Scaling robot manipulation models requires large amounts of interaction data, yet collecting diverse real-robot experience remains costly. Human manipulation videos, in contrast, provide abundant and diverse task experience that could potentially benefit robot learning. However, differences in morphology, action spaces, and control mechanisms make human motions unsuitable as direct supervision for robot actions, raising a scientific question: what knowledge in human videos should be transferred across embodiments to robot manipulation? To address this question, we analyze subtask transfer through the lens of causal beams, focusing on which contextual conditions and interaction dependencies should be retained to support local task effects. Based on this perspective, we propose Causal-Beam-Guided Subtask Transfer (CBST). CBST learns manipulation-related representations from human videos and grounds them in task-level semantic variables using robot demonstrations. Within a predefined manipulation model, causal-beam constraints guide contextual information selection by requiring retained assignments to sustain local mechanism outputs while preserving nontrivial responsiveness to retained inputs. The selected semantic information conditions a world-action model, allowing the robot to generate actions from its own observations without requiring human-robot motion correspondence. Experiments on robot manipulation benchmarks show improvements in task success over the corresponding world-action model baselines.
EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow
New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences(模式识别新实验室(NLPR),自动化研究所,中国科学院);School of Artificial Intelligence, University of Chinese Academy of Sciences(人工智能学院,中国科学院大学)
Cross-Embodiment Robot Manipulation via a Unified Hand Action Space
Intelligent Robotics and Vision Lab, University of Texas at Dallas(德克萨斯大学达拉斯分校智能机器人与视觉实验室);Intelligent Robotics and Interactive Systems Lab, Arizona State University(亚利桑那州立大学智能机器人与交互系统实验室)
MV-UMI: A Scalable Multi-View Interface for Cross-Embodiment Learning
Center for Artificial Intelligence and Robotics (CAIR) NYU Abu Dhabi(人工智能与机器人中心(CAIR)纽约大学阿布扎赫德分校);Mechanical Engineering Program, NYU Abu Dhabi(机械工程项目,纽约大学阿布扎赫德分校)
RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation
Beijing Innovation Center of Humanoid Robotics(北京人形机器人创新中心);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);Beijing Academy of Artificial Intelligence(北京人工智能研究院)
EaDex: A Cross-Embodiment Dexterous Manipulation Framework from Low-Cost Demonstrations
Faculty of Robot Science and Engineering, Northeastern University(机器人科学与工程学院,东北大学);Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(深圳先进技术研究所,中国科学院);School of Automation, Nanjing University of Information Science and Technology(自动化学院,南京信息科学技术大学)
The Role of Embodiment in Intuitive Whole-Body Teleoperation for Mobile Manipulation
Computer Science Department, TU Darmstadt(图恩-达姆施塔特大学计算机科学系);University of São Paulo(圣保罗大学);Centre for Cognitive Science, TU Darmstadt(图恩-达姆施塔特大学认知科学中心);Systems AI for Robot Learning, German Research Center for AI (DFKI)(德国人工智能研究中心(DFKI)机器人学习系统AI)
3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model
South China University of Technology(南方科技大学);Tencent Robotics X(腾讯机器人实验室);Hong Kong University of Science and Technology(香港科学与技术大学);Pazhou Laboratory(琶洲实验室)
Collective Learning for Unified Robotic Manipulation via Predictive Dynamics Adaptation
School of Computation, Information and Technology, Technical University of Munich(慕尼黑工业大学计算、信息与技术学院);School of Science and Technology, Nanjing University (Suzhou Campus)(南京大学(苏州校区)科学技术学院)
A Neurorobotic Embodiment for Exploring the Dynamical Interactions of a Spiking Cerebellar Model and a Robot Arm During Vision-based Manipulation Tasks
The Hong Kong Polytechnic University(香港理工大学);Technical University of Denmark(丹麦技术大学)
AM-Bench: A Modular Simulation Suite and Benchmark for Aerial Manipulation Policy Learning
The Robotics Institute, School of Computer Science, Carnegie Mellon University(卡内基梅隆大学计算机学院机器人研究所);Department of Aerospace Engineering, Pennsylvania State University(宾夕法尼亚州立大学航空航天工程系);School of Mechanical Engineering, Kyung Hee University(庆熙大学机械工程学院)
Physics-Driven Data Generation for Contact-Rich Manipulation via Trajectory Optimization
Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology(计算机科学与人工智能实验室(CSAIL),麻省理工学院);Robotics and AI Institute(机器人与人工智能研究院)
SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation
The University of Tokyo(东京大学);ByteDance Seed(字节跳动 Seed);The University of Hong Kong(香港大学);Shanghai Jiao Tong University(上海交通大学);Tsinghua University(清华大学)
Structural Action Transformer for 3D Dexterous Manipulation
MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China(脑启发智能感知与认知国家重点实验室,中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(人工智能研究院,合肥综合性国家科学中心)
OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning
Department of EECS, UC Berkeley(电子工程与计算机科学系,加州大学伯克利分校);GRASP Laboratory, University of Pennsylvania(格拉斯实验室,宾夕法尼亚大学);Department of CS, UT Austin(计算机科学系,得克萨斯大学奥斯汀分校)