokens. On VQA-RAD, it reduces membership-inference attack success from 0.99 to 0.76-0.79, lowers FSHA and FORA reconstruction PSNR relative to fixed-ratio pruning, and preserves competitive VQA accuracy using about 40% of the original visual-token budget. A sensitivity exclusion ratio of 1.20 +/- 0.18 indicates preferential removal of privacy-sensitive patches, while explainability analysis shows that retention adapts to question semantics rather than generic visual saliency.
Sep 12, 2026

Beyond OCR Accuracy: Text-Centric VQA Under Image Degradation with Modular and End-to-End

Text-centric Visual Question Answering (VQA) requires reading and reasoning over text embedded in images, a task made substantially harder when images suffer from real-world degradation such as motion blur, low resolution, or compression artifacts. While modular OCR-based pipelines and end-to-end vision-language models are both widely used for this task, their comparative robustness under degraded conditions remains underexplored. We present an empirical study comparing two modular pipelines with SA-DBNet, a custom detector architecture combining ResNet-18 with self-attention spatial modeling and deformable convolutions against an end-to-end vision-language baseline, evaluated on 4013 degraded images with 7000 question-answer pairs. Fine-tuned modular pipelines achieve up to 57.50% exact-match accuracy versus 38.00% for the end-to-end baseline, with domain-specific fine-tuning yielding a gain of up to 29.50 percentage points. Critically, we find that conventional OCR error metrics like Character Error Rate and Word Error Rate are unreliable predictors of downstream VQA performance, as semantic reasoning can compensate for recognition failures when contextual cues are present. These findings highlight the importance of task-aware evaluation for text-centric VQA systems under realistic visual conditions. Codes are available here
Sep 10, 2026

USPLIT-VQA: U-Shaped Split Learning for Visual Question Answering with Contribution-Aware Weighted Aggregation

Visual Question Answering (VQA) systems, jointly interpreting images and natural language queries, hold significant promise across many domains, yet the privacy-sensitive nature of user data creates a fundamental barrier. Centralized training requires access to all data, while federated learning requires each client to host the full model. We propose USPLIT-VQA, a U-shaped split learning framework for privacy-preserving VQA in which each client retains the initial layers and the classification head while the server hosts the computationally heavy intermediate layers, keeping raw inputs and labels on the client device. We further introduce Contribution-Aware Weighted Aggregation (CAWA), a gradientsimilarity-based client scoring mechanism designed to reduce the influence of malicious updates. Experiments on four VQA datasets (VQA-RAD, SLAKE, PathVQA, and VizWiz) with two backbones show accuracy gains over Federated Learning for the Custom model and reduced accuracy for BiomedCLIP under the evaluated fixed split, alongside client memory reductions of up to 5.8X and communication reductions of up to 10.8X. With one malicious client, CAWA reduces the attacker's influence by over 98%, while experiments at higher corruption levels identify its limitations. Reconstruction experiments further show lower inversion quality under the evaluated attacks.
Sep 9, 2026

Harnessing Image Question Dependence for Better VLM Test-time Reinforcement Learning

Test-time reinforcement learning can adapt vision-language models (VLMs) to unlabeled target data, but its effectiveness is fundamentally limited by the reliability of self-generated learning signals. To assess the reliability of consensus-based learning signals, we analyze VLM test-time reinforcement learning across diverse VQA datasets and model sizes, revealing two limitations. First, gains from consensus-based test-time training largely come from answer normalization rather than content correction. Second, many initial VLM responses are incorrect due to the model's limited ability to jointly use the image and the question; consensus rewards derived from these outputs may preserve the resulting grounding errors rather than correct them. Motivated by these, we propose TTIQ, a test-time reinforcement learning framework that harnesses image-question dependence for better vlm adaptation. TTIQ teacher-forces each sampled response under the original image-question pair and its image- and question-ablated variants, using the resulting token-level likelihood changes to estimate dependence on each input. It combines image and question dependence with calibrated confidence to construct a response-level reward that favors jointly grounded responses, and uses the token-level signals to assign greater positive policy credit to tokens supported by both inputs. This design favors responses that are jointly grounded in the image and the question and sufficiently confident, rather than merely popular. Experiments across eight VQA datasets and multiple VLM sizes show that TTIQ achieves the best average performance at every model scale. It further generalizes across VLM families, while models trained on one dataset improve performance on unseen datasets without further training.
Sep 9, 2026

LogiScope-VQA: Benchmarking Vision-Language Models for Logistics Hazard Identification in Industrial Scenarios

