3

FAST: Efficient Action Tokenization for Vision-Language-Action Models
arxiv 2025
Karl Pertsch, Kyle Stachowicz, Brian Ichter, Danny Driess, Suraj Nair, Quan Vuong, Oier Mees, Chelsea Finn, Sergey Levine
PDF Cite Code Project
FAST: Efficient Action Tokenization for Vision-Language-Action Models
Bridging Language and Action: A Survey of Language-Conditioned Robot Manipulation
arxiv 2024
Hongkuan Zhou, Xiangtong Yao, Oier Mees, Yuan Meng, Ted Xiao, Yonatan Bisk, Jean Oh, Edward Johns, Mohit Shridhar, Dhruv Shah, Jesse Thomason, Kai Huang, Joyce Chai, Zhenshan Bing, Alois Knoll
PDF Cite
Bridging Language and Action: A Survey of Language-Conditioned Robot Manipulation
Vision-Language Models Provide Promptable Representations for Reinforcement Learning
arxiv 2024
William Chen, Oier Mees, Aviral Kumar, Sergey Levine
PDF Cite Project
Vision-Language Models Provide Promptable Representations for Reinforcement Learning