VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Paper
• 2602.10693 • Published
• 216
HuangMeow
Luckyyy
AI & ML interests
None yet
Recent Activity
authored
a paper
10 days ago
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training upvoted an article 13 days ago
DenseR: Dense Rewards For Free in LLM Reasoning Organizations
None yet
authored a paper 10 days ago
upvoted a paper 10 days ago
upvoted an article 13 days ago
Article
DenseR: Dense Rewards For Free in LLM Reasoning
•
18