Jian Li

Discerning Minds or Generic Tutors? Evaluating Instructional Guidance Capabilities in Socratic LLMs

Statistical Optimality of Newton-type Federated Learning with Heterogeneous Data

Revisiting Differential Attention: A Fine-Tuning Perspective on Practical Noise Mitigation

Understanding Generalization in Transformers: Error Bounds and Training Dynamics Under Benign and Harmful Overfitting

FN-NOW: A Communication-Efficient Newton-Type Federated Learning via Low-Rank Hessian Approximation

Efficient Newton-type Federated Learning with Non-IID Data