The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 12 days ago • 543
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 13 days ago • 394
sentence-transformers/all-MiniLM-L6-v2 Sentence Similarity • 22.7M • Updated Jun 1 • 226M • • 6.24k
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published Aug 26 • 56