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/Chat-UniVi-13B

Chat-UniVi-13B

Reported on 14 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Natural Language Processing11 results

  • Question AnsweringonActivityNet-QA
    Accuracy· 2023-11-14
    46.4
    best: 61.6 (Tarsier (34B))
    SOTA
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Question AnsweringonScienceQA
    Grades 7-12· uses extra data· 2023-11-14
    90.64
    best: 94.13 (MC-CoT F-Large)
    SOTA
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Question AnsweringonScienceQA
    Social Science· uses extra data· 2023-11-14
    95.05
    best: 96.29 (Honeybee)
    SOTA
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Question AnsweringonActivityNet-QA
    Confidence Score· 2023-11-14
    3.6
    best: 1.1 (Video LLaMA)
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Question AnsweringonScienceQA
    Avg. Accuracy· uses extra data· 2023-11-14
    90.99
    best: 94.88 (MC-CoT F-Large)
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Question AnsweringonScienceQA
    Grades 1-6· uses extra data· 2023-11-14
    91.19
    best: 95.3 (MC-CoT F-Large)
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Question AnsweringonScienceQA
    Image Context· uses extra data· 2023-11-14
    88.05
    best: 93.75 (MC-CoT F-Large)
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Question AnsweringonScienceQA
    Language Science· uses extra data· 2023-11-14
    88.91
    best: 93.18 (MC-CoT F-Large)
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Question AnsweringonScienceQA
    Natural Science· uses extra data· 2023-11-14
    90.41
    best: 97.47 (MC-CoT F-Large)
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Question AnsweringonScienceQA
    No Context· uses extra data· 2023-11-14
    90.94
    best: 94.49 (MC-CoT F-Large)
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Question AnsweringonScienceQA
    Text Context· uses extra data· 2023-11-14
    89.64
    best: 96.97 (MC-CoT F-Large)
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046

Reasoning4 results

  • Video Question AnsweringonActivityNet-QA
    Accuracy· 2023-11-14
    46.4
    best: 61.6 (Tarsier (34B))
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Video Question AnsweringonActivityNet-QA
    Confidence score· 2023-11-14
    3.3
    best: 2.2 (Video Chat)
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Video Question AnsweringonActivityNet-QA
    Accuracy· 2023-11-14
    46.4
    best: 61.6 (Tarsier (34B))
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046
  • Video Question AnsweringonActivityNet-QA
    Confidence Score· 2023-11-14
    3.6
    best: 1.1 (Video LLaMA)
    Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingarXiv:2311.08046