Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics Paper • 2609.36608 • Published Sep 29 • 4
ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models Paper • 2609.18487 • Published Sep 16 • 26
PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models Paper • 2609.14973 • Published Sep 14 • 61
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search Paper • 2609.13356 • Published Sep 11 • 99
PhysBrain 1.5 Collection Unified Embodied Understanding, Action Generation, and Future-State Prediction • 5 items • Updated Oct 11 • 14
AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design Paper • 2605.08756 • Published May 9 • 23