arxiv:2505.18600
Sangwoo Kim
bryanswkim
AI & ML interests
None yet
Recent Activity
upvoted a paper 4 days ago
Representation Alignment for Just Image Transformers is not Easier than You Think upvoted a paper about 1 month ago
Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling upvoted a paper about 2 months ago
THINKSAFE: Self-Generated Safety Alignment for Reasoning Models