Cross-Embodiment Transfer

Follow this topic Ask about this topic

Latest papers 39

10 papers in the last four weeks, up 233% on the four weeks before. 0.1% of all new papers.

All topics

TRACE: Efficient Transfer Learning for Neural Whole-Body Control Across Humanoid Embodiments
Oct 13, 2026Qingyu Lan, Zhihao Tian, Zifan Wang +1Humanoid Robot Control Cross-Embodiment Robot Learning
The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology
CrossPortrait: Cross-Species Portrait Animation via Adversarial Motion Alignment
Oct 13, 2026Gezhong Pan, Zhe Li, Yunfan Tao +7Cross-Embodiment Transfer Domain-Adversarial Learning
University of Science and Technology of China · Shenzhen Loop Area Institute · Huawei Technologies Ltd. +1
LACE-CRAFT: Robot Co-Design with Actor Inheritance and Blackboard Collaboration
Oct 7, 2026Yuhan Wen, Jiawei Wang, Qixuan Zhang +3Robot Morphology-Control Co-Design Robot Policy Adaptation
Deemos Corporation · ShanghaiTech University · University of Cambridge +2
EmbPASS: Towards Cross-Embodiment Open Panoramic Segmentation
Oct 2, 2026Pujun Guo, Yuanfan Zheng, Fei Teng +5Semantic Segmentation Cross-Embodiment Transfer
School of Artificial Intelligence and Robotics, Hunan University, China · National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, China
CrossBFM: Distilling a Shared Latent Behavior Space Across Humanoid Embodiments
Sep 29, 2026Tan-Dzung Do, Tuan Dat Phuong, Nico Bohlinger +6Robot Foundation Models Cross-Embodiment Robot Learning
VinRobotics · National University of Singapore · TU Darmstadt +3
Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion Models
Sep 29, 2026Zhiyuan Li, Wenyan Yang, Pekka Marttinen +1Motion Retargeting Generative Modeling
Department of Electrical Engineering and Automation, Aalto University, Finland · Department of Computer Science, Aalto University, Finland
EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation
Sep 29, 2026Jin Chen, Yiming Jiang, Chongyang Xu +8Humanoid Loco-Manipulation Whole-Body Robotic Manipulation
OpenDriveLab at The University of Hong Kong · Alibaba Group · Shanghai Innovation Institute +4
Intelligence Across Embodiments
Sep 22, 2026Bo Ai, Henrik I. Christensen, Hao SuCross-Embodiment Robot Learning Embodied AI
Stanford University · University of California San Diego · Sudo AI GmbH
H2RBench: A Real-to-Sim Benchmark for Evaluating Human-to-Robot Transfer
Sep 21, 2026Chuyang Xiao, Haotian Zhan, Sriram Krishna +4Cross-Embodiment Robot Learning Robotic Manipulation
Robotics Institute, Carnegie Mellon University · University of Michigan · Toyota Research Institute
Whole-Body UMI: Transferring UMI Manipulation Skills to Humanoid Whole-Body Manipulation via Real-Time Motion Generation
Sep 19, 2026Yuxuan Nai, Leixin Chang, Liangjing Yang +2Whole-Body Robotic Manipulation Robot Motion Generation
Zhejiang University · Hong Kong Embodied AI Lab · Mondo Robotics +1
Latent Policy Steering: An Efficient and Flexible Framework for Cross-Embodiment Transfer
Sep 18, 2026Yiqi Wang, Mrinal Verghese, Jeff SchneiderCross-Embodiment Transfer Visuomotor Policy Learning
Robotics Institute, School of Computer Science, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, United States
Improving Cross-embodiment Transfer in Latent Action Models with Action-Similarity Supervision
Sep 17, 2026Maxime Alvarez, Renzo Caballero, Tatsuya Matsushima +2Latent Action Learning Robotic Manipulation
Graduate School of Engineering, The University of Tokyo
ZETA: A Controlled Study of Zero-Shot Cross-Embodiment VLA Transfer for Tabletop Manipulation
Sep 2, 2026Mi Yan, Wenhao Zhang, Zhiqi Zhang +14Cross-Embodiment Transfer Vision-Language-Action Models
Galbot · CFCS, School of CS, Peking University · Peking University +4
Towards Zero-Shot Transfer Across Embodiments For Driving VLAs
Sep 2, 2026Caio Azevedo, Stefano Sabatini, Sascha Hornauer +1Autonomous Driving Vision-Language-Action Models
1 ´Ecole des Mines de Paris, France · 2Stellantis, France
CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators
Aug 27, 2026Kechen Liu, Ola ShorinwaAction-Conditioned Video Generation Action-Conditioned World Models
Princeton University
XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?
Aug 6, 2026Yixiang Chen, Jiabing Yang, Yuan Xu +10World Model Learning Action-Conditioned World Models
New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Shandong University +1
Cross-Embodiment Transfer via Behavior-Aligned Representations
Jul 30, 2026Ajay Sridhar, Jensen Gao, Jonathan Yang +3Representation Learning Vision-Language-Action Models
1Stanford University · 2Toyota Research Institute
From Passive Video to Editable Experience: Physically Grounded Experience Synthesis for Embodied Intelligence
Jul 29, 2026Jia LuoSynthetic Data Generation for Robotics Robotic Manipulation
Huazhong University of Science and Technology
Ego-Dynamics-Augmented World Model for Autonomous Driving with Zero-Shot Cross-Embodiment Adaptation
Jul 15, 2026Zhidong Wang, Jingsong Liang, Zirui Li +3World Model Learning End-to-End Autonomous Driving
School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore · Collaborative Initiative, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore · College of Computing and Data Science, Nanyang Technological University, Singapore
Motion4Motion: Motion Transfer Across Subjects at Inference
Jul 13, 2026Ling-Hao Chen, Zixin Yin, Duomin Wang +2Cross-Embodiment Transfer
Tsinghua University, China · Stepfun, China · The Hong Kong University of Science and Technology, China
Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning
Jun 27, 2026Shuo Cheng, Chuye Zhang, Alfred Cueva +3Robot Skill Learning Generalization in Robotic Manipulation
Georgia Institute of Technology · NVIDIA Corporation
Cloak: Zero-Shot Cross-Embodiment Manipulation by Masking the End-Effector from the VLA
Jun 22, 2026Michael Piseno, Guy Tevet, C. Karen LiuZero-Shot Robotic Manipulation Language-Conditioned Robot Manipulation
Stanford University
KITE: Decoupling Kinematics and Interaction for Zero-Shot Cross-Embodiment Manipulation
Jun 20, 2026Qianxu Wang, Kuan FangZero-Shot Robotic Manipulation Generalization in Robotic Manipulation
Cornell University
A Scalable Embodied Intelligence Platform for Seamless Real-to-Sim-to-Real Transfer of Household Mobile Manipulation Tasks
Jun 17, 2026Kui Yang, Xianlei Long, Haoxuan Li +2Mobile Manipulation Robotics Simulation
School of Computer Science, Chongqing University, No. 55 Daxuecheng South Road, Shapingba District, Chongqing, 401331, Chongqing, China. · R&D Department, Lumos Robotics Technology (Suzhou) Co., Ltd, No. 17 345 Baodai East Road, Wuzhong District, Suzhou, 215128, Jiangsu, China.
Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time
Jun 14, 2026Jeongeun Park, Juhan Park, Taekyung Kim +3Test-Time Adaptation Visuomotor Policy Learning
NAVER AI Lab · Korea University
Transferring Contact, Not Just Motion: Compliant Grasping Across Dexterous Hands
Jun 14, 2026Soofiyan Atar, Yao-Ting Huang, Michael YipRobotic Grasping Dexterous Manipulation
Department of Electrical and Computer Engineering University of California San Diego, United States
EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment
Jun 11, 2026Shihefeng Wang, Kangchen Lv, Mingrui Yu +1Robot Skill Learning Generalization in Robotic Manipulation
Department of Automation, Tsinghua University · Beijing Key Laboratory of Embodied Intelligence Systems · Institute for Embodied Intelligence and Robotics, Tsinghua University
Bionic Human-Motion Style Transfer for Physically Executable Whole-Body Control of Humanoid Robots
Jun 2, 2026Tianchen Huang, Mingkuan Zhao, Yang Gao +8Humanoid Robot Control Human Motion Generation
Institute of Humanoid Robots, Department of Precision Machinery and Precision Instrumentation, University of Science and Technology of China, Hefei, Anhui, 230026, China. · School of Computer Science and Technology, Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, 710049, China. · School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, 730000, China.
X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models
May 24, 2026Boyu Li, Chaoyi Xu, Haoqi Yuan +5Cross-Embodiment Robot Learning Diffusion Policy
1SKL-MAIS, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · 3Beijing Academy of Artificial Intelligence +2
Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking
May 22, 2026Ming Yang, Tao Yu, Feng Li +1Humanoid Robot Control Cross-Embodiment Robot Learning
LimX Dynamics

