jwhe/09097_00
Text-to-Image • Updated • 2
🔄 In a Training Loop
quinn
jwhe
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics upvoted a paper about 8 hours ago
SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation submitted a paper about 8 hours ago
Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level RubricsOrganizations
