TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models
Paper • 2604.26553 • Published • 1
Jinho Choo
jhchoo
AI & ML interests
None yet
Recent Activity
liked a dataset 11 months ago
CohereLabs/aya_dataset liked a dataset over 2 years ago
monology/pile-uncopyrightedOrganizations
None yet