Yujing Chang — accepted AI-conference papers

2025

Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering

Kuicai Dong, Yujing Chang, Shijie Huang, Yasheng Wang, Ruiming Tang, Yong Liu

NeurIPS 2025poster

Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents (text, images, tables) and performing cross-modal reasoning. Current document retrieval-augmented generation (DocRAG) methods remain limited by their text-centric approaches, frequently missi…

Cited by 0 Source ↗code ↗Scholar ↗

2025

MMDocIR: Benchmarking Multimodal Retrieval for Long Documents

Kuicai Dong, Yujing Chang, Derrick Goh Xin Deik, Dexun Li, Ruiming Tang, Yong Liu

EMNLP 2025

Multimodal document retrieval aims to identify and retrieve various forms of multimodal content, such as figures, tables, charts, and layout information from extensive documents. Despite its increasing popularity, there is a notable lack of a comprehensive and robust benchmark to effectively evaluat

Cited by 0 Source ↗PDF ↗Scholar ↗