Training video-language models is often prohibitively expensive due to the high cost of processing long frame sequences and the limited availability of annotated long videos. We present VideoWeave, a simple yet effective approach to improve data efficiency by constructing synthetic long-context training samples that splice together short, captioned videos from existing datasets. Rather than modifying model architectures or optimization objectives, VideoWeave reorganizes available video-text pairs to expand temporal diversity within fixed compute. We systematically study how different data composition strategies like random versus visually clustered splicing and caption enrichment affect downstream performance on downstream video question answering. Under identical compute constraints, models trained with VideoWeave achieve higher accuracy than conventional video finetuning. Our results highlight that reorganizing training data, rather than altering architectures, may offer a simple and scalable path for training video-language models. We link our code for all experiments here.
VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modeling
Nanjing University(南京大学);Institute of Artificial Intelligence, China Telecom (TeleAI)(中国电信人工智能研究院(TeleAI));Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning
The Hong Kong University of Science and Technology(香港科技大学);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);University of Electronic Science and Technology of China(电子科技大学)
HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks
Sun Yat-Sen University(中山大学);Alibaba Group(阿里巴巴集团);Peng Cheng Laboratory(鹏城实验室);Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology(广东省消防科学与智能应急技术重点实验室)
MotionAtlas: Detailed Region Captioning for Motion-Centric Videos
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Shanghai Jiao Tong University(上海交通大学);Nanyang Technological University(南洋理工大学);Peking University(北京大学);Wuhan University(武汉大学);Beijing Jiaotong University(北京交通大学)
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);OpenGVLab, Shanghai AI Laboratory(上海人工智能实验室 OpenGVLab);The University of Hong Kong(香港大学);Nanjing University(南京大学)
Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding
City University of Hong Kong(香港城市大学);University of Science and Technology of China(中国科学技术大学);Tianjin University(天津大学);Nanjing University(南京大学);Zhejiang University(浙江大学);The Institute of Artificial Intelligence (TeleAI), China Telecom(中国电信人工智能研究所(TeleAI))
StateTrace: An Object-Centric Framework for Hidden-State Spatiotemporal Reasoning in Long Videos
University of California, San Diego(加利福尼亚大学圣地亚哥分校);The University of Sydney(悉尼大学);Central South University(中南大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));SenseTime Research(商汤科技研究院)
EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University(北京未来区块链与隐私计算先进创新中心,人工智能学院,北京航空航天大学);Hangzhou International Innovation Institute, Beihang University(杭州国际创新研究院,北京航空航天大学);Paradigm Inc.(4Paradigm公司)
Decoupled Object-Centric Video Understanding for Generating Robotic Manipulation Commands
School of Information Science, Japan Advanced Institute of Science and Technology(日本北陆先端科学技术大学院大学信息科学学院);University of Engineering and Technology, Vietnam National University(越南国立大学工程与技术大学);Department of Robotics, Hanyang University(汉阳大学机器人学系)
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)
EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos
Fudan University(复旦大学);The University of Tokyo(东京大学);Zhejiang University(浙江大学);Hong Kong University of Science and Technology(香港科技大学);Nanjing University(南京大学);Shanghai Jiao Tong University(上海交通大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)