Large Multimodal Models (LMMs) large-scale deployment in industrial warehouse settings specifically necessitates that models exhibit human-expert-level hazard-oriented perception, understanding, and reasoning capabilities. However, the scarcity of real industrial data, tightly coupled to commercial terms, significantly hampers further advancement. To bridge this gap, we curate LogiScope-VQA to investigate the practical applicability of mainstream LMMs in real-world logistics operations. LogiScope-VQA comprises 2,476 images and 2,918 videos primarily sourced from real-world logistics parks, along with 10,274 VQAs meticulously curated and validated by human annotators. Grounded in 18 core objects and 20 risk types, we devise 39 subtasks aligned with three principal themes: industrial element perception, warehouse knowledge understanding, and potential risk reasoning. Furthermore, we incorporate dynamic thinking-budget configurations and dual-dimensional risk bias analyses to elucidate the properties of LMMs. Extensive experiments unveil that even powerful proprietary models, including GPT-5.5, Gemini-3.1-Pro, and Claude-Opus-4.7, exhibit a significant gap relative to human performance. The unique challenge of jointly integrating perception, understanding, and reasoning for hazard identification poses substantial headroom for further improvement on LogiScope-VQA. We additionally reveal the pervasive security bias issue that impedes LLMs' practical deployment in real-world settings. The industrial dataset is publicly available under the CC BY-NC-SA 4.0 license.
Sep 8, 2026

ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains

In this report we present results of the ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains. This competition aimed to advance research in document understanding through the task of Visual Question Answering (VQA). Building upon previous DocVQA benchmarks, this competition introduces challenging reasoning questions over a diverse collection of documents spanning eight domains, including business reports, scientific papers, slides, posters, maps, comics, infographics, and engineering drawings. The competition concluded with 20 valid submissions from 8 teams spanning zero-shot VLMs, OCR and parser-augmented pipelines, agentic retrieval systems, multi-agent ensembles, and fine-tuned multimodal models. The results show that the strongest systems move beyond single-pass prompting and instead rely on structured evidence extraction, retrieval, verification, and orchestration across multiple components.
Sep 7, 2026

BEFORE THE FLIP: Measuring Hidden Score Shifts In Quantized Vision Language Models Before The Answer Changes for Visual Question Answering

Quantization makes vision language models (VLMs) cheaper to store and run by using fewer bits to represent their weights. While unchanged answers on visual question answering (VQA) after compression are an expected behavior, they can still hide changes in the underlying scores (log probabilities). For example, a model may still answer yes after compression, even as the score gap between yes and no shrinks. We introduce BEFORE THE FLIP to measure these hidden changes. Our method compares the score change caused by compression with the change caused by replacing the image's internal representations, or image tokens, with one fixed average token. We then increase the precision of one weight group at a time to identify where extra bits help, and test whether choosing different groups for each question offers benefits beyond shuffled controls. Among 8,277 LLaVA questions where image token replacement measurably affects the scores, 4-bit compression shifts the yes or no score gap farther toward the replacement output than 8-bit compression. Qwen shows the same pattern, but with a smaller difference. Yet only 265 of 9,000 LLaVA answers change at 4 bits. In a separate study of 1,024 calibration questions, choosing weight groups separately for each question does not outperform both shuffled controls at any tested storage budget. These findings show that compression can alter the scores behind unchanged answers, but do not establish a reliable benefit from adjusting precision for each question.
Sep 5, 2026

Grounded and Faithful P&ID Reasoning: Constraining Vision-Language Models with Recovered Evidence Graphs

Piping and Instrumentation Diagrams (P&IDs) are the authoritative maps of process plants: isolation, maintenance, and HAZOP decisions depend on what connects to what. Vision-language models describe these sheets fluently, yet they often invent or miss process connections---and an invented or missed link can reverse an isolation or reachability call, so a plant decision cannot trust a fluent answer that was never checked against the linework. We instead recover an explicit graph of the drawing---its symbols, the process connections between them, and the tags that name them---and then require the model to answer only by querying that graph through seven read-only operators, so a topology claim is returned only when it cites the query results that support it. On TopoPID-VQA, a new suite of 3000 topology questions over these sheets, Graph-Grounded Harness (Ours) raises exact match accuracy from 36.7--41.3% under image-only prompting to 74.3--76.0% for Qwen3-VL-4B, Qwen3-VL-8B, and Gemma-4-E4B. It does so on an imperfect substrate: on Digitize-PID dataset the recovered graph scores F1 0.742 on exact process connections, and 0.801 once symbols and tags are pooled in. The residual errors track that gap---grounding pays off where the recovered graph is right, and perception error still breaks topology questions where it is not.
Sep 2, 2026

