Long-Video QA

QA: Question Answering

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 61

All topics

CASE: Cost-Aware Stopping for Efficient Long-Video Agents
Oct 4, 2026Yiming Du, Chenghao Liu, Zhiyuan Liu +4Efficient VLM Inference Video Reasoning
Peking University
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 QA Long-Video QA
FORTE: Adaptive Scoring and Exact Keyframe Selection for Long-Video Question Answering
Sep 30, 2026Haifeng Huang, Biyin Xu, Chunsheng Xin +1Video Frame Selection Long-Video QA
Iowa State University.
LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception
Sep 30, 2026Juyi Lin, Zhiqiang Lao, Jiali Cui +9Audio-Visual QA Long-Video QA
Northeastern University · Futurewei Technologies
Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies
Sep 29, 2026Hui Ren, Lei Fan, Henry Pao +5Multimodal Memory Question Answering
University of Illinois Urbana-Champaign · Amazon.com, Inc.
Watch-Think-Interact: Bootstrapping Long-Horizon Multi-Turn Streaming Video Reasoning with Reinforcement Learning
Sep 29, 2026Ziheng Huang, Yicheng Bao, Xueheng Li +8Streaming Video Understanding Video QA
East China Normal University · University of Science and Technology of China · Xiamen University
Sprout: Building Dynamic Memory While Reasoning for Agentic Video Understanding
Sep 28, 2026Wei Chen, Xuanyu Zheng, Yancheng Long +6Memory-Augmented VLMs Memory-Augmented Video Understanding
HKUST · Kling AI
MetaSampling: Making Frame Samplers Efficient for Long-Video Question Answering
Sep 27, 2026Ashim Dahal, Bikramjit BanerjeeMultimodal Large Language Models Adaptive Sampling
University of Southern Mississippi Hattiesburg, MS, USA
Long-to-Short Video Evidence Reasoning for Grounded Question Answering
Sep 14, 2026Kaiyan Chen, Junbin Xiao, Xun YangTemporal Video Grounding Video QA
University of Science and Technology of China
One Skill Does Not Fit All: Automatic Discovery and Taxonomy-Guided Routing of Frame-Selection Skills for Long-Video Question Answering
Sep 14, 2026Jian Hu, Zixu Cheng, Da Li +3LLM Agent Skill Learning Long-Video QA
Queen Mary University of London · Samsung AI Research Institute · Nanyang Technological University, Singapore
Online Video Agent Harness for Long Video Understanding
Sep 14, 2026Sen Yang, Boqiang Duan, Jing Yang +7Tool-Using Vision-Language Agents Long-Video Understanding
Baidu Inc. · Baidu
Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding
Sep 11, 2026Weitong Cai, Hang Zhang, Yukai Huang +6Memory-Augmented VLMs Efficient VLM Inference
Queen Mary University of London · Independent Researcher · Durham University +2
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
Sep 1, 2026Yijun Chen, Yaqi Zheng, Yanya Li +11Multimodal RAG Efficient Multimodal Inference
Zhejiang University · South China University of Technology · Lenovo Group Limited
From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents
Aug 31, 2026Can Zhang, Baofeng Zhang, Xiaotian Han +5Long-Video Understanding Long-Video QA
Beijing University of Chemical Technology · Baidu, Inc.
NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video
Aug 13, 2026Yuheng Huang, Jianlang Chen, Jiayang Song +6Video Understanding Video-Language Model Evaluation
The University of Tokyo, Tokyo, Japan · Kyushu University, Fukuoka, Japan · Macau University of Science and Technology, Macau, China +2
R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video
Aug 11, 2026Ke Ma, Yamin Mao, Weiming Li +5Egocentric Video QA Video QA
College of Design and Innovation Tongji University Shanghai, China · Samsung R&D Institute China - Beijing Beijing, China · Shanghai Jiao Tong University Shanghai, China +2
REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question Answering
Aug 9, 2026Caijun Yan, Yang Zhou, Meixing Shi +4Video QA Long-Video QA
1Zhejiang University · 2Shanghai AI Laboratory
Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding
Aug 7, 2026Yeeun Choi, Youngbeom Yoo, Joon-Young Lee +2Memory-Augmented VLMs Episodic Memory
Yonsei University · Adobe Research
Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs
Aug 6, 2026Ziling Huang, Shin'ichi SatohMultimodal Large Language Models Long-Video Understanding
National Institute of Informatics, Japan
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
CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding
Jul 27, 2026Jinlong Yang, Wenhao Zhang, Kuanwei Lin +1Tool Use in VLMs Efficient VLM Inference
School of Computer Science, Northwestern Polytechnical University · School of Electronic and Computer Engineering, Peking University · Department of Computer Science and Technology, Tsinghua University
ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning
Jul 21, 2026Santiram Tiwari, Nishant Sinha, Kunal KislayMemory-Augmented VLMs KV Caching
KGraph AI Solutions Pvt. Ltd., Bangalore, India – 560016
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
SLVMBench: Skill Learning from Video Memory
Jul 13, 2026Yudong Yang, Guangzhi Sun, Yixuan Li +1Memory-Augmented VLMs Video-Language Models
Tsinghua University · University of Cambridge
Incentivizing Vision Language Models to Search for Long Video Question Answering
Jul 3, 2026Harsh Goel, S P Sharan, Sahil Shah +4Tool Use in VLMs Long-Video QA
The University of Texas at Austin, Austin, TX, USA
ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA
Jul 2, 2026Minkuk Kim, Suyong Yun, Young Tae Kim +3Efficient VLM Inference Video QA
Kyung Hee University, Republic of Korea · Electronics and Telecommunications Research Institute (ETRI), Republic of Korea
QCA: Query- and Content-Aware Keyframe Selection for Long Video Understanding
Jul 1, 2026Jun Peng, Baiyang Song, Jie Li +4Long-Video Understanding Video Frame Selection
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China · Peng Cheng Laboratory, Shenzhen, P.R. China · School of Electronic and Computer Engineering, Peking University, P.R. China
Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic Reasoning
Jul 1, 2026Yixin Ji, Fanghua Ye, Juntao Li +5Long-Video Understanding Memory-Augmented Video Understanding
1Soochow University · 2Tencent Hunyuan Multimodal Department
Graph it first! Enabling Reasoning on Long-form Egocentric Videos through Scene Graphs
Jun 24, 2026Agnese Taluzzi, Riccardo Santambrogio, Simone Mentasti +2Egocentric Video QA Video QA
Politecnico di Milano, Milan, Italy · Bocconi University, Milan, Italy

