Multimodal

MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs
A 4,016-question benchmark evaluating MLLMs on creative intent across audiovisual arts
Yuxuan Fan, Gyusik Seo, Jing Hao, Jaemin Cho, Mohit Bansal, Jaehong Yoon
Preprint Cite Code Project
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding
Multi-modal RAG framework and dataset for multi-page multi-document understanding
Jaemin Cho, Debanjan Mahata, Ozan İrsoy, Yujie He, Mohit Bansal
Preprint Cite Code Project
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding