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/HYDRA

HYDRA

Reported on 7 benchmarks across 3 tasks · 1 paper · 2 SOTA

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

Natural Language Processing3 results

  • Visual Question Answering (VQA)onA-OKVQA
    MC Accuracy· 2024-03-19
    56.35
    best: 83.75 (SMoLA-PaLI-X Specialist Model)
    HYDRA: A Hyper Agent for Dynamic Compositional Visual ReasoningarXiv:2403.12884
  • Visual Question Answering (VQA)onOK-VQA
    Accuracy· 2024-03-19
    48.6
    best: 66.8 (PaLI-X-VPD)
    HYDRA: A Hyper Agent for Dynamic Compositional Visual ReasoningarXiv:2403.12884
  • Visual Question Answering (VQA)onGQA test-dev
    Accuracy· 2024-03-19
    47.9
    best: 72.1 (CFR)
    HYDRA: A Hyper Agent for Dynamic Compositional Visual ReasoningarXiv:2403.12884

Computer Vision2 results

  • Visual GroundingonRefCOCO testA
    IoU· 2024-03-19
    61.7
    SOTA
    HYDRA: A Hyper Agent for Dynamic Compositional Visual ReasoningarXiv:2403.12884
  • Visual GroundingonRefCOCO+ testA
    IoU· 2024-03-19
    61.1
    SOTA
    HYDRA: A Hyper Agent for Dynamic Compositional Visual ReasoningarXiv:2403.12884

Miscellaneous2 results

  • Malware ClassificationonMicrosoft Malware Classification Challenge
    Accuracy (10-fold)
    0.9975
    best: 9641 (MalConv)
  • Malware ClassificationonMicrosoft Malware Classification Challenge
    Macro F1 (10-fold)
    0.9951