Skip to content
View Tonghe-Zhang's full-sized avatar
49 followers · 50 following

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Pull Sharkx2Achievement: Pair ExtraordinaireAchievement: Starstruckx2

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Pull Sharkx2Achievement: Pair ExtraordinaireAchievement: Starstruckx2

Block or report Tonghe-Zhang

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Tonghe-Zhang/README.md

✨ Welcome to My Homepage!

🔭 About Me

My name is Tonghe Zhang (he/him). It’s pronounced Tung-ho Zang.

I work on scalable robot learning.

My goal is to build robot learning systems that are robust, efficient, and dexterous.

Previously, I studied RL for visual-language-action models, humanoid loco-manipulation, generative modeling and statistical reinforcement learning theory.

👯 Get in Touch

I'm currently a graduate student in Robotics at the Robotics Institute, Carnegie Mellon University. Feel free to reach out for collaborations or just to chat!

Here is my email: [email protected] and my personal website.

Pinned Loading

  1. ReinFlow/ReinFlow ReinFlow/ReinFlow Public

    [NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., pi0, pi0.5. Fully open-sourced.

    Python 267 25

  2. Awesome-Flow-RL-Papers Awesome-Flow-RL-Papers Public

    A collection of paper/projects that trains flow matching model/policies via RL.

    372 13

  3. RLinf/RLinf RLinf/RLinf Public

    RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

    Python 2.8k 342

  4. LeCAR-Lab/BFM-Zero LeCAR-Lab/BFM-Zero Public

    BFM_Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning

    Python 477 29