Evidence-Grounded VQA

VQA: Video Question Answering

Follow this topic Ask about this topic

Latest papers

28 papers4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

TwinPast: Benchmarking Historical Evidence Use in Streaming Video Understanding with Evidence Contrastive Video Pairs
Oct 30, 2026Haotian Yang, Yong Chen, Cheng Peng +4Evidence-Grounded VQA Streaming Video Understanding
School of Software Technology, Zhejiang University · HeyGen · Zhejiang University
GroundedVDR: Grounding Video-to-Web Evidence Dependencies in Video Deep Research
Oct 18, 2026Xiyuan Liang, Yu Wang, Zuhao Yang +7Evidence-Grounded VQA Multimodal Model Evaluation
NTU · HKUST(GZ) · ModelBest +2
VideoJev: System One Model for Video Understanding and Interaction
Oct 13, 2026Yuhan Zhu, Xiangyu Zeng, Qingyi Si +15Video Question Answering Evidence-Grounded VQA
NJU · UCAS · THU +4
Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence
Oct 13, 2026Jiahao Meng, Zhongyuan Bao, Yue Tan +7Video Reasoning Video Understanding
Video Evidence Indexing: Learning Where to Look from Video Previews for Token-Budgeted Long-Video Question Answering
Sep 30, 2026Haowen Guan, Shengzhi Li, Shichao PeiVideo Question Answering Long-Video QA
STORM-Bench: Evaluating Online Video QA under Evolving and Incomplete Evidence
Sep 25, 2026Siru Zhong, Shenghan Tan, Rihong Yan +6Video Question Answering Evidence-Grounded VQA
HKUST (GZ) · Beta Infinity · Beihang University +2
Long-to-Short Video Evidence Reasoning for Grounded Question Answering
Sep 14, 2026Kaiyan Chen, Junbin Xiao, Xun YangTemporal Video Grounding Video Question Answering
University of Science and Technology of China
Cite or Decline: A Strict Course-Grounded Chatbot for STEM Lecture Videos
Sep 1, 2026S M Masrur Ahmed, Jaspal SubhlokEvidence Retrieval Video Question Answering
University of Houston
Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos
Aug 26, 2026Baixuan Xu, Yinyui Xu, Tianshi Zheng +9Long-Video QA Long-Video Understanding
Department of Computer Science and Engineering, HKUST, Hong Kong SAR, China
Multi-Agent Self-Improving Reinforcement Learning for Video Reasoning
Aug 25, 2026Mingwen Zhang, Jisheng Dang, Minqiang Yang +3Evidence-Grounded VQA Video Reasoning
School of information Science and Engineering, Lanzhou University, LanZhou, China · Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China · Brain Health Engineering Laboratory, Institute of Engineering Medicine, Beijing Institute of Technology, Beijing, China +1
TRACE: Temporal Retrieval with Anchored and Convergent Evidence for Long-Horizon Video Understanding
Aug 23, 2026Pengyiang Liu, Junbo Niu, Xiaoyang Hu +4Evidence-Grounded VQA Video Question Answering
Colab, Beihang University · Shanghai AI Laboratory · Peking University
What You Ask is What You Ground: Bridging Question Intent to Temporal Evidence for Grounded VideoQA
Aug 16, 2026Jinhwan Seo, Kyubeom Han, Jumin Lee +2Evidence-Grounded VQA Video Question Answering
KAIST · Ewha Womans University
Catching Hallucinated Citations in Video-LLM Question Answering: A Self-Verification Pipeline and Verifier Ablation Study
Aug 16, 2026Yogesh KumarEvidence-Grounded VQA Hallucination Detection in VLMs
DAEP: Difficulty-Aware Evidence Planning for Medical Video Corpus Temporal Answer Grounding
Aug 7, 2026Tianjian He, Yujie Liu, Zhiping Huang +1Temporal Video Grounding Video Understanding
TikTok, ByteDance, China · Beijing Institute of Graphic Communication, Beijing, China · Lingnan University, Hong Kong, China
MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding
Aug 5, 2026Benlei Cui, Ruize Wang, Junjie Li +9Video Question Answering Long-Video Understanding
Yuvion Team, Alibaba Group · Zhejiang University · Beihang University +1
Ground, Cover, and Refine: Evidence-Centric Frame Selection for Long-Video Question Answering
Aug 3, 2026Fan Wei, Siru Zhong, Runmin Dong +3Long-Video Understanding Video Frame Selection
Department of Earth System Science, Tsinghua University · 5The Hong Kong University of Science and Technology (Guangzhou) · School of Artificial Intelligence, Sun Yat-Sen University +2
Beyond Frame Selection: Generative Latent Evidence Aggregation for Long-Video Understanding
Jul 30, 2026Bowen Liu, Shuning Wang, Xinpeng Ding +3Video-Language Models Long-Video Understanding
The Hong Kong University of Science and Technology · Alibaba Group · Xidian University +1
Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA
Jul 17, 2026Ce Zhang, Ziyang Wang, Yulu Pan +6Temporal Video Grounding Tool-Using Vision-Language Agents
University of North Carolina at Chapel Hill · Sony
Evidence-Backed Video Question Answering
Jul 13, 2026Shijie Wang, Honglu Zhou, Ziyang Wang +5Temporal Video Grounding Video Question Answering
Salesforce, Palo Alto, CA, USA · Brown University, Providence, RI, USA
EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence
Jun 23, 2026Linpeng Huang, Weixing Chen, Zexin Chen +2VLM Evaluation Temporal Video Grounding
Sun Yat-sen University · Shenzhen University · Peng Cheng Laboratory
See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video Understanding
Jun 8, 2026Shuning Wang, Zhiheng Wu, YiNuo Lu +6Video Question Answering Video-Language Models
Baidu Inc. · Harbin Institute of Technology · Hong Kong University of Science and Technology
Question-Aware Evidence Ledgers for Video Relational Reasoning
Jun 1, 2026Yilin Ou, Mengshi Qi, Huadong MaVideo Reasoning Relational Reasoning
State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications, China
Temporal Evidence Routing with Structured Visual Evidence for TimeLogicQA
May 31, 2026Yuyang Sun, Yongliang Wu, Xingyu Zhu +8Temporal Video Understanding Structured Reasoning
Southeast University · National University of Singapore · Independent Researcher +2
CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering
May 18, 2026Mahesh Bhosale, Abdul Wasi, Vishvesh Trivedi +3Claim Verification Video Question Answering
University at Buffalo · 2New York University
Video-Zero: Self-Evolution Video Understanding
May 14, 2026Ruixu Zhang, Deyi Ji, Lanyun Zhu +4Temporal Video Grounding Long-Video Understanding
1Tsinghua University · 2Tencent · 3Tongji University +1
VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA
May 6, 2026Haibin He, Maoyuan Ye, Jing Zhang +2Video Question Answering Video Frame Selection
School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, Hubei, China
VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification
Apr 2, 2026Jiahao Meng, Yue Tan, Qi Xu +9Video-Language Model Evaluation Long-Video QA
PKU · WHU · CASIA +2
LongVidSearch: An Agentic Benchmark for Multi-hop Evidence Retrieval Planning in Long Videos
Mar 15, 2026Rongyi Yu, Chenyuan Duan, Wentao ZhangAI Agent Benchmarks Evidence-Grounded VQA
Peking University & Zhongguancun Academy Beijing, China