ViSAR: Training-Free Adaptive-kk Retrieval for Document Visual Question Answering

Document Visual Question Answering (DocVQA) often leverages Retrieval-Augmented Generation (RAG), where late-interaction encoders are commonly used to identify document pages relevant to a user query, before answer generation by a Large Vision-Language Model (LVLM). Existing approaches typically retrieve a fixed top-kk number of pages regardless of query complexity, which increases LVLM latency and may degrade answer accuracy when fewer pages would be enough. We introduce ViSAR (Visual Semantic Activation Retrieval), a training-free, budget-aware adaptive-kk retrieval method for late-interaction visual document retrieval. ViSAR operates directly in the embedding space to construct a query-conditioned page-level similarity matrix that highlights query-relevant semantics and dynamically determines the number of pages to retrieve, within a given page budget. We evaluate our method across multiple datasets, encoders, and LVLMs. ViSAR retrieves compact, query-adapted page sets that reduce end-to-end RAG latency by up to 58.9%, with no statistically significant accuracy loss and significant gains in several settings, compared with fixed top-kk and adaptive retrieval heuristics. Furthermore, we show that the similarity matrix structure correlates with answer accuracy, suggesting future directions for retrieval quality-aware document understanding.
Sep 1, 2026

Don't Just Look, Intervene: Perturbation Based Region Labeling for VQA Images

Vision Language Models (VLMs) should rely on visual evidence that directly determines the correct answer, but supervision for grounding visual reasoning is often expensive to obtain manually or tied to dataset-specific annotation primitives. We instead introduce model-causal visual evidence as an annotation target, defined as the set of image regions whose counterfactual intervention changes a model's answer distribution for a given image-question pair. Based on this principle, we introduce Counterfactual Search for Grounding Regions (CSGR). CSGR is a scalable pipeline that proposes candidate regions, perturbs them, measures their effect on answer sensitivity, and aggregates this evidence across multiple judges to approximate answer-critical regions in VQA data. To assess whether CSGR annotations contain a useful supervision signal, we plug them into three existing grounding-aware training routines: attention steering, Visual CoTfinetuning, and latent visual reasoning. These experiments test whether the proposed annotation scheme can provide a useful supervision signal across multiple ways of consuming region labels, rather than introducing a new way of using them. Across competing automatic region-labeling mechanisms, CSGR annotations provide the most consistent gains over Cross Entropy-only finetuning in both in-domain and out-of-domain evaluations, indicating that the proposed labeling scheme captures useful region-level information.
Sep 1, 2026

Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA

Mixed-format medical visual question answering (VQA) requires stable option selection and machine-readable free-text output. The two formats fail differently: multiple-choice predictions can change with option symbols or positions, while clinically plausible open answers can fail automated evaluation when serialization is malformed. We address both challenges with an answer-text memory, a permutation-stabilized vision--language expert, and a sparse candidate- expanding router. The cyclic schedule follows prior work; our contribution is to make expert top-2 a routable candidate alongside memory and expert top-1. On a 1,403-case retrospective internal analysis, this expansion improves a matched binary router from 88.95% to 91.73% (+2.78 percentage points; 95% CI 1.57--3.99), with 56 rescued errors and 17 regressions. Oracle coverage rises from 90.31% to 96.15%, and the final submitted configuration reaches 92.23% on the same retrospective split. For open questions, strict generation and deterministic guards produce 475/475 schema- valid participant-facing outputs without repair, retry, or hard-gate failure. Visual ablations reveal substantial textual dependence. Candidate expansion supplies the principal controlled routing gain; open-path evidence establishes output-contract validity rather than clinical correctness in medical use or deployment.
Sep 1, 2026

From Terminology to Diagrams: Visual-Instruction Generation for Scientific Diagram Understanding

Vision-language models (VLMs) have demonstrated strong performance in visual question answering with natural images. However, they continue to struggle with scientific diagrams, which are designed to convey functional or relational meaning rather than literal scenes. We therefore introduce a framework for generating large-scale diagram-grounded instruction data by leveraging terminology derived from scientific curricula. Our approach systematically extracts domain concepts, synthesizes atomic facts, retrieves relevant diagrams from the web, and generates multimodal supervision in the form of diagram captions and multiple-choice questions. Using this pipeline, we construct SciGram, a dataset of over 194K diagrams and 1.4M visual instructions across life, earth, and physical sciences. Despite relying on noisy web data and synthetic annotations, models fine-tuned on SciGram achieve substantial improvements on diagram-centric benchmarks, including TQA, ScienceQA, and AI2D, outperforming or matching state-of-the-art VLMs while using fewer training instances. Furthermore, augmenting existing models such as LLaVA OneVision with SciGram establishes new state-of-the-art performance on diagram question answering. Our results highlight the effectiveness of terminology-grounded instruction generation as a general strategy for improving vision-language reasoning in scientific domains. To support future research in scientific diagram understanding, we release both the SciGram dataset and models.
Sep 1, 2026

