arxiv:2609.34327
Sangwoo Park
Sangsang
AI & ML interests
I do LLM post-training & Distillation research (KAIST AI)
Recent Activity
upvoted a paper 1 day ago
Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data upvoted a paper 3 days ago
Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL upvoted a paper 4 days ago
Principia: Test-Time Hypotheses to Principle Construction for Scientific DiscoveryOrganizations
None yet
