Brian J.S. Lee

research @openai

[Brian J.S. Lee @brianjsl]

Really exciting release: the speed of the arms along with the physical compensation is insanely impressive!

[Reward AI @RewardAI_]

Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab

[Jacob Coxon @hilbertspaess]

@elonmusk @zerohedge I’m real and these are my real beliefs. You could ask your xAI researchers about me if you hadn’t fired them.

[Brian J.S. Lee @brianjsl]

@cdngdev shut up thijs

[OpenAI @OpenAI]

We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics.

The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra.

The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.

[Michael Zeng @michzeng_]

Action chunking — especially executing long action sequences open-loop — is widely used in imitation learning for robotic manipulation. Why is it so effective and do we really need it? We find a key reason:

Long open-loop execution helps short-context policies imitate non-Markovian experts.

With this insight, we show how to move beyond open-loop execution: extending policy context restores reactivity while achieving even higher task performance.

🧵(1/5)

[Brian J.S. Lee @brianjsl]

@SophieLWang Congrats!

[Aditya Ramesh @model_mechanic]

We've created a really unique environment to execute on the scope and ambitions of our program. If you're passionate about working full-stack on robotics, please building with us!

[Brian J.S. Lee @brianjsl]

@RussTedrake Congrats Russ!