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

CardsList

268 papers22 papers in the last four weeks, down 46% on the four weeks before. 0.2% of all new papers.

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

    Sep 18, 2026Jia Li, Li Dai, Peng Jia +4Visual Question AnsweringMultimodal QA

  2. DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering

    Sep 17, 2026Luca De Grandis, Silvia Cappelletti, William Raccagni +3Visual Question AnsweringVision-Language Grounding

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

    Sep 16, 2026Nguyen Hoai Thuong Bui, Thanh Nguyen Vo, Trinh Tra Giang Nguyen +1VLMs for Autonomous DrivingVisual Question Answering

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

    Sep 15, 2026Ahmed Rafid, Fariya Ahmed, Rumman Adib +3VLM Hallucination MitigationRadiology VLMs

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

    Sep 15, 2026Yihui Peng, Guorui Lu, Qinyu ChenVisual Question AnsweringEfficient VLM Inference

  6. Counterfactual Reasoning for Robust Visual Question Answering

    Sep 15, 2026Truong-Binh Duong, Thanh-Ngan Tran, Ngoc-Thao Nguyen +1Visual Question AnsweringContrastive Learning

  7. Vision And Text Transformer For Predicting Answerability On Visual Question Answering

    Sep 15, 2026Tung Le, Huy Tien Nguyen, Le Minh NguyenVisual Question Answering

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

    Sep 14, 2026Md Khalid Syfullah, Alvi Ataur KhalilVisual Question AnsweringPrivacy Protection in VLMs

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

    Sep 12, 2026Ritali Vatsi, Rachapudi Jagadeesh, Shruti Singh Baghel +3Visual Question AnsweringVLM Robustness

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

    Sep 10, 2026Md Khalid Syfullah, Alvi Ataur KhalilVisual Question AnsweringFederated Learning Aggregation

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

    Sep 9, 2026Xinrui He, Ting-Wei Li, Junting Wang +4Test-Time Adaptation of VLMsRL for VLMs

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

    Sep 9, 2026Hanjing Zhou, Mingze Yin, Ying Lian +3VLM EvaluationVisual Question Answering

  13. ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains

    Sep 8, 2026Artemis Llabrés, Marc Serra Ortega, Tomàs Ockier +6Document UnderstandingMultimodal QA

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

    Sep 5, 2026Prathamesh Gadekar, Sagar Srinivas Sakhinana, Venkataramana RunkanaVLM ReasoningFaithfulness in VLMs

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

    Sep 2, 2026Adrien Mialland, Marc Plantevit, Julien Gallois +1Adaptive RetrievalVisual Document Retrieval

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

    Sep 1, 2026Hai-Dang Nguyen, Huy-Hieu PhamMemory-Augmented VLMsVisual Question Answering

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

    Sep 1, 2026Raul Ortega, José Manuel Gómez-PérezSynthetic Data Generation for Language ModelsSynthetic Data Generation for VLMs

  18. Visual Attention Faithfulness in Vision-Language Models is Heterogeneous

    Sep 1, 2026Xurui Song, Weishi Wang, Zhongqi Yue +5VLM EvaluationVisual Question Answering

  19. LOCI: A Locator-Critic with Refinement Loop

    Aug 31, 2026Walid Bousselham, Mathilde Caron, Arsha Nagrani +1Visual Question AnsweringVision-Language Grounding

  20. ManGo: Manga Active Narrative Grounding Optimization

    Aug 30, 2026Hao Qiu, Junyan Wang, Zheyuan Liu +4Visual Question AnsweringRL for Language Model Reasoning

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

    Aug 27, 2026Anoop SenthilVisual Question AnsweringVision-Language Grounding

  22. AWM: Answerable Working Memory for Long-Document VQA Agents

    Aug 26, 2026Dongzhuoran Zhou, Yuqicheng Zhu, Yule Liu +5Long-Document Visual Question AnsweringLong-Context QA

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

    Aug 22, 2026Jinchang Zhu, Rong Fu, Yi Ding +3Large Vision-Language ModelsVisual Question Answering

  24. VIALS: A Benchmark for Visual Interpretation of Artifacts in the Life Sciences

    Aug 21, 2026Elaine Lau, Thanuka Udumulla, Lee Izhaki-Tavor +3AI for ScienceVLM Evaluation

  25. SCAFFOLD: A Large-Scale Structured Dataset of Computer Science Research Figures with Diagram QA and Chain-of-Thought Reasoning Traces

    Aug 20, 2026Ranjit Raut, Aarav Subedi, Sagun Rai +1Document Image UnderstandingVisual Question Answering

  26. GRACE: Grounded Reasoning via Adapter Composition and Evidence-Aware Calibration for Educational Visual Question Answering

    Aug 19, 2026Xinjin Li, Yudi Xia, Xi Zhao +8Visual Question AnsweringVLM Adaptation