Recovering Reliable Supervision via Critique-Guided On-Policy Distillation Paper • 2610.20572 • Published 19 days ago • 32
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems Paper • 2609.33325 • Published Sep 27 • 80
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Paper • 2609.04148 • Published Sep 3 • 81