arxiv:2508.21104
Penghong Zhao
DDDDrop
AI & ML interests
RL，Multimodal，Machine Learninh
Recent Activity
authored
a paper
about 12 hours ago
PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic
Reasoning
upvoted
a
paper
9 days ago
PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic
Reasoning
Organizations
None yet