arxiv:2606.04923
Zhuoyuan Hao 郝卓远
larry2210
AI & ML interests
LLM reasoning, reinforcement learning, reward hacking, trustworthy AI, AI agents
Recent Activity
commentedon a paper 16 days ago
Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning authored a paper 5 months ago
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning upvoted a paper 5 months ago
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement LearningOrganizations
None yet
