mlsanityData to 7 Oct 2026

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

arXiv 2501.13826 ↗First posted 23 Jan 2025cs.CV cs.CLcited by 225

Not on the map. Why?

Cited by 107 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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, Deltaknowledge, 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.

Key facts. Cited by 225 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jan 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 102; 2026: 123.

225 papers.

Sort:

By area:

  1. 2025Qwen3-VL Technical Reportcited by 2,534
  2. 2025Video-R1: Reinforcing Video Reasoning in MLLMscited by 464
  3. 2026Kimi K2.5: Visual Agentic Intelligencecited by 449
  4. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 439
  5. 2025Kimi-VL Technical Reportcited by 381
  6. 2025Cambrian-S: Towards Spatial Supersensing in Videocited by 123
  7. 2025Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?cited by 107
  8. 2025MiMo-VL Technical Reportcited by 106
  9. 2025Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalitiescited by 101
  10. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  11. 2025Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoningcited by 88
  12. 2025VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuningcited by 86
38 more
  1. 2025STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?cited by 74
  2. 2025Kwai Keye-VL 1.5 Technical Reportcited by 68
  3. 2025Ming-Omni: A Unified Multimodal Model for Perception and Generationcited by 62
  4. 2025VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perceptioncited by 60
  5. 2025LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Callingcited by 58
  6. 2025DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPOcited by 57
  7. 2026MIRAGE: The Illusion of Visual Understandingcited by 57
  8. 2025OneThinker: All-in-one Reasoning Model for Image and Videocited by 52
  9. 2025ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understandingcited by 50
  10. 2025HumanOmniV2: From Understanding to Omni-Modal Reasoning with Contextcited by 50
  11. 2025Kwai Keye-VL Technical Reportcited by 47
  12. 2026Seed1.8 Model Card: Towards Generalized Real-World Agencycited by 47
  13. 2025GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoningcited by 46
  14. 2026Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understandingcited by 46
  15. 2025Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidencecited by 43
  16. 2025VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoningcited by 41
  17. 2025Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmarkcited by 41
  18. 2025Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmarkcited by 37
  19. 2025MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agentscited by 35
  20. 2025LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Modelcited by 34
  21. 2025PAI-Bench: A Comprehensive Benchmark For Physical AIcited by 30
  22. 2025Activation-Informed Merging of Large Language Modelscited by 29
  23. 2025Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoningcited by 29
  24. 2025VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinkingcited by 27
  25. 2025LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMscited by 25
  26. 2025VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videoscited by 24
  27. 2025VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoningcited by 24
  28. 2025VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videoscited by 23
  29. 2025LongCat-Flash-Omni Technical Reportcited by 23
  30. 2025MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videoscited by 22
  31. 2025ShotBench: Expert-Level Cinematic Understanding in Vision-Language Modelscited by 22
  32. 2025ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesiscited by 22
  33. 2025Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Taskscited by 22
  34. 2026LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMscited by 22
  35. 2025Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Datacited by 21
  36. 2025EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?cited by 20
  37. 2025AdaTooler-V: Adaptive Tool-Use for Images and Videoscited by 20
  38. 2026Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoningcited by 20

50 most cited of 225 All 225 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
  2. 2026LEMON: How Well Do MLLMs Perform Temporal Multimodal Understanding on Instructional Videos?
  3. 2025VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
  4. 2024WorldQA: Multimodal World Knowledge in Videos through Long-Chain Reasoning
  5. 2026How Far Are Video Models from True Multimodal Reasoning?
  6. 2026MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledge
  7. 2025InstructionBench: An Instructional Video Understanding Benchmark
  8. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI