The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 16 days ago • 561
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 17 days ago • 396
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published 16 days ago • 137
vllm-sr/mmbert-embed-32k-2d-matryoshka Sentence Similarity • 0.3B • Updated 12 days ago • 14.9k • • 20