The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 5 days ago • 419
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published 5 days ago • 128
Unlocking Lossless Speedups in LLMs via Discrete Diffusion Paper • 2609.04010 • Published about 1 month ago • 114