WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection Paper • 2611.21373 • Published 5 days ago • 49
ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters Paper • 2611.21607 • Published 5 days ago • 40
FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning Paper • 2611.08240 • Published 15 days ago • 29
World In-Context Learning for Agentic Robot Manipulation Paper • 2611.12885 • Published 12 days ago • 56
InfraRSI: Harnessing Recursive Self-Improvement for Training Infrastructure Paper • 2611.11558 • Published 12 days ago • 28
SLA: Scaling Spatial-Language-Action Model via Continual Pre-training Paper • 2611.08373 • Published 16 days ago • 60
Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems Paper • 2611.05275 • Published 18 days ago • 45