Think Less, Locally: Local Preference Learning for Reasoning Compression Paper • 2611.04814 • Published 11 days ago • 67
Tree-Ising: Repairing Language Models with Bit-Level Ising Edits Paper • 2611.14210 • Published 4 days ago • 46
Test-Time Scaling for Diffusion Language Models with Frequency-Aware Remasking Paper • 2611.10486 • Published 7 days ago • 9
The Surprising Effectiveness of Deleting Weights in LLM Post-Training Paper • 2611.10866 • Published 7 days ago • 21
Running 282 The ultimate guide to RL environments: building and scaling them in the LLM era 📝 282 Building and scaling RL environments for LLM training