STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability
Paper • 2606.19236 • Published • 8
CJL
cjl196
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
Meta-CoT: Enhancing Granularity and Generalization in Image Editing liked a model about 2 months ago
shiyi0408/Meta-CoTOrganizations
None yet
