🔥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

A BIG thanks to all collaborators: Laura Graesser David D'Ambrosio Pannag Sanketi Atil Iscen ASU School of Computing and Augmented Intelligence Kamalesh Kalirathinam Yifan Zhou

Can LLMs analyze games and coach a robot? 🤖 Thrilled to announce "SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement", led by Heni Ben Amor! Shows how LLMs can analyze motion and suggest improvements, just like a real coach!

In addition to the SAS paper (lnkd.in/gSaUhVzb), today we are releasing the dataset of table tennis ball trajectories used to train the Google DeepMind robot that can play amateur table tennis with humans (lnkd.in/gMNdmfG6). Github: github.com/google-deepmin…

Threading the needle with our robotic arm. Good autonomy can’t be achieved without a solid arm to begin with.

Headed to ICRA, stoked to learn about all the new research. We're presenting (1) Achieving Human Level Competitive Robot Table Tennis 🏓 (2) SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement 🤓 Come check them out. More details in 🧵

Robo-DM (Best Paper Award Finalist!) is a comprehensive open-sourced system for dataset management, designed for large diverse robot datasets like OXE! w/ Eric Pannag Sanketi Ken Goldberg Talk: Tuesday 09:55 - 10:30 (TuAT1.2) Poster: Tuesday 10:30 - 11:05 github.com/BerkeleyAutoma…

We are presenting our paper on LLMs for robot self-improvement for robot table-tennis tomorrow at ICRA 2025! Looking forward to see you all. #Deepmind #ASU

Congrats to all nominated papers and authors! Our UC Berkeley + Google DeepMind paper, "Robo-DM: Efficient Robot Big Data Management," is available here: drive.google.com/file/d/1REEkLM…

It’s been an amazing few months of relentless building, shipping, and optimising our models incorporating your feedback. Excited for more users and developers to try out the incredible Gemini 2.5 series!