RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 6 days ago • 264
Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation Paper • 2610.02788 • Published 5 days ago • 15
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 11 days ago • 323
Marathoner: Ultra-Long-Horizon Autonomous Intelligence Paper • 2609.34378 • Published 9 days ago • 42
Anisotropic Representations Improve Planning in JEPA World Models Paper • 2609.37441 • Published 8 days ago • 34
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision Paper • 2609.35954 • Published 9 days ago • 50
SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video Paper • 2609.37969 • Published 8 days ago • 41
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published 10 days ago • 565