Researcher

Tongzhou Mu

Rhoda AI · Mountain View, California, United States

Role and affiliation as stated on the event page, organisation cross-checked against the live LinkedIn profile. Publication count is the dominant co-author cluster among 20 arXiv papers published under this name.

Recent work

• Scaling Cross-Embodiment World Models for Dexterous Manipulation
• Towards Embodiment Scaling Laws in Robot Locomotion
• Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
• Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control
• When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?
• Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

From the resolved cluster. Most recent submission 2025-11-03.

Works on

Papers in this index

Matched on author name across this corpus only. Common names can collide, so tell us if one is wrong.