Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation
Paper • 2603.13045 • Published • 1
Yifeng Liu
lyf07
AI & ML interests
None yet
Recent Activity
authored a paper 2 days ago
R-PRM: Reasoning-Driven Process Reward Modeling authored a paper 2 days ago
Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation updated a model 3 days ago
lyf07/Translategemma-4B-it-WALAROrganizations
None yet
upvoted a paper 3 days ago