Visual Attention Faithfulness in Vision-Language Models is Heterogeneous

Whether attention weights faithfully reflect model reasoning has been actively debated in NLP, yet this question remains largely unexplored for the visual modality in Vision-Language Models (VLMs). We address this gap through causal perturbation analysis on current VLMs, evaluating both the comprehensiveness and sufficiency gap of attention-ranked visual tokens. Our analysis reveals that visual attention faithfulness is heterogeneous, manifesting in three distinct processing modes: Faithful-Sufficient, where top-kk attention tokens are both necessary and sufficient for prediction; Faithful-Distributed, where they are necessary but broader visual context remains required; and Non-Focal, where no localized attention region is individually necessary while visual information remains an essential trigger for prediction. Furthermore, human-annotated ground-truth regions satisfy comprehensiveness in only ∼60\sim 60% of cases compared with model attention rankings, revealing systematic divergence between model visual reliance and human intuition. We demonstrate these patterns across both general VQA on VQAv2 and document tasks on VRDU and ChartQA, showing that visual attention faithfulness varies systematically with processing demands and model architectures rather than being uniformly faithful or unfaithful.
Aug 31, 2026

LOCI: A Locator-Critic with Refinement Loop

Vision-Language Models (VLMs) still struggle on tasks requiring complex visual understanding. We argue that the core issue is not high-level reasoning, but instead failing to locate critical details in the image. Due to this shortcoming, VLMs generate often plausible but incorrect reasoning based on flawed perceptual grounding. To address this, we propose Locator-Critic (LOCI), a training-free framework that decouples visual search from evidence verification. LOCI employs a Locator agent to propose candidate visual evidence and a separate Critic agent to evaluate its relevance and sufficiency. These agents engage in an iterative refinement loop, progressively improving the evidence until it is adequate to answer the given question. This decoupled, self-correcting process yields substantial performance gains, achieving state-of-the-art results on multiple complex visual benchmarks. LOCI improves accuracy for both open-weight models like Qwen3-VL (+12.1 on V*, +5.8 on HR-Bench and +11.2 on VisualProbe-Hard) and proprietary models like Gemini 2.5 Pro (+8.9 on V*, +4.3 on HR-Bench, +4.8 on VisualProbe-Hard).
Aug 30, 2026

ManGo: Manga Active Narrative Grounding Optimization

Manga visual question answering requires models to answer questions over panel-based visual narratives, where relevant evidence is distributed across ordered panels, embedded text, recurring characters, and implicit event transitions. This structure makes passive page encoding insufficient, as the model must identify which panels to inspect, what clues to retain, and when the accumulated evidence is sufficient for answering. We propose ManGo (Manga Active Narrative Grounding Optimization), an unsupervised framework for active manga visual question answering. ManGo introduces Active Narrative Sketching (ANS), which iteratively selects panels, extracts concise grounded clues, and decides when to stop, forming a compact question-directed evidence sketch before answer generation. To optimize this behavior without human-annotated answers or rationale paths, ManGo samples multiple ANS rollouts and applies group-relative training with two rewards: answer preference from listwise self-ranking and path consistency from stable ordered panel trajectories. The combined reward is optimized with group-relative policy training, encouraging the model to improve both final answers and the panel-level evidence paths that support them. Experiments on standard manga understanding benchmarks show that ManGo achieves state-of-the-art performance across different settings.
Aug 29, 2026

DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Question Answering

Real-world degradations such as blur, shadow, distortion, and moire patterns severely impair the document question-answering capabilities of Multimodal Large Language Models (MLLMs). Applying restoration tools before Visual Question Answering (VQA) is an intuitive solution. However, existing restoration approaches remain limited, as manually designing and executing restoration strategies is labor-intensive and requires domain expertise. Agentic restoration offers new possibilities for automation, yet existing frameworks primarily target natural images and pursue perceptual quality, overlooking that restoration should serve downstream tasks rather than optimize generic image quality metrics. To this end, we explore the value of agentic restoration for real-world degraded document VQA and propose DocIntent, a training-free Answerability-Guided Agentic Restoration framework. DocIntent first assesses question answerability, then identifies task-relevant degradations and selectively invokes restoration tools. A Comparison-Based Rollback mechanism validates each restoration step and reverts it when question-relevant evidence becomes less decipherable. The entire process requires no additional pretrained degradation classifier or image quality assessment model. Extensive experiments on the WildDoc benchmark show that DocIntent consistently improves the average score and consistency of different open- and closed-source MLLMs. The code and experimental data will be publicly available.
Aug 27, 2026

