Causal Reasoning in Videos

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 34

All topics

VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction
Oct 5, 2026Qiutong Chen, Yuchan Guo, Zhenlong Yuan +10Video Prediction Causal Reasoning in Videos
Nankai University · Carnegie Mellon University · Xiaohongshu Inc. +4
EMBER-Bench: Benchmarking Cross-Event Causal Memory in Long-Horizon Embodied Tasks
Oct 4, 2026Aoyang Cai, Boning Zhao, Shaoxuan Xie +5Next-Action Prediction Embodied QA
Tsinghua University · Beijing Academy of Artificial Intelligence · The University of Hong Kong
ThinkV2V: Unleashing the Reasoning Capability of MLLMs for Instruction-Guided Video Editing
Sep 29, 2026Donghao Zhou, Haoyang He, Fan Zhang +10Video Editing Benchmarks Video Diffusion Models
The Ohio State University
Causal-EVC: Breaking Emotional Spurious Causality via Spatiotemporal Grounding and Counterfactual Intervention
Sep 29, 2026Cheng Ye, Weidong Chen, Peipei Song +1Video Captioning Multimodal Emotion Recognition
University of Science and Technology of China, Hefei
When Should the Count Change? Learning State Maintenance for Causal Video Counting
Sep 28, 2026Pengyiang Liu, Dongyue Lyu, Junbo Niu +3Streaming Video Understanding State Tracking
Beihang University · Peking University
StoryEngine: A State-Grounded Agentic Framework for Video Storytelling
Sep 27, 2026Yingrui Wang, Zeqing Wang, Yeying JinLong Video Generation Agentic Video Generation
Tencent · National University of Singapore
ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding
Sep 7, 2026Chia-Hui Chen, Shih-Ying Yeh, Fu-En Yang +2Streaming Video Understanding Video Anomaly Detection
National Tsing Hua University, Hsinchu, Taiwan · NVIDIA, Taipei, Taiwan
Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning
Sep 1, 2026Zixuan Wang, Yixin Hu, Wen Li +4Physical Consistency in Video Generation Video Diffusion Models
College of Electronics and Information Engineering, Sichuan University, Chengdu, 610064, China · School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731 · School of Computer Science, University of Adelaide, 5005, Adelaide, Australia +2
SocialReasonBench: A Video-QA Benchmark for Social Reasoning with Counterfactual Narrative Videos
Aug 31, 2026Zheyu Huang, Zijing Shi, Haozhe Luo +4Video QA Multimodal Reasoning
AAII, University of Technology Sydney · Northeastern University · Fudan University +1
FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding
Aug 11, 2026Fufangchen Zhao, Jinhu Fu, Jiachen Lei +3Counterfactual Evaluation Video QA
State Key Laboratory of Networking and Switching Technology, BUPT · AMAP, Alibaba Group
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
Aug 10, 2026Diandian Zhang, Tingyu Song, Lin Fu +2VLM Evaluation Video Generation
Zhejiang University · UCAS · Tongji University +1
EgoSafe: A First-Person Mobile-Captured Benchmark for Visual Safety Understanding
Jul 29, 2026Yuyun Chen, Tianao Li, TianQuan Feng +4Egocentric Video Understanding Video Reasoning
South China University of Technology · Beihang University
Thinking in Video: Can Video Generators Really Reason About the Real World?
Jul 20, 2026Yongheng Zhang, Guang Yang, Ruihan Hou +12Video Reasoning Causal Reasoning in Videos
Central South University · Tencent · Tsinghua University
Benchmarking Dynamic Affective Reasoning: A Viewer-Centric Video Emotion Dataset
Jul 11, 2026Zhiyan Zhang, Peipei Song, Jinpeng Hu +3Video Reasoning Causal Reasoning in Videos
University of Science and Technology of China, Hefei, China · Hefei University of Technology, Hefei, China
Learning to Deny: Action Denial in Multimodal Large Language Models
Jun 30, 2026Raiyaan Abdullah, Shehreen Azad, Yogesh Singh RawatMultimodal Large Language Models Causal Reasoning in Videos
Institute of Artificial Intelligence, University of Central Florida, USA
APT: Atomic Physical Transitions for Causal Video-Language Understanding
Jun 17, 2026Shang Wu, Haoran Lu, Songling Liu +6VLM Adaptation Causal Reasoning in Videos
Northwestern University · Dolby Laboratories
CausalMotion: Structured Physical Reasoning as Keyframe and Trajectory Guidance for Training-Free Video Generation
Jun 12, 2026Sihan Zhuang, Xinyuan Chen, Tianfan Xue +1Physical Consistency in Video Generation Diffusion Model Guidance
Shanghai Artificial Intelligence Laboratory · ShanghaiTech University · Work done during an internship at Shanghai AI Laboratory. +1
Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA
Jun 8, 2026Zhou Du, Hamid Krim, Xiao Wu +3Causal Representation Learning Video QA
Graduate School of Informatics, Nagoya University, Nagoya 464-8601, Japan · Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC 27695, USA · School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611730, China +1
CACR:Reinforcing Temporal Answer Grounding in Instructional Video via Candidate-Aware Causal Reasoning
Jun 7, 2026Muge Qi, Rong Fu, Pengbin Feng +7Temporal Video Grounding Video Understanding
National Biomedical Imaging Center, Peking University, Beijing, China · University of Macau, Macau, China · University of Southern California, Los Angeles, USA +3
SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence
May 29, 2026Yulu Pan, Han Yi, Seongsu Ha +4Sports Video Analysis AI Agent Benchmarks
University of North Carolina at Chapel Hill, Chapel Hill, NC, USA · Northeastern University, Boston, MA, USA
YoCausal: How Far is Video Generation from World Model? A Causality Perspective
May 28, 2026You-Zhe Xie, Yu-Hsuan Li, Jie-Ying Lee +3Video Diffusion Models Causal World Models
National Yang Ming Chiao Tung University · Shanda AI Research Tokyo
DMC-CF: Dynamic Multimodal CounterFactual QA benchmark for Causal Reasoning
May 28, 2026Junzhe Zhang, Huixuan Zhang, Guirong Wang +5Counterfactual Evaluation Counterfactual Reasoning in Language Models
Wangxuan Institute of Computer Technology, Peking University · Alibaba Group
What-If World: A Causal Benchmark for General World Models in Embodied Scenarios
May 26, 2026Kunlin Cai, Rui Song, Jinghuai Zhang +7Physical Consistency in Video Generation Causal World Models
1UCLA · University of Tennessee · 3Amazon
CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models
May 22, 2026León Begiristain, Olaf Dünkel, Adam KortylewskiCounterfactual Evaluation Physical Consistency in Video Generation
University of Freiburg · Freiburg im Breisgau, Germany · Max Planck Institute for Informatics +3
CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
May 22, 2026Mingfang Zhang, Jingjing Pan, Ashutosh Kumar +7VLM Evaluation Temporal Video Grounding
Woven by Toyota · The University of Tokyo
MotiMotion: Motion-Controlled Video Generation with Visual Reasoning
May 21, 2026Lee Hsin-Ying, Hanwen Jiang, Yiqun Mei +3Physical Consistency in Video Generation Image-to-Video Generation
University of California, Merced · Adobe Research
Entity-Centric World Models: Interaction-Aware Masking for Causal Video Prediction
May 14, 2026Santosh Kumar PaidiWorld Model Learning Causal World Models
Genentech, Inc.
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
May 11, 2026Keming Wu, Yijing Cui, Wenhan Xue +11World Models Video Reasoning
Tsinghua University · Nanyang Technological University · Hong Kong University of Science and Technology (Guangzhou) +2
Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
May 10, 2026Jiafeng Liang, Zhihao Zhu, Zihan Zhang +7Causal Discovery Multimodal Large Language Models
Harbin Institute of Technology · Harvard University · Peking University +2
Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios
May 7, 2026Peizheng Yan, Yu Zhao, Liang Xie +3Retrieval-Augmented Generation Streaming Video Understanding
Tianjin Key Lab of Intelligent Unmanned Swarm Tech & System Tianjin University Tianjin, China · Institute of Computing and Intelligence Harbin Institute of Technology (Shenzhen) Shenzhen, China · Tianjin Artificial Intelligence Innovation Center Tianjin, China +2

