Zhixuan Fang

Secure Outlier-Aware Large Language Model Inference

Near Optimal Robust Federated Learning Against Data Poisoning Attack

Selective Deferred Routing: Enabling Cost-Efficient Collaboration between Local SLMs and Remote LLMs

Layer-Informed Fine-Tuning via Three-Stage Functional Segmentation of LLMs

Coalitional Personalized Federated Learning: A Hedonic Game Perspective

Optimal Action Abstraction for Imperfect Information Extensive-Form Games

Sparsity-Aware Grouped Reinforcement Learning for Designated Driver Dispatch

Bandit Learning in Matching: Unknown Preferences On Both Sides