---
title: "Ashish Vaswani — all works — Elamur Research"
description: "All 52 works of Ashish Vaswani in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/ashish-vaswani/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/ashish-vaswani/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Ashish Vaswani](https://md.research.elamur.ai/free/en/authors/ashish-vaswani/) / all works

# Ashish Vaswani — all works

52 works · [← Ashish Vaswani](https://md.research.elamur.ai/free/en/authors/ashish-vaswani/)

1. [**Attention Is All You Need arXiv:1706.03762**Ashish Vaswani, Noam Shazeer, Niki Parmar, et al.*2017 · 17,458 citations*](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/)
2. **[Self-Attention with Relative Position Representations](https://md.research.elamur.ai/free/en/papers/shaw-2018-self-attention-relative-position-representations/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Peter Shaw, Jakob Uszkoreit, Ashish Vaswani*2018 · 2,848 citations*
3. **[Bottleneck Transformers for Visual Recognition ↗](https://doi.org/10.1109/cvpr46437.2021.01625) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Aravind Srinivas et al.*2021 · 1,310 citations*
4. **[Attention Augmented Convolutional Networks ↗](https://doi.org/10.1109/iccv.2019.00338) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Irwan Bello et al.*2019 · 1,246 citations*
5. **[Efficient Content-Based Sparse Attention with Routing Transformers](https://md.research.elamur.ai/free/en/papers/roy-2020-efficient-content-based-sparse-attention/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Aurko Roy, Mohammad Saffar, Ashish Vaswani, et al.*2020 · 677 citations*
6. **[The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/chen-2018-best-both-worlds-combining-recent/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Mia Xu Chen, Orhan Firat, Ankur Bapna, et al.*2018 · 559 citations*
7. **[Scaling Local Self-Attention for Parameter Efficient Visual Backbones ↗](https://doi.org/10.1109/cvpr46437.2021.01270) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Ashish Vaswani et al.*2021 · 476 citations*
8. **[Learning Whom to Trust with MACE](https://md.research.elamur.ai/free/en/papers/hovy-2013-learning-whom-trust-mace/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Dirk Hovy, Taylor Berg-Kirkpatrick, Ashish Vaswani, et al.*2013 · 473 citations*
9. **[Image Transformer ↗](https://arxiv.org/abs/1802.05751) arXiv (Cornell University) · no summary yet**Niki Parmar et al.*2018 · 342 citations*
10. **[Decoding with Large-Scale Neural Language Models Improves Translation](https://md.research.elamur.ai/free/en/papers/vaswani-2013-decoding-large-scale-neural-language/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Ashish Vaswani, Yinggong Zhao, Victoria Fossum, et al.*2013 · 318 citations*
11. **[Music Transformer: Generating Music with Long-Term Structure ↗](https://openalex.org/W2919624000) International Conference on Learning Representations · no summary yet**Cheng-Zhi Anna Huang et al.*2019 · 314 citations*
12. **[One Model To Learn Them All ↗](https://arxiv.org/abs/1706.05137) arXiv (Cornell University) · no summary yet**Łukasz Kaiser et al.*2017 · 277 citations*
13. **[Stand-Alone Self-Attention in Vision Models ↗](https://arxiv.org/abs/1906.05909) arXiv (Cornell University) · no summary yet**Prajit Ramachandran et al.*2019 · 267 citations*
14. **[Fast Decoding in Sequence Models using Discrete Latent Variables ↗](https://arxiv.org/abs/1803.03382) arXiv (Cornell University) · no summary yet**Łukasz Kaiser et al.*2018 · 213 citations*
15. **[Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation ↗](https://aclanthology.org/P19-1181/) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · no summary yet**Vihan Jain et al.*2019 · 205 citations*
