distilled model checkpoints with PromptKD (https://arxiv.org/abs/2402.12842) method.
Gyeongman Kim
gmkim
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
PaperCritic: Training AI Reviewers to Assess the Soundness of Papers liked a model 8 days ago
KRAFTON/Raon-1-nano upvoted a paper 23 days ago
Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL