{"work":{"id":"365a8624-64bf-45a7-8a3e-c575aba224dc","openalex_id":null,"doi":null,"arxiv_id":"2501.13826","raw_key":null,"title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","authors":null,"authors_text":"Kairui Hu, Penghao Wu, Fanyi Pu, Wang Xiao, Yuanhan Zhang, Xiang Yue","year":2025,"venue":"cs.CV","abstract":"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, {\\Delta}knowledge, 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.","external_url":"https://arxiv.org/abs/2501.13826","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T06:10:23.812824+00:00","pith_arxiv_id":"2501.13826","created_at":"2026-05-09T22:18:58.364110+00:00","updated_at":"2026-05-25T06:10:23.812824+00:00","title_quality_ok":true,"display_title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","render_title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos"},"hub":{"state":{"work_id":"365a8624-64bf-45a7-8a3e-c575aba224dc","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":38,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2025-02-19T18:00:14+00:00","last_pith_cited_at":"2026-05-21T18:00:22+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-02T10:04:34.566140+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"dataset","n":9},{"context_role":"background","n":3},{"context_role":"baseline","n":2}],"polarity_counts":[{"context_polarity":"use_dataset","n":9},{"context_polarity":"background","n":3},{"context_polarity":"baseline","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}