I’m very excited to join Northeastern U. Khoury College of Computer Sciences as an assistant professor starting Fall '25!! Looking forward to working with the amazing people there! Until then I'll be a postdoc at NLP @ Uni Vienna with Ben Roth, so reach out if you want to meet up while I'm over in Europe ✨

We have released the YouTube recording of our #RSS2024 workshop on "Geometric and Algebraic Structure in Robot Learning"! 🎥Youtube: youtube.com/playlist?list=… 🏠Webpage: sites.google.com/view/gas-rl-rs…

Finally - big shout-out to the co-organizers of the workshop for making it happen at RSS! Prof. Lawson Wong, Chien Erh Lin, Yilun Du, Dian Wang, Anqi Li, @thepythagorian, Prof. Robin Walters, Prof. Byron Boots

A nice article on highlighting our work on Spot:

Apply to Tom’s new lab if want to work on robot planning and learning!! It’s foundational for robotics and AI. I’ve been working in the field of learning+planning for a while but still learned so much from his (and his collaborators’) work.

I do think learning for planning is crucial for AI and robotics to tackle more real-world tasks. A key challenge is how to build “internal state” representations for a model to predict/plan/reason over. MuZero has done on Go, o1 works on math. How can we do it on robots?

Cool to see demos on real robot!

Our paper on equivariant action sampling will be presented next week at #WAFR2024 in Chicago. It studies how preserving symmetry could improve sample efficiency and generalization in sampling-based planning for policy learning. Check out lfzhao.com/EquivSampling. Happy to chat!

I am attending #IROS and will present our RA-L paper Wednesday at 10am (soon!) in Room 9 (WeAT09), with Hongyu Li. We study learning-based planning for (visual) navigation on graphs and how equivariance enables more efficient learning. 🏠: lhy.xyz/e2-planning/ Let's chat!

Incredible insights from Prof. Tomás Lozano-Pérez of MIT during his keynote on the evolution of robotics! He took us on a journey through the shifting landscape of robotics over the years, discussing “inverted pendulum” theory of Robotics. #CoRL2024 #RobotLearning #AI #Robotics

Check out our work at #CoRL2024 on leveraging knowledge in pretrained vision-langauge models for grasping on complex environments! Led by Yaoyao(Freax) Qian and being presented at #CoRL2024 by Haojie Huang, feel free to reach out and chat!

A great group of speakers and panelists on planning & learning!

The original RL algorithms, inspired by natural learning, were online and incremental—they were streaming in the sense that they learned from each increment of experience as it happened, then discarded it, never to be processed again. The streaming algorithms were simple and

Dear MAGA friends, I have been worrying about STEM in the US a lot, because right now the Senate is writing new laws that cut 75% of the STEM budget in the US. Sorry for the long post, but the issue is really important, and I want to share what I know about it. The entire

🚀 FM4RoboPlan workshop is now live at #RSS2025! 📍 USC SGM 123, 8 : 30 – 12 : 35 PT Hear speakers from Stanford, MIT, Princeton, Physical Intelligence & more explore how foundation models are reshaping robot planning. ➡️ Website & Zoom Live sites.google.com/brown.edu/fm4r… #Robotics

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

Hierarchy and geometric prior are important for policy learning with better efficiency and generalization - see our #ICML2025 work on how to leverage them in policy learning!