user avatar
Yuke Zhu
@yukez
Associate Professor @UTCompSci | Director @NVIDIAAI Co-Leading GEAR | CS PhD @Stanford | Building generalist robot autonomy in the wild | Opinions are my own
Austin, TX
yukezhu.me
Joined August 2008
475
Following
22.2K
Followers
Posts
  • user avatar
    Yuke Zhu
    @yukez
    Apr 14, 2024
    Got a taste of @Tesla's FSD v12.3.4 last night. By no means flawless, but the human-like driving maneuvers (with no interventions) delivered a magical experience. Excited to witness the recipe of scaling law and data flywheel for full autonomy show signs of life in real products.
    468K
  • user avatar
    Yuke Zhu
    @yukez
    Feb 18, 2021
    The game of tenure-track faculty job: ℍ𝕒𝕣𝕕 𝕞𝕠𝕕𝕖: 1st year ℍ𝕖𝕝𝕝 𝕞𝕠𝕕𝕖: 1st year + COVID-19 𝕀𝕟𝕗𝕖𝕣𝕟𝕠 𝕞𝕠𝕕𝕖: 1st year + COVID-19 + No Power/Internet in freezing Texas P.S. It has been great fun to play. What's next?
  • user avatar
    Yuke Zhu
    @yukez
    Jul 30, 2024
    Proud to see our latest progress on Project GR00T featured in Jensen's #SIGGRAPH2024 keynote talk today! We integrated our RoboCasa and MimicGen works into NVIDIA Omniverse and Isaac, enabling model training across the Data Pyramid from real-robot data to large-scale simulations.
    00:00
    47K
  • user avatar
    Yuke Zhu
    @yukez
    Sep 11, 2025
    People who are really serious about robot learning should make their own robot hardware.
    86K
  • user avatar
    Yuke Zhu
    @yukez
    Oct 21, 2024
    The million-dollar question in humanoid robotics is: Can humanoids tap into Internet-scale training data such as online videos due to their human-like physique? Our #CoRL2024 oral paper showed the promise of humanoids learning new skills from single video demonstrations. (1/n)
    00:00
    70K
  • user avatar
    Yuke Zhu
    @yukez
    Sep 5, 2021
    My Robot Learning class @UTCompSci is updated with the latest advances and trends, such as implicit representations, attention architectures, offline RL, human-in-the-loop, and synthetic data for AI. All materials will be public. Enjoy! #RobotLearning cs.utexas.edu/~yukez/cs391r_…
  • user avatar
    Yuke Zhu
    @yukez
    Oct 7, 2019
    New work: we built a meta-learning algorithm for an agent to discover the causal and effect relations from its visual observations and to use such causal knowledge to perform goal-directed tasks. Paper: arxiv.org/abs/1910.01751 Joint work w/ @SurajNair_1 @drfeifei @silviocinguetta
  • user avatar
    Yuke Zhu
    @yukez
    May 28, 2024
    Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at robocasa.ai
    00:00
    141K
  • user avatar
    Yuke Zhu
    @yukez
    Mar 19, 2024
    📢Update announced in today’s #GTC2024 Keynote📢 We are working on Project GR00T, a general-purpose foundation model for humanoid robots. GR00T will enable the robots to follow natural language instructions and learn new skills from human videos and demonstrations. Generalist
    00:00
    212K
  • user avatar
    Yuke Zhu
    @yukez
    Mar 15, 2020
    Heard students say WFH lowers productivity. In 1665, a Cambridge college student had to WFH during a pandemic. He got away from professors and worked on math alone. When he returned, the world knew him as Issac Newton! Good time to think hard in pajamas.
    During a pandemic, Isaac Newton had to work from home, too. He used the time wisely.
    From washingtonpost.com
  • user avatar
    Yuke Zhu
    @yukez
    Feb 23, 2024
    Thrilled to co-lead this new team with my long-time collaborator @DrJimFan. We are on a mission to build transformative breakthroughs in the landscape of Robotics and Embodied Agents. Come join us and shape the future together!
    user avatar
    Jim Fan
    @DrJimFan
    Feb 23, 2024
    Career update: I am co-founding a new research group called "GEAR" at NVIDIA, with my long-time friend and collaborator Prof. @yukez. GEAR stands for Generalist Embodied Agent Research. We believe in a future where every machine that moves will be autonomous, and robots and
    64K
  • user avatar
    Yuke Zhu
    @yukez
    Sep 3, 2019
    Life update: I will be joining @UTAustin as an Assitant Professor in @UTCompSci starting Fall 2020. I am thrilled to continue my research on robot learning and perception as a faculty and look forward to collaborating with the exceptional faculty, researchers, and students at UT.
  • user avatar
    Yuke Zhu
    @yukez
    Mar 3, 2025
    Sharing the slide deck and video recording of my talk "Data Pyramid and Data Flywheel for Robotic Foundation Models" at Princeton Robotics Symposium last November. I discussed the vision of training foundation models on diverse data sources and refining them during deployments.
    25K
  • user avatar
    Yuke Zhu
    @yukez
    Apr 9, 2025
    We took a short break from robotics to build a human-level agent to play Competitive Pokémon. Partially observed. Stochastic. Long-horizon. Now mastered with Offline RL + Transformers. Our agent, trained on 475k+ human battles, hits the top 10% on Pokémon Showdown leaderboards.
    00:00
    51K