Zao Dai's picture

2

Zao Dai

zoeyd

AI & ML interests

None yet

Recent Activity

upvoted a paper about 17 hours ago

Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning

upvoted a paper 8 days ago

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders

View all activity

Organizations

None yet

upvoted a paper about 17 hours ago

Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning

Paper • 2606.04923 • Published 2 days ago • 35

upvoted a paper 8 days ago

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders

Paper • 2605.27354 • Published 10 days ago • 15