Yao Li

Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions

Partition-Losses Fine-Tuning: Contamination-Robust Backdoor Unlearning

DALD: Improving Logits-based Detector without Logits from Black-box LLMs

DeeDiff: Dynamic Uncertainty-Aware Early Exiting for Accelerating Diffusion Model Generation

FedDecay: Adapting to Data Heterogeneity in Federated Learning With Gradient Decay