Minghuan Liu (original) (raw)

Tuchel and Me!

I am currently a Postdoc at theRPL Lab,UT Austin, working with Prof.Yuke Zhu. Before that I worked as a research scientist at ByteDance Seed-Robotics. I received my Ph.D. in 2024 fromApex Lab atShanghai Jiao Tong University, advised by Prof.Weinan Zhang and Prof.Yong Yu. During my Ph.D., I also spent time in UCSD (24-25, San Diego, US), ByteDance (23-24, Beijing, China) and Sea AI Lab (22-23, Singapore). I received my bachelor's degree fromSouthwest Jiaotong University in 2019. I obtained ByteDance Scholarship in 2022.

Current Interests

• General-purpose robot intelligence, including foundation robot models,large-scale systems, whole-body control,simulation and RL.
• Building robot systems from a full-stack perspective based on extensive experience with humanoids, quadrupeds, robotic arms, and dexterous hands.
• Developing general robot policies by aligning embodiment actions (the robot's 3D state and action space) with world representations (external 3D structure).

I am also actively building agent-based tooling such asAgentMonitor.

1. Apr. 30, 2026
   In-depth analysis onsim-real co-training,continual VLA learning, and zero-shot cross-humanoid controlXHugWBC were accepted by ICML 2026.
2. Jan. 31, 2026
   Cross-humanoid locomotionH-zero and real2sim2realRe3Sim were accepted by ICRA 2026.
3. Sept. 4, 2025
   ManipAsInSim was released.
4. Apr. 11, 2025
   HugWBC was accepted by RSS 2025.
5. Sept. 26, 2024
   MADiff was accepted by NeurIPS 2024.
6. Sept. 6, 2024
   Three papers,VBC,ACE, andGenSim2, were accepted by CoRL 2024.