VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Paper
• 2602.10693 • Published
• 185 •
6
Zhenghao Xu
zhenghaoxu
AI & ML interests
None yet
Recent Activity
commented on
a paper
4 days ago
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training updated
a dataset 5 days ago
zhenghaoxu/aime-beyond updated
a dataset 5 days ago
zhenghaoxu/aime-amc23 Organizations
commented a paper 4 days ago
updated 2 datasets 5 days ago
published a dataset 5 days ago
updated 4 datasets 5 days ago
updated a dataset 14 days ago
published 5 datasets 14 days ago
published a dataset 15 days ago
upvoted a paper 21 days ago
upvoted a paper 24 days ago
liked 2 models 3 months ago
liked a model 4 months ago