Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
Paper • 2605.06139 • Published • 57
qinyanglin
qinyanglin
AI & ML interests
None yet
Recent Activity
upvoted a paper about 20 hours ago
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response SimplexOrganizations
None yet
upvoted a paper about 20 hours ago