Oct 5, 2026, cs.CVJ/K move · Enter open · S save

VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction

Qiutong Chen, Yuchan Guo, Zhenlong Yuan, Haobo Yang+9

Nankai University · Carnegie Mellon University · Xiaohongshu Inc.+4

Video Prediction Causal Reasoning in Videos

Open paper AskPDF arXiv

Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in video understanding, yet their reliance on retrospective summarization and text-centric priors often limits their ability to bridge unobserved causal transitions when applied to Video Event Prediction (VEP). To address this, we propose VepAgent, an agentic framework that integrates causal-transition reasoning with tool-augmented reinforcement learning (RL) for robust VEP. Unlike prior methods that passively project future trajectories from historical dependencies, our approach explicitly models the logical progression from terminal observed states to future events. Specifically, we first construct futurebench-4K, a high-quality chain-of-thought dataset for supervised fine-tuning (SFT) that effectively bridges the causal-logic gap by structuring the deduction of unobserved intermediate states. Subsequently, we develop a diagnostic tool library integrating state tracking, frame retrieval, and region magnification, enabling the agent to dynamically augment reasoning with external tools to recover missing spatio-temporal evidence and resolve visual ambiguities during inference. Moreover, we propose a composite reward mechanism that jointly optimizes prediction accuracy, causal coherence, and reliable prior, compelling the agent to rely on genuine visual grounding rather than superficial textual similarities. Extensive evaluations on FutureBench and NEPBench datasets demonstrate that our method achieves state-of-the-art performance, significantly outperforming larger MLLMs and validating the empirical effectiveness of our agentic, future-oriented reasoning paradigm.

Momentum

Related topics

Latest papers 34