TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/LLaVA-Mini

LLaVA-Mini

Reported on 12 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing6 results

  • Question AnsweringonMSVD-QA
    Accuracy· 2025-01-07
    70.9
    best: 80.3 (Tarsier (34B))
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895
  • Question AnsweringonMSVD-QA
    Confidence Score· 2025-01-07
    4
    best: 2.5 (Video LLaMA-7B)
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895
  • Question AnsweringonMSRVTT-QA
    Accuracy· 2025-01-07
    59.5
    best: 72.4 (Flash-VStream)
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895
  • Question AnsweringonMSRVTT-QA
    Confidence Score· 2025-01-07
    3.6
    best: 1.8 (Video LLaMA-7B)
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895
  • Question AnsweringonActivityNet-QA
    Accuracy· 2025-01-07
    53.5
    best: 61.6 (Tarsier (34B))
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895
  • Question AnsweringonActivityNet-QA
    Confidence Score· 2025-01-07
    3.5
    best: 1.1 (Video LLaMA)
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895

Reasoning6 results

  • Video Question AnsweringonMSVD-QA
    Accuracy· 2025-01-07
    70.9
    best: 80.3 (Tarsier (34B))
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895
  • Video Question AnsweringonMSVD-QA
    Confidence Score· 2025-01-07
    4
    best: 2.5 (Video LLaMA-7B)
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895
  • Video Question AnsweringonMSRVTT-QA
    Accuracy· 2025-01-07
    59.5
    best: 72.4 (Flash-VStream)
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895
  • Video Question AnsweringonMSRVTT-QA
    Confidence Score· 2025-01-07
    3.6
    best: 1.8 (Video LLaMA-7B)
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895
  • Video Question AnsweringonActivityNet-QA
    Accuracy· 2025-01-07
    53.5
    best: 61.6 (Tarsier (34B))
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895
  • Video Question AnsweringonActivityNet-QA
    Confidence Score· 2025-01-07
    3.5
    best: 1.1 (Video LLaMA)
    LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenarXiv:2501.03895