BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
Paper • 2510.18927 • Published • 85
Mathew Gates
MGates
AI & ML interests
None yet
Organizations
None yet
upvoted 6
papers 8 months ago
Language Models are Injective and Hence Invertible
Paper • 2510.15511 • Published • 70
Attention Sinks in Diffusion Language Models
Paper • 2510.15731 • Published • 50
MoEUT: Mixture-of-Experts Universal Transformers
Paper • 2405.16039 • Published • 3
Who invented deep residual learning?
Paper • 2509.24732 • Published • 5
Annotated History of Modern AI and Deep Learning
Paper • 2212.11279 • Published • 3