Jiaxin Zhang

Study shows programming languages can improve each other's performance in code generation.

Introducing a new method for better evaluation of language model text quality.

This paper presents a method to improve fairness in federated learning while safeguarding data privacy.

A new benchmark assesses AI models' abilities in geometry problem-solving.

This article discusses a new method to improve prompt performance for language models.

DocRes simplifies document image restoration with a new model for multiple tasks.

New dataset enhances image and text generation in Vision-Language Models.

This study examines using technology to evaluate safety perceptions in cities.

Learn how multiple imputation helps with missing data in studies.