16. [**Mesh-TensorFlow: Deep Learning for Supercomputers arXiv:1811.02084**Noam Shazeer, Youlong Cheng, Niki Parmar, et al.*2018 · 203 citations*](https://md.research.elamur.ai/free/en/papers/shazeer-2018-mesh-tensorflow-deep-learning-supercomputers/)
17. **[Tensor2Tensor for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/vaswani-2018-tensor2tensor-neural-machine-translation/) [Conference of the Association for Machine Translation in the Americas (AMTA)](https://md.research.elamur.ai/free/en/venues/amta/)**Ashish Vaswani, Samy Bengio, Eugene Brevdo, et al.*2018 · 191 citations*
18. **[DeepConsensus improves the accuracy of sequences with a gap-aware sequence transformer ↗](https://doi.org/10.1038/s41587-022-01435-7) Nature Biotechnology · no summary yet**Gunjan Baid et al.*2022 · 150 citations*
19. **[Aligning context-based statistical models of language with brain activity during reading ↗](https://aclanthology.org/D14-1030/) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yet**Leila Wehbe et al.*2014 · 122 citations*
20. **[Music Transformer ↗](https://arxiv.org/abs/1809.04281) arXiv (Cornell University) · no summary yet**Cheng-Zhi Anna Huang et al.*2018 · 117 citations*
21. **[Supertagging With LSTMs ↗](https://aclanthology.org/N16-1027/) Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Ashish Vaswani et al.*2016 · 107 citations*
22. **[Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers ↗](https://arxiv.org/abs/2109.10686) arXiv (Cornell University) · no summary yet**Yi Tay et al.*2021 · 104 citations*
23. **[Unsupervised Neural Hidden Markov Models ↗](https://aclanthology.org/W16-5907/) Proceedings of the Workshop on Structured Prediction for NLP · no summary yet**Ke M. Tran et al.*2016 · 81 citations*
24. **[Theory and Experiments on Vector Quantized Autoencoders ↗](https://arxiv.org/abs/1805.11063) arXiv (Cornell University) · no summary yet**Aurko Roy et al.*2018 · 67 citations*
25. **[The Efficiency Misnomer ↗](https://arxiv.org/abs/2110.12894) arXiv (Cornell University) · no summary yet**Mostafa Dehghani et al.*2021 · 50 citations*
26. **[Simple, Fast Noise-Contrastive Estimation for Large RNN Vocabularies ↗](https://aclanthology.org/N16-1145/) Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Barret Zoph et al.*2016 · 45 citations*
27. **[Name Tagging for Low-resource Incident Languages based on Expectation-driven Learning ↗](https://aclanthology.org/N16-1029/) Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Boliang Zhang et al.*2016 · 44 citations*
28. **[Hassan: A Virtual Human for Tactical Questioning ↗](https://aclanthology.org/2007.sigdial-1.15/) Proceedings of the 8th SIGdial Workshop on Discourse and Dialogue · no summary yet**David Traum et al.*2007 · 42 citations*
29. **[Smaller Alignment Models for Better Translations: Unsupervised Word Alignment with the l0-norm ↗](https://aclanthology.org/P12-1033/) Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Ashish Vaswani, Liang Huang, David Chiang*2012 · 37 citations*
30. **[Unifying Bayesian Inference and Vector Space Models for Improved Decipherment ↗](https://aclanthology.org/P15-1081/) Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yet**Qing Dou et al.*2015 · 28 citations*
31. **[Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation ↗](https://aclanthology.org/D14-1061/) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yet**Qing Dou, Ashish Vaswani, Kevin Knight*2014 · 27 citations*
32. **[Radiobot-CFF: a spoken dialogue system for military training ↗](https://doi.org/10.21437/interspeech.2006-151) Interspeech (USB) · no summary yet**Antonio Roque et al.*2006 · 25 citations*
33. **[Rule Markov Models for Fast Tree-to-String Translation ↗](https://aclanthology.org/P11-1086/) Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Ashish Vaswani et al.*2011 · 21 citations*
