STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability
Paper • 2606.19236 • Published • 8
Guanxing Lu
GuanxingLu
·
AI & ML interests
Computer Vision, Reinforcement Learning, etc.
Recent Activity
upvoted a paper about 8 hours ago
STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability liked a Space 17 days ago
WorldArena/WorldArena updated a model about 1 month ago
GuanxingLu/momo-dapo-overlong-deepseek-r1-no-dpo-lossOrganizations
None yet
upvoted a paper about 8 hours ago
upvoted an article 3 months ago
Article
Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries
- +7
aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego
• • 164