Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Kairui, Wu, Penghao, Pu, Fanyi, Xiao, Wang, Zhang, Yuanhan, Yue, Xiang, Li, Bo, Liu, Ziwei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912201493708800
author Hu, Kairui
Wu, Penghao
Pu, Fanyi
Xiao, Wang
Zhang, Yuanhan
Yue, Xiang
Li, Bo
Liu, Ziwei
author_facet Hu, Kairui
Wu, Penghao
Pu, Fanyi
Xiao, Wang
Zhang, Yuanhan
Yue, Xiang
Li, Bo
Liu, Ziwei
contents Humans acquire knowledge through three cognitive stages: perceiving information, comprehending knowledge, and adapting knowledge to solve novel problems. Videos serve as an effective medium for this learning process, facilitating a progression through these cognitive stages. However, existing video benchmarks fail to systematically evaluate the knowledge acquisition capabilities in Large Multimodal Models (LMMs). To address this gap, we introduce Video-MMMU, a multi-modal, multi-disciplinary benchmark designed to assess LMMs' ability to acquire and utilize knowledge from videos. Video-MMMU features a curated collection of 300 expert-level videos and 900 human-annotated questions across six disciplines, evaluating knowledge acquisition through stage-aligned question-answer pairs: Perception, Comprehension, and Adaptation. A proposed knowledge gain metric, Δknowledge, quantifies improvement in performance after video viewing. Evaluation of LMMs reveals a steep decline in performance as cognitive demands increase and highlights a significant gap between human and model knowledge acquisition, underscoring the need for methods to enhance LMMs' capability to learn and adapt from videos.
format Preprint
id arxiv_https___arxiv_org_abs_2501_13826
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
Hu, Kairui
Wu, Penghao
Pu, Fanyi
Xiao, Wang
Zhang, Yuanhan
Yue, Xiang
Li, Bo
Liu, Ziwei
Computer Vision and Pattern Recognition
Computation and Language
Humans acquire knowledge through three cognitive stages: perceiving information, comprehending knowledge, and adapting knowledge to solve novel problems. Videos serve as an effective medium for this learning process, facilitating a progression through these cognitive stages. However, existing video benchmarks fail to systematically evaluate the knowledge acquisition capabilities in Large Multimodal Models (LMMs). To address this gap, we introduce Video-MMMU, a multi-modal, multi-disciplinary benchmark designed to assess LMMs' ability to acquire and utilize knowledge from videos. Video-MMMU features a curated collection of 300 expert-level videos and 900 human-annotated questions across six disciplines, evaluating knowledge acquisition through stage-aligned question-answer pairs: Perception, Comprehension, and Adaptation. A proposed knowledge gain metric, Δknowledge, quantifies improvement in performance after video viewing. Evaluation of LMMs reveals a steep decline in performance as cognitive demands increase and highlights a significant gap between human and model knowledge acquisition, underscoring the need for methods to enhance LMMs' capability to learn and adapt from videos.
title Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2501.13826