collaborators

5 papers

cs.LG2026

How Can Mamba Learn In Context with Outliers and Generalize Provably?

Hongkang Li, Songtao Lu, Xiaodong Cui +2

The Mamba model has gained significant attention for its computational advantages over Transformer-based models, while achieving comparable performance across a wide range of langu…

cs.CV2026

Visual prompting reimagined: The power of the Activation Prompts

Yihua Zhang, Hongkang Li, Yuguang Yao +5

Visual prompting (VP) has emerged as a popular method to repurpose pretrained vision models for adaptation to downstream tasks. Unlike conventional model fine-tuning techniques, VP…

cs.LG2025

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

Hongkang Li, Yihua Zhang, Shuai Zhang +3

Task arithmetic refers to editing the pre-trained model by adding a weighted sum of task vectors, each of which is the weight update from the pre-trained model to fine-tuned models…

cs.LG2025

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

Hongkang Li, Songtao Lu, Pin-Yu Chen +2

Chain-of-Thought (CoT) is an efficient prompting method that enables the reasoning ability of large language models by augmenting the query using multiple examples with multiple in…

cs.LG2025

PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection

Wei Li, Pin-Yu Chen, Sijia Liu +1

Deep neural networks are susceptible to backdoor attacks, where adversaries manipulate model predictions by inserting malicious samples into the training data. Currently, there is…