Yongyi Yang

Provable Low-Frequency Bias of In-Context Learning of Representations

Topological Invariance and Breakdown in Learning

RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm

Swing-by Dynamics in Concept Learning and Compositional Generalization

ICLR: In-Context Learning of Representations

HERTA: A High-Efficiency and Rigorous Training Algorithm for Unfolded Graph Neural Networks