My goal throughout my PhD has been to take robots out of the lab and into the real world. It was so special to be a part of this effort and see this dream become reality! Excited to keep pushing model capabilities—and, of course, keep playing with robots 🤖

last but not least, I'm excited to let people know that I'm joining PI as a full-time RS once I graduate this May!

We built an AI model to simulate how a fruit fly walks, flies and behaves – in partnership with HHMI | Janelia. 🪰 Our computerized insect replicates realistic motion, and can even use its eyes to control its actions. Here’s how we developed it – and what it means for science. 🧵

What is the RL equivalent of "next-token prediction"? Our answer is offline *goal-conditioned RL*. We also made a clean, easy-to-use benchmark. Come see our poster at #387 tomorrow morning! (4/26 Sat, 10am-12:30pm) Project page: seohong.me/projects/ogben…

Humanoid robots should not be black boxes 🔒 or budget-busters 💸! Meet Berkeley Humanoid Lite! ▹ 100% open source & under $5k ▹ Prints on entry-level 3D printers—break it? fix it! ▹ Modular cycloidal-gear actuators—hack & customize towards your own need ▹ Off-the-shelf

Command humanoids *directly* with natural language? Introducing LangWBC, a generative, end-to-end policy that turns natural language into real-world whole-body humanoid control! 💬→🦿Smooth, robust, surprisingly intuitive! See more 👉 LangWBC.github.io #RSS2025

🤖Introducing TWIST: Teleoperated Whole-Body Imitation System. We develop a humanoid teleoperation system to enable coordinated, versatile, whole-body movements, using a single neural network. This is our first step toward general-purpose robots. 🌐humanoid-teleop.github.io

Excited to introduce PyRoki ("Python Robot Kinematics"): easier IK, trajectory optimization, motion retargeting... with an open-source toolkit on both CPU and GPU

Leveraging large-scale data sources can enable extremely general and robust policies. See our recent work MBRA! model-base-reannotation.github.io Led by noriaki_hirose Dhruv Shah Kyle Stachowicz Lydia Ignatova, Sergey Levine and thanks FrodoBots for making large-scale data for nav possible!

In the last month, we’ve been building an open-source framework for robot learning and sim-to-real transfer, made for RL whole-body control from simple walking to complex human imitation Check out the details on HN: news.ycombinator.com/item?id=440221… Get started in 5 minutes ⬇️

PhD not the same when your besties graduate 😕 all of a sudden, lab feels really empty and lonely

Excited to present FastTD3: a simple, fast, and capable off-policy RL algorithm for humanoid control -- with an open-source code to run your own humanoid RL experiments in no time! Thread below 🧵

Is RL really scalable like other objectives? We found that just scaling up data and compute is *not* enough to enable RL to solve complex tasks. The culprit is the horizon. Paper: arxiv.org/abs/2506.04168 Thread ↓

Join experts Yuval Tassa from Google DeepMind and Miles Macklin from NVIDIA at #GTCParis to learn about Newton, an open-source, extensible physics engine for robotics simulation, co-developed by Disney Research, Google DeepMind and NVIDIA. Gain insights into breakthroughs in

How can we move beyond static-arm lab setups and learn robot policies in our messy homes? We introduce HoMeR, an imitation learning agent for in-the-wild mobile manipulation. 🧵1/8

Specifically, HoMeR builds on our prior work SPHINX: x.com/priyasun_/stat… extending it to Jimmy Wu‘s Tidybot++: x.com/jimmyyhwu/stat… with a whole-body controller based on Kevin Zakka‘s mink! x.com/kevin_zakka/st… 🧵4/8

Excited to get this release out there! It's been cool seeing sw made for the real robot function identically in sim. Also really glad to be building on MuJoCo; their codebase & docs are incredible

Looking forward to giving a talk at the Real2Sim workshop at #CVPR2025 today at 3:50pm CDT. I will be speaking about sim-to-real for robot learning -- and MuJoCo Playground! #CVPR2025