ReVA: A Region-Aware Visual Assistant for Visually Grounded Question Answering

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Visual Question Answering (VQA), yet they continue to struggle with questions requiring precise spatial reasoning and fine-grained visual understanding. These limitations often manifest as object, attribute, and spatial hallucinations, where models generate confident but visually unsupported responses due to insufficient region-level and fine-grained visual grounding. To address this challenge, we propose ReVA, a region-aware VQA model that employs a frozen CLIP ViT-L/14 Vision Transformer (ViT) and a Qwen2.5-7B-Instruct large language model (LLM) connected through a dual bridge that aligns both whole-image and region-level representations with the LLM's embedding space. The image bridge maps final transformer block features into image tokens. The region bridge maps cropped features from enriched intermediate features across ViT blocks so early texture and later object cues are more evident, into K region tokens for every bounding box. ReVA uses a detector stack that supplies automatic zero-shot bounding boxes that are both question-agnostic and question-dependent, using RAM++ (Recognize Anything Model), spaCy, and Grounding DINO. The image tokens and region tokens are concatenated as an LLM prompt prefix to jointly encode scene-level context and fine-grained regional evidence when answering questions. Evaluated on VQAv2, MMBench, POPE, and SEED-Bench, ReVA achieves 82.85% mean F1 on POPE, compared with 81.14% for an image-token baseline without region tokens. These results demonstrate that explicit region-aware visual representations reduce object hallucination and improve the factual grounding of MLLMs.
Aug 26, 2026

AWM: Answerable Working Memory for Long-Document VQA Agents

Long-document visual question answering increasingly relies on VLM agents that retrieve candidate pages, inspect page images, write findings to working memory, and synthesize answers. Working memory should carry answer-supporting evidence across page inspections for later grounded answering, yet existing evaluation mainly checks final-answer correctness and evidence-page access. This creates a memory-quality blind spot: an agent may reach the right page and answer correctly while leaving behind memory too generic or incomplete to support answering once page context is removed. We introduce memory-only answerability, a diagnostic that asks whether a reader can answer from the question and terminal working memory alone. Building on this diagnostic, Answerable Working Memory (AWM) treats terminal working memory as an answerable evidence artifact, and AWM-GRPO incorporates this signal into the GRPO reward while preserving final-answer priority. Under GRPO, this reward assigns higher advantages to answer-correct trajectories whose terminal working memory remains answerable. On MMLongBench-Doc, even when gold evidence pages are provided, 42.5% of correct answers still cannot be answered from terminal working memory alone. AWM-GRPO improves final-answer accuracy over the RAG baseline by 8.1 and 11.9 points on MMLongBench-Doc and LongDocURL and reduces the memory-missing-correct rate by 2.7 points over answer-only GRPO.
Aug 22, 2026

Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models

Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image is compressed into a low-resolution global view. Allocating more visual tokens to every query improves some OCR and document cases, but it spends computation indiscriminately and can disturb tasks that rely on global context. We propose GapSight, a framework for learning visual re-reading: a VLM first takes a global glance, then selectively returns to a free-form region when the question calls for local evidence. The supervision comes from the target model's own failure signal. Offline, we compare answer loss or multiple-choice option margin under a global-only view and candidate crop-augmented views; crops that improve the target answer become model-specific review labels. A lightweight free-form crop router distills these labels into a one-shot inference policy that predicts whether to review, expected utility, and a continuous crop box from the global state. Across LLaVA-1.5-7B, InternVL2.5-8B, and Qwen2-VL-2B-Instruct, GapSight improves the Base no-zoom baseline on six benchmarks spanning OCR, documents, charts, infographics, VStarBench, and MME-RealWorld-Lite. On InternVL2.5-8B, GapSight raises the six-benchmark average from 52.25 to 64.29, above CropVLM (57.16), ViCrop (55.84), and ZoomRefine (54.43). Mechanism analyses show that the router rescues concrete wrong answers, adapts its action rate by task, and forms a favorable token-performance profile. These results position loss-gap supervision as a practical route to teaching VLMs when and where to look again.