New #RLC2024 paper Three Dogmas of Reinforcement Learning joint w/ Mark Ho and Anna Harutyunyan | Աննա Հարությունյան! arxiv.org/pdf/2407.10583 We reflect on where our scientific paradigm needs adjustment, and suggest three departures from previous conventions. Curious to hear what folks think! 🧵

How do robots understand natural language? #IJCAI2024 survey paper on robotic language grounding We situated papers into a spectrum w/ two poles, grounding language to symbols and high-dimensional embeddings. We discussed tradeoffs, open problems & exciting future directions!

10 years after DQN, what are deep RL’s impacts on robotics? Which robotic problems have seen the most thrilling real-world successes thanks to DRL? Where do we still need to push the boundaries, and how? Our latest survey explores these questions! Read on for more details. 👇

Much needed guidelines for robot policy evaluation

Pre-release of part 1 of our handbook: from SLAM to Spatial Intelligence. Please provide comments and suggestions to make it better! and a big THANK YOU to our amazing contributors! #spatialAI #robotics #perception #slam #ComputerVision

Interested in uncertainty quantification for LLMs? Check out our new survey paper on the topic! arxiv.org/abs/2412.05563 A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions

"Gr00t" vs "Pi0" vs "Pi0 Fast". I compared top open-source robotic models, and here's a detailed overview based on our own experience:

I’m hiring multiple PhD students and one postdoc at NTU Singapore, starting in Spring or Fall 2026, to push the frontiers of robot planning, learning, and embodied AI. Details are available here: yoonchangsung.com/opportunity Thank you for your support in sharing this opportunity!

I will be presenting this work at the RSS Workshop on Robot Hardware-Aware Intelligence on Wednesday, 06/25. (Location: EEB 248) The spotlight talk is happening in the session 3:30PM-4:00PM. The poster session will be 10:30AM-11:00AM and 4:00PM-4:45PM. Come chat with us!

How can 🤖 learn from human workers to provably reduce their workload in factories? Our latest Robotics: Science and Systems paper answers this question by proposing the first cost-optimal interactive learning (COIL) algorithm for multi-task collaboration.

A much-needed discussion in the field. Please consider submitting your work to our CoRL workshop by 8/30 and attending on 9/27 Many thanks to my awesome co-organizers! Abrar Anwar, Jesse Zhang, Paul Zhou,Huihan Liu, Jensen Gao,Abhishek Gupta, Stefanie Tellex,Yuke Zhu