김수아
gracehall
AI & ML interests
Alignment-focused model research.
Recent Activity
liked a dataset 5 days ago
Anthropic/hh-rlhf upvoted a paper 6 days ago
Looped World Models upvoted a paper 21 days ago
Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight MergingOrganizations
None yet