Chenguang Wang

MusiXQA: Advancing Visual Music Understanding in Multimodal LLMs

Towards Visual Text Grounding of Multimodal Large Language Model

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning

Mosaic-IT: Free Compositional Data Augmentation Improves Instruction Tuning