Cover Image

RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Songming, Li, Bangguo, Ma, Kai, Wu, Lingxuan, Tan, Hengkai, Ouyang, Xiao, Su, Hang, Zhu, Jun
Format:	Preprint
Published:	2026
Subjects:	Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
by: Liu, Songming, et al.
Published: (2024)

H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation
by: Bi, Hongzhe, et al.
Published: (2025)

Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning
by: Tan, Hengkai, et al.
Published: (2024)

UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies
by: Gupta, Harsh, et al.
Published: (2025)

ManiBox: Enhancing Embodied Spatial Generalization via Scalable Simulation Data Generations
by: Tan, Hengkai, et al.
Published: (2024)

MV-UMI: A Scalable Multi-View Interface for Cross-Embodiment Learning
by: Rayyan, Omar, et al.
Published: (2025)

Mirage: Cross-Embodiment Zero-Shot Policy Transfer with Cross-Painting
by: Chen, Lawrence Yunliang, et al.
Published: (2024)

DexGrasp-Zero: A Morphology-Aligned Policy for Zero-Shot Cross-Embodiment Dexterous Grasping
by: Wu, Yuliang, et al.
Published: (2026)

Scaling Cross-Embodiment World Models for Dexterous Manipulation
by: He, Zihao, et al.
Published: (2025)

VLN-Game: Vision-Language Equilibrium Search for Zero-Shot Semantic Navigation
by: Yu, Bangguo, et al.
Published: (2024)

Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing
by: Li, Zhiyuan, et al.
Published: (2026)

Towards Embodiment Scaling Laws in Robot Locomotion
by: Ai, Bo, et al.
Published: (2025)

GET-Zero: Graph Embodiment Transformer for Zero-shot Embodiment Generalization
by: Patel, Austin, et al.
Published: (2024)

PANav: Toward Privacy-Aware Robot Navigation via Vision-Language Models
by: Yu, Bangguo, et al.
Published: (2024)

FastUMI-100K: Advancing Data-driven Robotic Manipulation with a Large-scale UMI-style Dataset
by: Liu, Kehui, et al.
Published: (2025)

Mobile UMI: Cross-View Diffusion Policy with Decoupled Kinematics for Mobile Manipulation
by: Huang, Haoran, et al.
Published: (2026)

In-the-Wild Compliant Manipulation with UMI-FT
by: Choi, Hojung, et al.
Published: (2026)

Pushing the Limits of Cross-Embodiment Learning for Manipulation and Navigation
by: Yang, Jonathan, et al.
Published: (2024)

Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization
by: Bohlinger, Nico, et al.
Published: (2025)

H-Zero: Cross-Humanoid Locomotion Pretraining Enables Few-shot Novel Embodiment Transfer
by: Lin, Yunfeng, et al.
Published: (2025)

MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfer
by: Zhi, Heng, et al.
Published: (2026)

X-Nav: Learning End-to-End Cross-Embodiment Navigation for Mobile Robots
by: Wang, Haitong, et al.
Published: (2025)

LEGATO: Cross-Embodiment Imitation Using a Grasping Tool
by: Seo, Mingyo, et al.
Published: (2024)

Toward Embodiment Equivariant Vision-Language-Action Policy
by: Chen, Anzhe, et al.
Published: (2025)

AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation
by: Tan, Hengkai, et al.
Published: (2025)

Learning Adaptive Cross-Embodiment Visuomotor Policy with Contrastive Prompt Orchestration
by: Zhang, Yuhang, et al.
Published: (2026)

XMoP: Whole-Body Control Policy for Zero-shot Cross-Embodiment Neural Motion Planning
by: Rath, Prabin Kumar, et al.
Published: (2024)

OmniUMI: Towards Physically Grounded Robot Learning via Human-Aligned Multimodal Interaction
by: Luo, Shaqi, et al.
Published: (2026)

LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer
by: Zha, Lihan, et al.
Published: (2026)

OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning
by: Ji, Guanhua, et al.
Published: (2025)

Latent Action Diffusion for Cross-Embodiment Manipulation
by: Bauer, Erik, et al.
Published: (2025)

CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local Navigation
by: Yang, Kai, et al.
Published: (2025)

HuBE: Cross-Embodiment Human-like Behavior Execution for Humanoid Robots
by: Lyu, Shipeng, et al.
Published: (2025)

Vidarc: Embodied Video Diffusion Model for Closed-loop Control
by: Feng, Yao, et al.
Published: (2025)

Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
by: Luo, Hao, et al.
Published: (2026)

Vidar: Embodied Video Diffusion Model for Generalist Manipulation
by: Feng, Yao, et al.
Published: (2025)

Data Analogies Enable Efficient Cross-Embodiment Transfer
by: Yang, Jonathan, et al.
Published: (2026)

LACE: Latent Visual Representation for Cross-Embodiment Learning
by: Jang, Yoo Sung, et al.
Published: (2026)

RoboWheel: A Data Engine from Real-World Human Demonstrations for Cross-Embodiment Robotic Learning
by: Zhang, Yuhong, et al.
Published: (2025)

UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception
by: Wang, Ziming
Published: (2026)