[
  {
    "id": "dl3-a01-1",
    "type": "article",
    "title": "Attention Is All You Need",
    "author": [
      {
        "literal": "Ashish Vaswani"
      },
      {
        "literal": "Noam Shazeer"
      },
      {
        "literal": "Niki Parmar"
      },
      {
        "literal": "Jakob Uszkoreit"
      },
      {
        "literal": "Llion Jones"
      },
      {
        "literal": "Aidan N. Gomez"
      },
      {
        "literal": "Lukasz Kaiser"
      },
      {
        "literal": "Illia Polosukhin"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2017
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/1706.03762",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "1706.03762"
  },
  {
    "id": "dl3-a01-2",
    "type": "article",
    "title": "Low-Rank Bottleneck in Multi-head Attention Models",
    "author": [
      {
        "literal": "Srinadh Bhojanapalli"
      },
      {
        "literal": "Chulhee Yun"
      },
      {
        "literal": "Ankit Singh Rawat"
      },
      {
        "literal": "Sashank J. Reddi"
      },
      {
        "literal": "Sanjiv Kumar"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2020
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/2002.07028",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "2002.07028"
  },
  {
    "id": "dl3-a01-3",
    "type": "article",
    "title": "Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth",
    "author": [
      {
        "literal": "Yihe Dong"
      },
      {
        "literal": "Jean-Baptiste Cordonnier"
      },
      {
        "literal": "Andreas Loukas"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2021
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/2103.03404",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "2103.03404"
  },
  {
    "id": "dl3-a01-4",
    "type": "article",
    "title": "Are Transformers universal approximators of sequence-to-sequence functions?",
    "author": [
      {
        "literal": "Chulhee Yun"
      },
      {
        "literal": "Srinadh Bhojanapalli"
      },
      {
        "literal": "Ankit Singh Rawat"
      },
      {
        "literal": "Sashank J. Reddi"
      },
      {
        "literal": "Sanjiv Kumar"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2019
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/1912.10077",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "1912.10077"
  },
  {
    "id": "dl3-a01-5",
    "type": "article",
    "title": "Rethinking Attention with Performers",
    "author": [
      {
        "literal": "Krzysztof Choromanski"
      },
      {
        "literal": "Valerii Likhosherstov"
      },
      {
        "literal": "David Dohan"
      },
      {
        "literal": "Xingyou Song"
      },
      {
        "literal": "Andreea Gane"
      },
      {
        "literal": "Tamas Sarlos"
      },
      {
        "literal": "Peter Hawkins"
      },
      {
        "literal": "Jared Davis"
      },
      {
        "literal": "Afroz Mohiuddin"
      },
      {
        "literal": "Lukasz Kaiser"
      },
      {
        "literal": "David Belanger"
      },
      {
        "literal": "Lucy Colwell"
      },
      {
        "literal": "Adrian Weller"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2020
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/2009.14794",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "2009.14794"
  },
  {
    "id": "dl3-a01-6",
    "type": "article",
    "title": "Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention",
    "author": [
      {
        "literal": "Angelos Katharopoulos"
      },
      {
        "literal": "Apoorv Vyas"
      },
      {
        "literal": "Nikolaos Pappas"
      },
      {
        "literal": "François Fleuret"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2020
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/2006.16236",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "2006.16236"
  }
]