Yunzhi Yao
cowTodd
AI & ML interests
None yet
Recent Activity
authored
a paper
9 days ago
From Data to Behavior: Predicting Unintended Model Behaviors Before Training
upvoted
a
paper
10 days ago
From Data to Behavior: Predicting Unintended Model Behaviors Before Training
authored
a paper
14 days ago
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics