美国机器人基础模型B轮

Physical Intelligence

Develops general-purpose foundation models that let robots handle many physical tasks.

英文原文

官网

π0.5: a Vision-Language-Action Model with Open-World Generalization
Physical Intelligence2026年9月29日VLA署名作者
Magic-W0: A Structured World-Action Foundation Model for Physical Intelligence
Magiclab Robotics Inc. (Magic-Lab Team)2026年9月30日World-action model相关
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
2026年9月30日Grounding相关
ChunkTrust: Adapting Execution Horizons for Robot Policies with Action-Expert Evidence
Tsinghua University, Beijing Academy of Artificial Intelligence (BAAI), Renmin University of China, Shenzhen Technology University, Hefei University of Technology, Jiangnan University, Chongqing University, The Chinese University of Hong Kong2026年9月30日VLA相关
EmbodiedEvo: Self-improving Coding Agents for Physical Intelligence
2026年10月13日VLA相关
What Visual Representations Do World Action Models Need?
Institute of Automation, Chinese Academy of Sciences; Galbot; Peking University; University of Science and Technology of China2026年10月9日World-action model相关
ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models
NVIDIA; KAIST2026年10月13日Continual reinforcement learning on top of robot foundation models相关
WorldOracle: Benchmarking Action-Conditioned World Models against Real-World Executions
AgiBot; NVIDIA; Princeton University; University of Texas at Austin; University of Toronto2026年10月13日Evaluating robot world models against real executions相关