The first edition of the workshop was a hit — so we’re bringing it back, this time in LA!

Now that’s a speaker lineup that will be hard to beat. I hope this will be recorded and archived

Really excited about the amazing speaker lineup! Come join our workshop on June 25th this year ✨

our new system trains humanoid robots using data from cell phone videos, enabling skills such as climbing stairs and sitting on chairs in a single policy (w/ Hongsuk Benjamin Choi Junyi Zhang David McAllister)

✨Come hear from plenary speaker, Raffaello D’Andrea, Professor of dynamic systems and control, ETH Zurich! He will present the talk, "Models are dead, long live models!" 📆 Thursday, May 22 | 1:45-2:45 PM 🔗 Read the full abstract here: loom.ly/N-F285Q

Closed-loop robot policies directly from human interactions. No teleop, no robot data co-training, no RL, and no sim. Just Aria smart glasses. Everyday human data is passively scalable and a massively underutilized resource in robotics...More to come here in the coming weeks.

We just extended the deadline until May 31st! Submit your work here: exait-workshop.github.io

Over the past year, I've been compiling some "alchemist's notes" on deep learning. Right now it covers basic optimization, architectures, and generative models. Focus is on learnability -- each page has nice graphics and an end-to-end implementation. notes.kvfrans.com

FastTD3 Simple, Fast, and Capable Reinforcement Learning for Humanoid Control

Amazing work! This could finally open the door for bringing all the cool research about off-policy RL algorithms from the last years to large scale robotics policy training where PPO was the only thing before that would scale

FastTD3: "Minimum innovation, maximum results" Not the paper we had planned to write, but one of the works I am most proud of. We wanted to make sure our baseline (TD3) was a very solid baseline, so we added a few things that are already known to help in RL (large,

Join our #CVPR2025 Workshop on Real2Sim: Bridging the Gap between Neural Rendering and Robot Learning on 6/12! With amazing speakers: Marco Pavone Dhruv Shah Gordon Wetzstein Lingjie Liu Sicheng Mo Ruohan Zhang Carlo Sferrazza ⏲️ Thu, 6/12, 1:45-5:30 PM CDT 🏢 Davidson

Very excited for this one. We took a cautiously experimental view on NN optimizers, aiming to find something that just works. SPlus matches Adam within ~44% of steps on a range of objectives. Please try it out in your setting, or read below for how it works.

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