Hongkang Li

Can Mamba Learn In Context with Outliers? A Theoretical Generalization Analysis

A Theoretical Analysis of Mamba’s Training Dynamics: Filtering Relevant Features for Generalization in State Space Models

Contrastive Learning with Data Misalignment: Feature Purity, Training Dynamics and Theoretical Generalization Guarantees

When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis

Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning

Theoretical Analysis of Contrastive Learning in Vision-Language Model Pretraining: The Role of Synthetic Text Captions for Feature Alignment

Visual Prompting Reimagined: The Power of Activation Prompts