The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 150
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems Paper • 2609.33325 • Published Sep 27 • 55
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Paper • 2609.38721 • Published Sep 30 • 134
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States Paper • 2610.01415 • Published Oct 1 • 60
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published Sep 28 • 81
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published Sep 2 • 150