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/S4

S4

Reported on 9 benchmarks across 2 tasks · 2 papers · 8 SOTA

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

Medical8 results

  • Language ModellingonLRA
    Avg· 2022-06-24
    86.09
    best: 87.46 (S5)
    SOTA
    How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis ProjectionsarXiv:2206.12037
  • Language ModellingonLRA
    Image· 2022-06-24
    88.65
    SOTA
    How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis ProjectionsarXiv:2206.12037
  • Language ModellingonLRA
    ListOps· 2022-06-24
    59.6
    best: 62.15 (S5)
    SOTA
    How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis ProjectionsarXiv:2206.12037
  • Language ModellingonLRA
    Pathfinder· 2022-06-24
    94.2
    best: 95.33 (S5)
    SOTA
    How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis ProjectionsarXiv:2206.12037
  • Language ModellingonLRA
    Pathfinder-X· 2022-06-24
    96.35
    best: 98.58 (S5)
    SOTA
    How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis ProjectionsarXiv:2206.12037
  • Language ModellingonLRA
    Retrieval· 2022-06-24
    90.9
    best: 91.4 (S5)
    SOTA
    How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis ProjectionsarXiv:2206.12037
  • Language ModellingonLRA
    Text· 2022-06-24
    86.82
    best: 89.31 (S5)
    SOTA
    How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis ProjectionsarXiv:2206.12037
  • Language ModellingonWikiText-103
    Test perplexity· 2021-10-31
    21.28
    best: 2.4 (RETRO (7.5B))
    Efficiently Modeling Long Sequences with Structured State SpacesarXiv:2111.00396

Audio1 result

  • Speech RecognitiononSpeech Commands
    Accuracy (%)· 2021-10-31
    98.32
    best: 98.53 (Centaurus)
    SOTA
    Efficiently Modeling Long Sequences with Structured State SpacesarXiv:2111.00396