Oct 4, 2026, cs.AIJ/K move · Enter open · S save

CASE: Cost-Aware Stopping for Efficient Long-Video Agents

Yiming Du, Chenghao Liu, Zhiyuan Liu, Fangxing Zheng+3

Peking University

Efficient VLM Inference Video Reasoning Long-Video QA

Open paper AskPDF arXiv

Long-video agents can actively gather question-relevant evidence, but they typically leave a central decision implicit: when has the agent seen enough to answer? We propose CASE, a plug-in termination framework that frames this decision as policy-conditioned sequential stopping. At each causal checkpoint, CASE combines an auxiliary multiple-choice assessment of accumulated evidence with the host agent's execution state. From complete native trajectories, we construct a cost-aware target that compares answering now with stopping later along the same search path, accounting jointly for answer correctness and the full cost of continued reasoning. A lightweight Ridge regressor learns this decision gap and produces STOP/CONTINUE decisions. We evaluate three vision-language models with VideoSeek and AVP. On Video-MME, end-to-end accuracy changes by +0.67 percentage points on average while CASE reduces model-token use by 53.63%. The same frozen policies then transfer zero-shot to LongVideoBench and MLVU, with end-to-end accuracy changes of +3.38 and +4.58 points while saving 58.78% and 51.28% of model tokens, respectively. Across all agent-model-benchmark combinations, CASE attains the highest accuracy-efficiency Pareto-frontier coverage among the compared stopping methods (83.3%) at the selected operating points. Online execution preserves this favorable accuracy-efficiency trade-off and additionally reduces measured runtime by 54.1% on average. CASE provides a plug-in termination framework for long-video reasoning agents, enabling them to decide when further evidence acquisition is no longer worthwhile.

Momentum

Related topics

Latest papers 61