Sangwoo Park's picture

Sangwoo Park

Sangsang

·

swgger

AI & ML interests

I do LLM post-training research (KAIST AI)

Recent Activity

upvoted a paper 1 day ago

PREPING: Building Agent Memory without Tasks

updated a model 11 days ago

Sangsang/safepath_Qwen3-32B

published a model 11 days ago

Sangsang/safepath_Qwen3-32B

View all activity

Organizations

None yet

authored a paper 3 months ago

THINKSAFE: Self-Generated Safety Alignment for Reasoning Models

Paper • 2601.23143 • Published Jan 30 • 39

submitted a paper to Daily Papers 3 months ago

THINKSAFE: Self-Generated Safety Alignment for Reasoning Models

Paper • 2601.23143 • Published Jan 30 • 39

authored a paper 8 months ago

Rethinking Reward Models for Multi-Domain Test-Time Scaling

Paper • 2510.00492 • Published Oct 1, 2025 • 28

authored a paper 12 months ago

FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA

Paper • 2505.12805 • Published May 19, 2025 • 22

authored a paper about 1 year ago

FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates

Paper • 2503.07216 • Published Mar 10, 2025 • 31