N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization
Paper • 2606.10768 • Published • 24
newshawn
newshawn
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 17 days ago
N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization updated a model 5 months ago
newshawn/Qwen2.5-7B-GRPO-MATH-1EPOCH updated a model 5 months ago
newshawn/Qwen2.5-7B-VIGOR-MATH-1EPOCHOrganizations
upvoted a paper 17 days ago