Xintao Wu

A new method for selecting demonstrations enhances model performance in language tasks.

This article discusses privacy methods for tabular data in large language models.

Exploring privacy risks and solutions in large language models.

Exploring the capabilities of vision language models in microscopy image analysis.

CausalDiffAE improves control over image features through counterfactual generation.

This article discusses soft prompting as a method for machine unlearning in LLMs.

A new method aims to reduce bias in language models' predictions.