34. **[Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States ↗](https://aclanthology.org/Q16-1014/) Transactions of the Association for Computational Linguistics · no summary yet**Ashish Vaswani, Kenji Sagae*2016 · 20 citations*
35. **[Model Invertibility Regularization: Sequence Alignment With or Without Parallel Data ↗](https://aclanthology.org/N15-1063/) Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Tomer Levinboim, Ashish Vaswani, David Chiang*2015 · 20 citations*
36. **[Models and Training for Unsupervised Preposition Sense Disambiguation ↗](https://aclanthology.org/P11-2056/) Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Dirk Hovy et al.*2011 · 17 citations*
37. [**Rethinking Reflection in Pre-Training arXiv:2504.04022**Essential AI: Darsh J Shah, Peter Rushton, Somanshu Singla, et al.*2025 · 15 citations*](https://md.research.elamur.ai/free/en/papers/shah-2025-rethinking-reflection-pre-training/)
38. **[Fast, Greedy Model Minimization for Unsupervised Tagging ↗](https://aclanthology.org/C10-1106/) Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010) · no summary yet**Sujith Ravi et al.*2010 · 15 citations*
39. **[Efficient Optimization of an MDL-Inspired Objective Function for Unsupervised Part-Of-Speech Tagging ↗](https://aclanthology.org/P10-2039/) Proceedings of the ACL 2010 Conference Short Papers · no summary yet**Ashish Vaswani, Adam Pauls, David Chiang*2010 · 15 citations*
40. **[Towards a better understanding of Vector Quantized Autoencoders ↗](https://openalex.org/W2906111771) no summary yet**Aurko Roy et al.*2018 · 13 citations*
41. **[Evaluation of a Spoken Dialogue System for Virtual Reality Call for Fire Training ↗](https://doi.org/10.21236/ada461549) no summary yet**Susan M. Robinson et al.*2007 · 12 citations*
42. **[Practical Efficiency of Muon for Pretraining ↗](https://arxiv.org/abs/2505.02222) arXiv (Cornell University) · no summary yet**Essential AI et al.*2025 · 10 citations*
43. **[Simple and Efficient ways to Improve REALM ↗](https://aclanthology.org/2021.mrqa-1.16/) Proceedings of the 3rd Workshop on Machine Reading for Question Answering · no summary yet**Vidhisha Balachandran et al.*2021 · 9 citations*
44. **[A Virtual Human for Tactical Questioning ↗](https://openalex.org/W35788968) Borås Academic Digital Archive (University of Borås) · no summary yet**Bilyana Martinovski et al.*2007 · 9 citations*
45. **[Essential-Web v1.0: 24T tokens of organized web data ↗](https://arxiv.org/abs/2506.14111) arXiv · no summary yet**Essential AI et al.*2025 · 3 citations*
46. **[Studying Stand-Alone Self-Attention in Vision Models ↗](https://openalex.org/W2973106100) no summary yet**Prajit Ramachandran et al.*2019 · 3 citations*
47. **[Visualizing Music Self-Attention ↗](https://openalex.org/W2981646816) no summary yet**Anna Huang et al.*2018 · 3 citations*
48. **[A Training-Time Diagnostic for Generalization via the Log-Alignment Ratio ↗](https://arxiv.org/abs/2605.28975) arXiv (Cornell University) · no summary yet**Ali Shehper, Ashish Vaswani*2026*
49. **[OTel: Open Telco AI Datasets, Benchmarks, and Models ↗](https://arxiv.org/abs/2610.07766) arXiv (Cornell University) · no summary yet**Farbod Tavakkoli et al.*2026*
50. **[Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models ↗](https://arxiv.org/abs/2610.10478) arXiv (Cornell University) · no summary yet**Tan Yu et al.*2026*
51. **[Large Scale Multi-Domain Multi-Task Learning with MultiModel ↗](https://openalex.org/W2785866442) no summary yet**Łukasz Kaiser et al.*2018*
52. **[Smaller, faster and accurate models for statistical machine translation ↗](https://doi.org/10.25549/usctheses-c3-449238) University of Southern California Digital Library · no summary yet**Ashish Vaswani*2014*