BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
Paper
•
2510.18927
•
Published
•
82
Mathew Gates
MGates
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
27 days ago
Language Models are Injective and Hence Invertible
upvoted
a
paper
27 days ago
Attention Sinks in Diffusion Language Models
Organizations
None yet
upvoted
6
papers
27 days ago
Language Models are Injective and Hence Invertible
Paper
•
2510.15511
•
Published
•
67
Attention Sinks in Diffusion Language Models
Paper
•
2510.15731
•
Published
•
48
MoEUT: Mixture-of-Experts Universal Transformers
Paper
•
2405.16039
•
Published
•
2
Who invented deep residual learning?
Paper
•
2509.24732
•
Published
•
4
Annotated History of Modern AI and Deep Learning
Paper
•
2212.11279
•
Published
•
3