Ming Liu

Bayesian Data Reweighting Improves Retrieval in Knowledge-Based VQA

On alignment of unified multimodal large language models

On Fairness of Unified Multimodal Large Language Model for Image Generation

Is Your Video Language Model a Reliable Judge?

Can Decoding by Contrasting Layers Really Improve Factuality in Large Language Models?

On the Robustness of Vision-Language Models Against Distractions