Oct 30, 2026J/K move · Enter open · S save

TwinPast: Benchmarking Historical Evidence Use in Streaming Video Understanding with Evidence Contrastive Video Pairs

Haotian Yang, Yong Chen, Cheng Peng, Haobo Wang+3

School of Software Technology, Zhejiang University · HeyGen · Zhejiang University

Evidence-Grounded VQA Streaming Video Understanding Temporal Reasoning in VLMs Video Question Answering Memory-Augmented Video Understanding

Open paper AskPDF arXiv

High accuracy on streaming video benchmarks does not establish whether a model uses visual history. Our review of OVO-Bench and StreamingBench finds that recent frames suffice for 32% of sampled historical questions, while models also answer many questions correctly from the question and options alone. We introduce TwinPast to test whether answers correctly follow changes in history, using 350 human-reviewed video pairs spanning five historical tasks. Each pair holds the recent video context, question, and ordered options fixed while changing critical historical evidence and the correct answer. Each video is evaluated independently, and PairAcc requires correct answers for both histories. We evaluate 34 model and input configurations. For Qwen3-VL-8B and DeepSeek-Flash, historical inputs improve performance on TwinPast, reversing the recent-frame advantage on existing benchmarks. The strongest evaluated streaming system reaches 49.14% PairAcc, compared with 66.57-91.43% for the evaluated general-purpose models. This gap persists across all five tasks. Case studies further show that models select states from the wrong time or contradict recorded event order despite retaining the relevant evidence. These findings highlight the need to connect historical memory and retrieval with reasoning that uses evidence according to the question's temporal references and event relations.