Srishti280992/repro-exact-unlearning-in-reinforcement-learning-traces Traces • Updated Aug 3 • 211 • 13
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 18 days ago • 564
Edge0/Audio8-ASR-Infinite Automatic Speech Recognition • 4B • Updated 22 days ago • 42k • 2.45k
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It Paper • 2609.36585 • Published 18 days ago • 73
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 17 days ago • 665
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published Sep 8 • 483