Oct 13, 2026J/K move · Enter open · S save

TRACE: Efficient Transfer Learning for Neural Whole-Body Control Across Humanoid Embodiments

Qingyu Lan, Zhihao Tian, Zifan Wang, Junwei Liang

The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology

Humanoid Robot Control Cross-Embodiment Robot Learning Cross-Embodiment Transfer Whole-Body Control Humanoid Motion Tracking Data-Efficient Robot Learning

Open paper AskPDF arXiv

Humanoid behavior foundation models (BFMs) enable diverse whole-body control, but adapting a pretrained controller to a new embodiment remains challenging because of kinematic and dynamic mismatch. We present TRACE, a framework for efficient cross-embodiment adaptation that preserves pretrained motion representations while specializing feedback control to the target robot.TRACE first injects kinematic priors into input and output projection layers and aligns nominal joint dynamics to reduce embodiment mismatch and support stable fine-tuning. It then combines encoder distillation with low-rank reinforcement learning on a compact, quality-screened motion set, using a two-phase curriculum to establish stable tracking before refining difficult motions. We apply TRACE to transfer SONIC from Unitree G1 to Unitree H2 using 10 million motion frames and approximately eight hours of training on a single RTX PRO 6000 GPU, at less than 0.1% of the GPU-hour cost of training SONIC from scratch. The adapted controller achieves 96.08% success on 67,953 evaluation motions under a height-scaled tracking criterion. Real-robot demonstrations span dynamic motion tracking and whole-body teleoperation, with collected demonstrations supporting downstream vision-language-action policy post-training. These results demonstrate practical reuse of a pretrained humanoid controller across robots with different body scales and dynamics.