Xiang Cheng

In Context Semi-Supervised Learning

Mechanistic Study of Transformer In-Context Learning with Categorical Outputs

Trajectory Optimal Anisotropic Diffusion Models

From Softmax to Score: Transformers Can Effectively Implement In-Context Denoising Steps

Graph Transformers Dream of Electric Flow

On Understanding Attention-Based In-Context Learning for Categorical Data

Functional Gradients and Generalizations for Transformer In-Context Learning