Have you wondered whether LLMs could directly execute robot tasks?🚨 Excited to share our work, *RoboPrompt*, a framework that enables off-the-shelf text-only LLMs to directly predict robot actions with ICL demonstrations without training! Berkeley AI Research davidyyd.github.io/roboprompt/

Excited to share our new work! It is absolutely shocking to me that LLMs can be used for motion planning through In-Context Learning, without any finetuning!

Please come to our oral and poster presentations on Wednesday — I’ll be there along with Zekai Wang and Dantong Niu to present our work! Oral: Wednesday, 3:20 — 3:25pm, Room 314 Poster: Wednesday, 3:50 — 4:25pm, Room 314 Paper: arxiv.org/abs/2410.12782