FAST: Efficient Action Tokenization for Vision-Language-Action Models
Karl Pertsch, Kyle Stachowicz, Brian Ichter, Danny Driess, Suraj Nair, Quan Vuong, Oier Mees, Chelsea Finn and 1 more
Who it is from
- University of California, Berkeleyaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- Lost in the Middle: How Language Models Use Long ContextsStanford University · 6,873 citations
- Structured information extraction from scientific text with large language modelsLawrence Berkeley National Laboratory · 1,409 citations
- A Review of Safe Reinforcement Learning: Methods, Theories, and ApplicationsTongji University · 903 citations
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement LearningUniversity of California, Berkeley · 710 citations
- Union through UNITY: Cosmology with 2000 SNe Using a Unified Bayesian FrameworkLawrence Berkeley National Laboratory · 665 citations
- Evaluating Real-World Robot Manipulation Policies in SimulationUniversity of California, Berkeley · 624 citations