Can Huang

ChineseVideoBench: Benchmarking Multi-modal Large Models for Chinese Video Question Answering

Vision as LoRA

GLOMA: Global Video Text Spotting with Morphological Association

A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering

Video Q-Former: Multimodal Large Language Model with Spatio-Temporal Querying Transformer Towards Video Understanding

TextSquare: Scaling up Text-Centric Visual Instruction Tuning

MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark