MLVU: A Comprehensive Benchmark for Multi-Task Long Video Understanding

By Junjie Zhou, Yan Shu, Bo Zhao, Boya Wu, Shitao Xiao, Xi Yang, Yongping Xiong, Bo Zhang, Tiejun Huang, Zheng Liu. arXiv.org, 2024

378 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c735320ee0e5b2e580043b0a1504e592c0840e24

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Bo Li
2. Ziwei Liu
3. Luc Van Gool
4. Yuanhan Zhang
5. Xiaogang Wang
6. Chunyuan Li
7. Raquel Urtasun
8. Ming-Hsuan Yang

Citations in the corpus

• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency (2025, neutral): “…[71], MTVQA [119], AI2D [55], OCRBench [72], WildVision [78], MME-RealWorld (en) [178], Hal-lusionBench [41], MVBench [63], VideoMME [35], MLVU [186], (2) Reasoning Tasks : MMMU [170], MathVista [76], MathVision [76], MathVerse [175], DynaMath [189], WeMath [100], OlympiadBench [43],…”
• VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding (2025, neutral): “…VideoLLaMA3 to process and comprehend long-form video content, we assess performance on three long-video understanding (LVU) benchmarks: (1) MLVU [131]: diverse long-video understanding tasks for videos ranging from 3 minutes to more than 2 hours, (2) LongVideoBench [132]: video reasoning over…”
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models (2025, neutral): “For Video-MME [38], MMBench-Video [35], MLVU [154], and LongVideoBench [129], we test with four different settings: 16, 32, 48, and 64 frames, and report the maximum results.”
• LLaVA-OneVision: Easy Visual Task Transfer (2024, neutral): “These include ActivityNet-QA [154] that contains human-annotated action-related QA pairs derived from ActivityNet dataset, EgoSchema [98] and MLVU [169] focusing on long video understanding, PerceptionTest [115] designed to evaluate the perception skills, VideoMME [29] and NeXTQA [141] containing…”
• Video Instruction Tuning With Synthetic Data (2024, positive): “We also utilized LongVideoBench (Wu et al., 2024b), EgoSchema (Mangalam et al., 2024), and MLVU (Zhou et al., 2024) for long video understanding, PerceptionTest (P ˘ atr ˘ aucean et al., 2023) for assessing fine-grained perception skills, and VideoMME (Fu et al., 2024) and NExT-QA (Xiao et al.,…”