Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning (RL) and verbose chain-of-thought, resulting in substantial computational overhead during both training and inference. Moreover, the mechanisms that control the thinking process in these reasoning models are very limited. In this paper, we use the entropy of the model's output distribution as a signal to study and guide reasoning behavior. We discover that high-quality models exhibit a characteristic pattern of micro-exploration and micro-exploitation cycles, followed by a later entropy peak (i.e., longer thinking) and a lower final entropy, indicating more deliberate exploration and confident convergence (i.e., avoid excessive randomness while the model is exploring or thinking through an answer). We then use these novel, theoretically-grounded insights to introduce V-Reason (Video-Reason), an inference-time optimization method that adapts the value cache of the LMM through a lightweight, trainable controller. Our proposed controller is guided by an entropy-based objective, to tune the model's behavior directly at inference, without using any RL or supervised fine-tuning. Our experiments show that V-Reason significantly outperforms the base instruction-tuned models on many video reasoning datasets, narrowing the gap with RL models to within 0.6% accuracy on average. We achieve this without any training, while offering efficiency benefits: V-Reason uses 58.6% fewer tokens than the RL model. Project Page https://deepaksridhar.github.io/vreason.github.io/
VideoExplorer: Think With Videos For Agentic Long-Video Understanding
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学人工智能学院);Beijing Academy of Artificial Intelligence(北京人工智能研究院);Beijing University of Posts and Telecommunications(北京邮电大学);Hong Kong Polytechnic University(香港理工大学);Peking University(北京大学);University of Trento(特伦托大学)
GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China(清华大学深圳国际研究生院,清华大学,深圳,中国);CSE department, The Chinese University of Hong Kong, Hong Kong,China(中国香港大学计算机科学与工程系,中国香港,中国);Department of Computer Science(计算机科学系);Engineering, The Hong Kong University of Science(工程,香港科学大学)
Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks
DeepWisdom;Tsinghua University(清华大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Renmin University of China(中国人民大学);University of Oxford(牛津大学);National University of Singapore(新加坡国立大学);Xiamen University(厦门大学);Hong Kong University of Science and Technology (GuangZhou)(香港科技大学(广州))
UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks
Lincoln North Star High School(林肯北星高中);The Charter School of Wilmington(威尔明顿 charter 学校);Greenwich High School(格林威治高中);Santa Susana High School(圣塔苏娜高中);UC Berkeley(伯克利大学)
VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
University of California, Berkeley(加州大学伯克利分校);Stanford University(斯坦福大学);University of Toronto(多伦多大学);University of Washington(华盛顿大学);University of Michigan(密歇根大学)
DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
Nanjing University of Posts and Telecommunications(南京邮电大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)
I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning
Beijing Jiaotong University(北京交通大学);HUJING Digital Media & Entertainment Group(汇晶数字媒体与娱乐集团);MAIS Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所MAIS)
Video-CoM: Interactive Video Reasoning via Chain of Manipulations
Mohamed bin Zayed University of AI(穆罕默德·本·扎耶德人工智能大学);University of California Merced(加州梅尔 Ced 大学);Google Research(谷歌研究院);Linköping University(林奈大学);Australian National University(澳大利亚国立大学)
Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level
University of Central Florida(中佛罗里达大学);University of Western Australia(西澳大学);Amazon Web Services(亚马逊网络服务);The University of Texas at Dallas(德克萨斯大学达拉斯分校)
VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection
Beihang University(北京航空航天大学);The University of Hong Kong(香港大学);Shanghai AI Lab(上海人工智能实验室);Central South University(中南大学);Sangfor Technologies Inc.(深信服科技股份有限公司);CUHK(香港中文大学)