Skip to content
View StarCycle's full-sized avatar
29 followers · 16 following

Achievements

Achievement: Pull Sharkx2Achievement: Pair ExtraordinaireAchievement: StarstruckAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx2Achievement: Pair ExtraordinaireAchievement: StarstruckAchievement: Quickdraw

Block or report StarCycle

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, 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
StarCycle/README.md

Hi, I am Zhuoheng Li 👋

I work in an intersection of AI, robotics, and space exploration. I build systems for you ヾ(^▽^*)) so feel free to ask me if you have any question!

  • ⚡ Recent works: Train a generalized policy / video generation model for robotics manipulation.
    • GR1-Training is the current SOTA policy on CALVIN benchmark for multi-task robotics manipulation (ABC-D split).
    • MimicTest integrates some of my policies, including Florence Policy developed on Microsoft's Florence2 VLM, which is trained with VQA, OCR, detection and segmentation tasks on 900M images.
      • Unlike OpenVLA and RT2, Florence2 is much smaller with 0.23B (Florence-2-base) or 0.7B (Florence-2-large) parameters.
      • Florence policy directly generates continuous actions with a linear action head / a diffusion transformer action head.
    • I am contributing to the HuggingFace LeRobot toolbox, including integration of the Florence policy.
    • I am participating the 1x challenge to train video generation model for robotics manipulation.
    • I developed some VLM ranged from 2B~8B, please check My HuggingFace Page.
  • 📫 Reach me: My email or Wechat: StarRingSpace.
  • 🌱 My profile: Linkedin and my personal website.

Pinned Loading

  1. EDiRobotics/mimictest EDiRobotics/mimictest Public

    A simple testbed for robotics manipulation policies

    Python 24 3

  2. EDiRobotics/GR1-Training EDiRobotics/GR1-Training Public

    Reimplementation of GR-1, a generalized policy for robotics manipulation.

    Python 95 3

  3. GraphExtract GraphExtract Public

    Extract inter-procedural control flow graph from C/C++ source code for graph neural networks

    Python 4 1

  4. SimplePPO SimplePPO Public

    Simple PPO implementation with ~270 lines of code. Support parallel sampling and multiple GPU

    Python 3

  5. EmbodiedAI-Reading-List-For-Lists EmbodiedAI-Reading-List-For-Lists Public

    It's not a list of papers, but a list of paper reading lists...

    64 3

  6. Citation2Prompt Citation2Prompt Public

    Fetch citations and abstracts of a Google Scholar paper and generate prompt for LLM

    Jupyter Notebook 16