🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

The Porter Ogden Jacobus Fellowship, the University’s top honor for Princeton University Graduate School students, is awarded to one Ph.D. student in humanities, social sciences, natural sciences, and engineering. The 2025 awardees will be honored at #PrincetonAlumniDay! bit.ly/41aEuNP

So excited for this!!! The key technical breakthrough here is that we can control joints and fingertips of the robot **without joint encoders**. Learning from self-supervised data collection is all you need for training the humanoid hand control you see below.

Before the (exciting) workshops on Sun, catch Vincent’s oral talk at the #ICLR2025 main conference on this paper today at 3:30pm, Hall 1 Apex! And don’t forget to talk with the co-leads Vincent and Yi Su at the poster 10 a.m - 12:30 p.m Hall 3 + Hall 2B #558.

Building AI systems is now a fragmented process spanning multiple organizations & entities. In new work (w/ Aspen Sarah Cen Andrew Ilyas Isabella Struckman Luis Videgaray Caso), we study the implications of these emerging networks → what we call *AI supply chains* 🧵

Congrats to Andrea Bajcsy (Andrea Bajcsy) on receiving the NSF CAREER award! 👏 Her work: “Formalizing Open World Safety for Interactive Robots,” explores how robots make safe decisions beyond collision avoidance. Read about it and her education plans: loom.ly/59evuD0

really excited about this one -- please submit your best work, and come join us in beautiful Lyon to talk about machine learning and science!

The Chicago Pope implies the existence of a New Keynesian Pope and a Behavioral Pope

RL and post-training play a central role in giving language models advanced reasoning capabilities, but many algorithmic and scientific questions remain unanswered. Join us at FoPT @ COLT '25 to explore pressing emerging challenges and opportunities for theory to bring clarity.

Want to scale robot data with simulation, but don’t know how to get large numbers of realistic, diverse, and task-relevant scenes? Our solution: ➊ Pretrain on broad procedural scene data ➋ Steer generation toward downstream objectives 🌐 steerable-scene-generation.github.io 🧵1/8

I am giving a talk "From Sim2Real 1.0 to 4.0 for Humanoid Whole-Body Control and Loco-Manipulation" at the RoboLetics 2.0 workshop IEEE ICRA today, summarizing my recent thoughts on sim2real. If you are interested: 2pm, May 23 @ room 302.

Very cool! In addition to optimizing inference-time search as a learning desideratum, this really speaks to power of building reward models purely from expert trajectories, via discriminative objectives. Excited to see how far this can go!

TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: toyotaresearchinstitute.github.io/lbm1/ One of our main goals for this paper was to put out a very careful and thorough study on the topic to help people understand the state of the