Movens-Zero: Scaling Humanoid Motion Foundation Models with Large-Scale Human Videos
Zhejiang University（浙江大学）；Unitree Robotics（宇树机器人）；Joint Laboratory of Embodied Intelligence, ZJU & Unitree Robotics（浙江大学与宇树机器人联合具身智能实验室）；Bit Oasis；HiThink Research（HiThink研究院）；Microsoft Research（微软研究院）；East China Normal University（华东师范大学）；Peking University（北京大学）；National University of Singapore（新加坡国立大学）
Wendong Bu, Tinghong Ye, Qizhou Wang, Jiacheng Li, Zhiqi Ge, Yuze Lin, Zhongqi Yue, Yi Su, Jingyu Wang, Kai Shen, Jingdong Liu, Chengyuan Deng, Xiaoxuan Chen, X… 展开作者
Wendong Bu, Tinghong Ye, Qizhou Wang, Jiacheng Li, Zhiqi Ge, Yuze Lin, Zhongqi Yue, Yi Su, Jingyu Wang, Kai Shen, Jingdong Liu, Chengyuan Deng, Xiaoxuan Chen, Xin Tan, Jiaming Ji, Wenqiao Zhang, Chenghong Jiang, Tuoyu Li, Siliang Tang, Jun Xiao, Tat-Seng Chua, Yueting Zhuang, Xingxing Wang, Juncheng Li
Scaling humanoid motion foundation models is constrained by the scarcity of diverse, robot-executable data and by the difficulty of jointly learning from heterogeneous multimodal inputs while supporting real-time closed-loop control. We present Movens-5M, constructed from raw Internet videos through clip generation, quality filtering, semantic annotation, motion recovery, and physical refinement with humanoid retargeting and execution verification. It contains 15 million human-motion sequences and 5 million physically executable humanoid-motion sequences spanning over 10,000 hours, aligned with text, RGB video, speech, and music. Building on this data, we introduce Movens-Zero, a scalable understanding-generation-execution architecture that supports joint learning across modalities and real-time closed-loop execution. Task-mixed flow-matching training jointly optimizes a single action expert across seven generation tasks, enabling direct motion generation from text, speech, music, and video. Multimodal Real-Time Chunking connects overlapping chunks under continuously updated instructions and robot states for continuous closed-loop execution. We further introduce Movens-Intent, a four-track benchmark with 8,192 expert-verified condition-motion pairs across text, speech, music, and video. Experiments show consistent gains across all four modalities when scaling execution-verified data from 1% to 100% and action-expert capacity from 64M to 911M parameters, while demonstrating that data quality and cross-modal supervision improve generation and execution.
CoHuB: A Simulation Benchmark for Multi-Humanoid Collaboration
Yonsei University（延世大学）；Gwangju Institute of Science and Technology（光州科学技术院）；University of California, Berkeley（加州大学伯克利分校）；Seoul National University（首尔大学）
HuBE: Cross-Embodiment Human-like Behavior Execution for Humanoid Robots
Department of Mechanical Engineering, The Hong Kong Polytechnic University (PolyU)（机械工程系，香港理工大学（PolyU））；Research Institute for Smart Ageing (RISA), PolyU（智能老龄化研究所以及PolyU）；Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT)（宁波数字孪生研究所，东部技术研究所（EIT））
SPRINT: Efficient Spectral Priors for Humanoid Athletic Sprints
College of Intelligence Science and Technology, National University of Defense Technology（智能科学与技术学院，国防科技大学）；School of Artificial Intelligence and Robotics, Hunan University（人工智能与机器人学院，湖南大学）
Peking University（北京大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shanghai Jiaotong University（上海交通大学）；Fudan University（复旦大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Humanoid Agent via Embodied Chain-of-Action Reasoning with Multimodal Foundation Models for Zero-Shot Loco-Manipulation
Embodied AI and Robotics (AIR) Lab, New York University, New York, USA and NYUAD Center for Artificial Intelligence and Robotics, New York University Abu Dhabi, Abu Dhabi, UAE（纽约大学Embodied AI和机器人实验室及纽约大学阿布扎赫尔人工智能与机器人中心）；Harvard AI and Robotics Lab, Harvard University, Boston, USA（哈佛大学人工智能与机器人实验室）；Department of Computer Science, University College London, London, UK（伦敦大学学院计算机科学系）；Department of Computer Science, University of Liverpool, UK（利物浦大学计算机科学系）；NYUAD Center for Artificial Intelligence and Robotics, New York University Abu Dhabi, Abu Dhabi, UAE（纽约大学阿布扎赫尔人工智能与机器人中心）
Humanoid Factors: Design Principles for AI Humanoids in Human Worlds
School of Computing and Augmented Intelligence, Arizona State University, AZ, USA（计算与增强智能学院，亚利桑那州立大学，亚利桑那州，美国）；School of Manufacturing Systems and Networks, Arizona State University, AZ, USA（制造系统与网络学院，亚利桑那州立大学，亚利桑那州，美国）；Human Systems Engineering, Arizona State University, AZ, USA（人机系统工程，亚利桑那州立大学，亚利桑那州，美国）
A Survey of Behavior Foundation Model: Next-Generation Whole-Body Control System of Humanoid Robots
Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系）；LimX Dynamics；Ningbo Institute of Digital Twin, Eastern Institute of Technology（宁波数字孪生研究院、东部技术研究所）；Department of Data and Systems Engineering, The University of Hong Kong（香港大学数据与系统工程系）；CREATE Lab, EPFL（EPFL CREATE 实验室）；School of System Design and Intelligent Manufacturing, Southern University of Science and Technology（南方科技大学系统设计与智能制造学院）；ZJU-UIUC Institute, Zhejiang University（浙江大学ZJU-UIUC研究院）；INFIFORCE Intelligent Technology Co., Ltd.（INFIFORCE智能科技有限公司）
HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object-Interaction
National University of Singapore（新加坡国立大学）；The University of Hong Kong（香港大学）；SIGS, Tsinghua University（清华大学深圳国际研究生院）；The Hong Kong University of Science and Technology（香港科技大学）；Noitom Robotics（诺亦腾机器人公司）
From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance
University of Sydney（悉尼大学）；BAAI（北京人工智能研究院）；Harbin Institute of Technology（哈尔滨工业大学）；Hong Kong University of Science and Technology（香港科学与技术大学）；Shanghai Jiao Tong University（上海交通大学）；Peking University（北京大学）
iGPC: Generative Motion Priors for Object-Aware Humanoid Interaction
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）；Massachusetts Institute of Technology (MIT)（麻省理工学院）；Minerva Humanoids, Inc.（Minerva Humanoids公司）
KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control
Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信）；Shanghai Jiao Tong University（上海交通大学）；East China University of Science and Technology（东华大学）
WareFly-VLA: A Vision-Language-Action Framework for UAV Navigation and Human Tracking in Smart Warehouses
Center for AI Research, VinUniversity（VinUniversity人工智能研究中心）；College of Engineering and Computer Science, VinUniversity（VinUniversity工程与计算机科学学院）；VinRobotics（VinRobotics公司）
