wongyukim
wongyukim
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 16 hours ago
Specification Self-Correction: Mitigating In-Context Reward Hacking
Through Test-Time Refinement
upvoted
a
paper
about 16 hours ago
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
upvoted
a
paper
about 16 hours ago
CLEAR: Error Analysis via LLM-as-a-Judge Made Easy
Organizations
None yet