GET/v1/search?type=scholar&q=transformer+attention
{
"searchParameters": {
"q": "transformer attention",
"gl": "us",
"hl": "en",
"tbs": "",
"page": 1,
"engine": "google",
"type": "scholar"
},
"organic": [
{
"title": "Analyzing the structure of attention in a transformer language model",
"link": "https://aclanthology.org/W19-4808/",
"publicationInfo": "J Vig, Y Belinkov - Proceedings of the 2019 ACL workshop …, 2019 - aclanthology.org",
"snippet": "… In this section, we present three visualizations of attention in the Transformer model: the attentionhead view, the model view, and the neuron view. Source code and Jupyter notebooks …",
"year": 2019,
"citedBy": 631,
"pdfUrl": "https://aclanthology.org/W19-4808.pdf",
"htmlUrl": null,
"id": "eTwV8Gym-v8J",
"position": 1
},
{
"title": "Attentionviz: A global view of transformer attention",
"link": "https://ieeexplore.ieee.org/abstract/document/10297591/",
"publicationInfo": "C Yeh, Y Chen, A Wu, C Chen, F Viégas… - … on Visualization and …, 2023 - ieeexplore.ieee.org",
"snippet": "… comprehending how transformers operate. (We include a brief introduction to transformers in Sec. 2.) The target of our analysis is the characteristic transformer self-attention mechanism…",
"year": 2023,
"citedBy": 191,
"pdfUrl": "https://arxiv.org/pdf/2305.03210",
"htmlUrl": null,
"id": "mGmdDY3CZ8QJ",
"position": 2
},
{
"title": "Neighborhood attention transformer",
"link": "https://ieeexplore.ieee.org/abstract/document/10205440/",
"publicationInfo": "A Hassani, S Walton, J Li, S Li… - 2023 IEEE/CVF …, 2023 - ieeexplore.ieee.org",
"snippet": "… , it provided empirical evidence that Transformerbased models outperform CNNs in larger scales. ViT paved the way for many more vision transformers, and attentionbased models in …",
"year": 2023,
"citedBy": 798,
"pdfUrl": "https://arxiv.org/pdf/2204.07143",
"htmlUrl": null,
"id": "j4aKOnoM074J",
"position": 3
},
{
"title": "Synthesizer: Rethinking self-attention for transformer models",
"link": "https://proceedings.mlr.press/v139/tay21a.html",
"publicationInfo": "Y Tay, D Bahri, D Metzler, DC Juan… - International …, 2021 - proceedings.mlr.press",
"snippet": "… performance when compared against vanilla Transformer models across a range of tasks, … with dot product attention, we find that Synthesizers consistently outperform Transformers. …",
"year": 2021,
"citedBy": 547,
"pdfUrl": "http://proceedings.mlr.press/v139/tay21a/tay21a.pdf",
"htmlUrl": null,
"id": "d2tbBUAhy7kJ",
"position": 4
},
{
"title": "A multiscale visualization of attention in the transformer model",
"link": "https://aclanthology.org/P19-3007/",
"publicationInfo": "J Vig - Proceedings of the 57th annual meeting of the …, 2019 - aclanthology.org",
"snippet": "… their attention patterns (Vaswani et al.… by visualizing attention in the Transformer at multiple scales. We introduce a high-level model view, which visualizes all of the layers and attention …",
"year": 2019,
"citedBy": 1101,
"pdfUrl": "https://aclanthology.org/P19-3007.pdf",
"htmlUrl": null,
"id": "V0Jqf-KuBZEJ",
"position": 5
},
{
"title": "Spectformer: Frequency and attention is what you need in a vision transformer",
"link": "https://ieeexplore.ieee.org/abstract/document/10943595/",
"publicationInfo": "BN Patro, VP Namboodiri… - 2025 IEEE/CVF winter …, 2025 - ieeexplore.ieee.org",
"snippet": "… They do use self-attention in deeper layers to capture longer … transformers, we developed SpectFormer, a new transformer … Further, we use multi-headed self-attention in the deeper …",
"year": 2025,
"citedBy": 261,
"pdfUrl": "https://arxiv.org/pdf/2304.06446",
"htmlUrl": null,
"id": "GmB9gVn1UI8J",
"position": 6
},
{
"title": "EAPT: efficient attention pyramid transformer for image processing",
"link": "https://ieeexplore.ieee.org/abstract/document/9580642/",
"publicationInfo": "X Lin, S Sun, W Huang, B Sheng, P Li… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org",
"snippet": "… This paper presented a new vision transformer architecture called Efficient Attention Pyramid Transformer (EAPT). Our rigorous evaluation demonstrates that EAPT outperforms the state-…",
"year": 2021,
"citedBy": 652,
"pdfUrl": null,
"htmlUrl": null,
"id": "pLOMOTmUKpYJ",
"position": 7
},
{
"title": "Vision transformer with deformable attention",
"link": "https://ieeexplore.ieee.org/abstract/document/9878689/",
"publicationInfo": "Z Xia, X Pan, S Song, LE Li… - 2022 IEEE/CVF …, 2022 - ieeexplore.ieee.org",
"snippet": "… This flexible scheme enables the self-attention module to focus on relevant regions and … Deformable Attention Transformer, a general backbone model with deformable attention for both …",
"year": 2022,
"citedBy": 1473,
"pdfUrl": "https://arxiv.org/pdf/2201.00520",
"htmlUrl": null,
"id": "KYwPK25Z3ZsJ",
"position": 8
},
{
"title": "Transformer architecture and attention mechanisms in genome data analysis: a comprehensive review",
"link": "https://www.mdpi.com/2079-7737/12/7/1033",
"publicationInfo": "SR Choi, M Lee - Biology, 2023 - mdpi.com",
"snippet": "… of the transformer architecture and the attention mechanism … specific application of transformers and attention methods. … of deep learning with transformers and attention mechanisms for …",
"year": 2023,
"citedBy": 341,
"pdfUrl": null,
"htmlUrl": "https://www.mdpi.com/2079-7737/12/7/1033",
"id": "LY1VJ0g70YsJ",
"position": 9
},
{
"title": "Lite transformer with long-short range attention",
"link": "https://arxiv.org/abs/2004.11886",
"publicationInfo": "Z Wu, Z Liu, J Lin, Y Lin, S Han - arXiv preprint arXiv:2004.11886, 2020 - arxiv.org",
"snippet": "… attention weights of the same layer for a fully trained basic transformer and our Lite Transformer … model both global and local contexts, the attention module in LSRA only focuses on the …",
"year": 2004,
"citedBy": 555,
"pdfUrl": "https://arxiv.org/pdf/2004.11886",
"htmlUrl": null,
"id": "3r2NPlIbzAUJ",
"position": 10
}
],
"tookMs": 4709
}
Clay
