Sarah
sbmiller7
ยท
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics updated a model 8 days ago
sbmiller7/vit-classification51 published a model 8 days ago
sbmiller7/vit-classification51Organizations
None yet