BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
Paper
•
2510.18927
•
Published
•
83
Shen
Vindicaters
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
Thinking with Video: Video Generation as a Promising Multimodal
Reasoning Paradigm
authored
a paper
2 months ago
BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via
Balanced Policy Optimization with Adaptive Clipping
Organizations
None yet
authored
a
paper
2 months ago