Language Models Can Learn from Verbal Feedback Without Scalar Rewards Paper • 2509.22638 • Published 6 days ago • 61
cwm Collection Collection for Code World Model, an agentic coding model from FAIR. • 3 items • Updated 8 days ago • 14
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling Paper • 2506.20512 • Published Jun 25 • 47
Optimizing Anytime Reasoning via Budget Relative Policy Optimization Paper • 2505.13438 • Published May 19 • 36
Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis Paper • 2505.13227 • Published May 19 • 45
view article Article Accelerating LLM Inference: Fast Sampling with Gumbel-Max Trick By cxdu • Oct 24, 2024 • 12