MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models

fanqing meng, Jin Wang, Chuanhao, Quanfeng Lu, Hao Tian, liaojiaqi, Xizhou Zhu, Jifeng Dai, Yu Qiao, Ping Luo, KAIPENG ZHANG, SII - Wenqi Shao

MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models: 60 upvotes on Hugging Face Daily Papers, #1 of 12 papers on 2024-08-07. Day-by-day upvote history.

The capability to process multiple images is crucial for Large Vision-Language Models (LVLMs) to develop a more thorough and nuanced understanding of a scene. Recent multi-image LVLMs have begun to address this need. However, their evaluation has not kept pace with their development. To fill this gap, we introduce the Multimodal Multi-image Understanding (MMIU) benchmark, a comprehensive evaluation suite designed to assess LVLMs across a wide range of multi-image tasks. MMIU encompasses 7 types of multi-image relationships, 52 tasks, 77K images, and 11K meticulously curated multiple-choice questions, making it the most extensive benchmark of its kind. Our evaluation of 24 popular LVLMs, including both open-source and proprietary models, reveals significant challenges in multi-image comprehension, particularly in tasks involving spatial understanding. Even the most advanced models, such as GPT-4o, achieve only 55.7% accuracy on MMIU. Through multi-faceted analytical experiments, we identify key performance gaps and limitations, providing valuable insights for future model and data improvements. We aim for MMIU to advance the frontier of LVLM research and development, moving us toward achieving sophisticated multimodal multi-image user interactions.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.