Jingwen Fu

On the Statistical Mechanisms of Distributional Compositional Generalization

Insufficient Task Description can Impair In-context Learning: A Study from Information Perspective

On Task Description of In-context Learning: A Study from Information Perspective

How does representation impact in-context learning: An exploration on a synthetic task

Generalization error bounds for iterative learning algorithms with bounded updates

When and Why Momentum Accelerates SGD: An Empirical Study