Jianliang He

Interpreting Multi-Layer Transformers for In-Context Linear Regression with Varying Covariance

How Transformers Learn Causal Structures In-Context: Explainable Mechanism Meets Theoretical Guarantee

On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking

Mechanistic Interpretability of In-Context Learning Generalization through Structured Task Curriculum

In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention