Zhihao Wu
KunH
AI & ML interests
NLP, dialogue
Recent Activity
authored a paper 1 day ago
EDIT: Evidence-Diagnosed Intervention Training for Rule-Faithful LLM Grading upvoted a paper 1 day ago
Large Language Models Hack Rewards, and Society upvoted a paper 4 days ago
AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical
SearchOrganizations
None yet