Yiyan Huang

Sampling experts from a multinomial policy can significantly enhance routing efficiency while satisfying operational constraints, achieving low regret in real-world applications.

Learning policies for distributional outcomes reveals that regret rates are intricately linked to policy class complexity, challenging conventional wisdom in offline policy learning.

You can now audit CLIP and CLAP models for PII memorization using *only* text queries, sidestepping the need for risky biometric inputs and computationally expensive shadow models.