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/LinVT-Qwen2-VL (7B)

LinVT-Qwen2-VL (7B)

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

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

Reasoning8 results

  • Video Question AnsweringonNExT-QA
    Accuracy· 2024-12-06
    85.5
    SOTA
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Video Question AnsweringonMVBench
    Avg.· 2024-12-06
    69.3
    SOTA
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Video Question AnsweringonMSVD-QA
    Accuracy· 2024-12-06
    80.2
    best: 80.3 (Tarsier (34B))
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Video Question AnsweringonMSVD-QA
    Confidence Score· 2024-12-06
    4.4
    best: 2.5 (Video LLaMA-7B)
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Video Question AnsweringonTGIF-QA
    Accuracy· 2024-12-06
    81.3
    best: 82.5 (Tarsier (34B))
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Video Question AnsweringonTGIF-QA
    Confidence Score· 2024-12-06
    4.3
    best: 2.3 (Video Chat-7B)
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Video Question AnsweringonMSRVTT-QA
    Accuracy· 2024-12-06
    66.2
    best: 72.4 (Flash-VStream)
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Video Question AnsweringonMSRVTT-QA
    Confidence Score· 2024-12-06
    4
    best: 1.8 (Video LLaMA-7B)
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185

Natural Language Processing6 results

  • Question AnsweringonMSVD-QA
    Accuracy· 2024-12-06
    80.2
    best: 80.3 (Tarsier (34B))
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Question AnsweringonMSVD-QA
    Confidence Score· 2024-12-06
    4.4
    best: 2.5 (Video LLaMA-7B)
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Question AnsweringonTGIF-QA
    Accuracy· 2024-12-06
    81.3
    best: 82.5 (Tarsier (34B))
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Question AnsweringonTGIF-QA
    Confidence Score· 2024-12-06
    4.3
    best: 2.3 (Video Chat-7B)
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Question AnsweringonMSRVTT-QA
    Accuracy· 2024-12-06
    66.2
    best: 72.4 (Flash-VStream)
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185
  • Question AnsweringonMSRVTT-QA
    Confidence Score· 2024-12-06
    4
    best: 1.8 (Video LLaMA-7B)
    LinVT: Empower Your Image-level Large Language Model to Understand VideosarXiv:2412.05185