ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control Paper • 2604.27711 • Published 13 days ago • 41
view article Article SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data +7 danaaubakirova, andito, merve, ariG23498, fracapuano, loubnabnl, pcuenq, mshukor, cadene • Jun 3, 2025 • 346
Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering Paper • 2601.10402 • Published Jan 15 • 37
FlowRL: Matching Reward Distributions for LLM Reasoning Paper • 2509.15207 • Published Sep 18, 2025 • 118
DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving Paper • 2505.16278 • Published May 22, 2025 • 5