Video Large Language Models (Video LLMs) have shown promising capabilities in video comprehension, yet they struggle with tracking temporal changes and reasoning about temporal relationships. While previous research attributed this limitation to the ineffective temporal encoding of visual inputs, our diagnostic study reveals that video representations contain sufficient information for even small probing classifiers to achieve perfect accuracy. Surprisingly, we find that the key bottleneck in Video LLMs' temporal reasoning capability stems from the underlying LLM's inherent difficulty with temporal concepts, as evidenced by poor performance on textual temporal question-answering tasks. Building on this discovery, we introduce the Textual Temporal reasoning Transfer (T3). T3 synthesizes diverse temporal reasoning tasks in pure text format from existing image-text datasets, addressing the scarcity of video samples with complex temporal scenarios. Remarkably, without using any video data, T3 enhances LongVA-7B's temporal understanding, yielding a 5.3 absolute accuracy improvement on the challenging TempCompass benchmark, which enables our model to outperform ShareGPT4Video-8B trained on 28,000 video samples. Additionally, the enhanced LongVA-7B model achieves competitive performance on comprehensive video benchmarks. For example, it achieves a 49.7 accuracy on the Temporal Reasoning task of Video-MME, surpassing powerful large-scale models such as InternVL-Chat-V1.5-20B and VILA1.5-40B. Further analysis reveals a strong correlation between textual and video temporal task performance, validating the efficacy of transferring temporal reasoning abilities from text to video domains.
ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);National Key Laboratory of General Artificial Intelligence, Peking University(北京大学通用人工智能国家重点实验室)
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)
ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models
School of Computer Science and Engineering, Central South University(计算机科学与工程学院,中南大学);Research Center for SCIR, Harbin Institute of Technology(SCIR研究中心,哈尔滨工业大学);NExT Research Center, National University of Singapore(NExT研究中心,新加坡国立大学)
DaMO: A Data-Efficient Multimodal Orchestrator for Temporal Reasoning with Video LLMs
College of Artificial Intelligence, National Yang Ming Chiao Tung University(人工智能学院,阳明交通大学);Institute of Population Health Sciences, National Health Research Institutes(人口健康科学研究所,国家健康研究院);Department of Computer Science, National Yang Ming Chiao Tung University(计算机科学系,阳明交通大学)
Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);Center for Data Science, AAIS, Peking University(北京大学人工智能研究院数据科学中心);Beijing Institute for General Artificial Intelligence(北京通用人工智能研究院)
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)
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)
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))
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);OPPO AI Center, OPPO Inc.(OPPO公司OPPO人工智能中心)
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)
VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(多媒体信息处理国家重点实验室,计算机科学学院,北京大学);Moonshot AI;Nanjing University(南京大学);School of Mathematical Sciences, Peking University(数学科学学院,北京大学)
MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints
Northeastern University(东北大学);The Chinese University of Hong Kong(香港中文大学);Westlake University(西湖大学);ByteDance Seed(字节跳动种子);Peking University(北京大学);NVIDIA(英伟达)