AG
Aidan N. Gomez
cs.LGstat.MLcs.CLcs.CVcs.AIcs.ITeess.IVEvolution, MoleculargeneticsGenetic Variation
On Valency
published · living versionsW_qeugbgvj·v1 · currentpublished
Attention Is All You Need
with Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit +3
1 version
Preprints & journals
24 papers in the corpus · 2017–2025Aya Vision: Advancing the Frontier of Multilingual Multimodality2505.08751v1 · Saurabh Dash, Yiyang Nan, John Dang et al.2025 · 1 citationarXiv
Command A: An Enterprise-Ready Large Language Model2504.00698v2 · Team Cohere: Aakanksha, Arash Ahmadian, Marwan Ahmed et al.2025 · 0 citationsarXiv
Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier2412.04261v1 · John Dang, Shivalika Singh, Daniel D'souza et al.2024 · 3 citationsarXiv
Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)2107.02565v4 · Soren Mindermann, Muhammed Razzak, Winnie Xu et al.2021 · 0 citationsICML 2021 Workshop on Subset Selection in Machine Learning
Attention Is All You Need1706.03762v7 · Ashish Vaswani, Noam Shazeer, Niki Parmar et al.2017 · 26,892 citationsarXivon Valency
Exploring Low Rank Training of Deep Neural Networks2209.13569v1 · Siddhartha Rao Kamalakara, Acyr Locatelli, Bharat Venkitesh et al.2022 · 3 citationsarXiv
Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt2206.07137v3 · Soren Mindermann, Jan Brauner, Muhammed Razzak et al.2022 · 19 citationsarXiv
Interlocking Backpropagation: Improving depthwise model-parallelism2010.04116v3 · Aidan N. Gomez, Oscar Key, Kuba Perlin et al.2020 · 5 citationsarXiv
Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval2205.13760v1 · Pascal Notin, Mafalda Dias, Jonathan Frazer et al.2022 · 125 citationsarXiv
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning2106.02584v2 · Jannik Kossen, Neil Band, Clare Lyle et al.2021 · 44 citationsarXiv
Disease variant prediction with deep generative models of evolutionary data.34707284 · Frazer, Jonathan, Notin, Pascal, Dias, Mafalda et al.2022 · 883 citationsNature. 2021;599(7883):91-95
Publisher Correction: Disease variant prediction with deep generative models of evolutionary data.34921310 · Frazer, Jonathan, Notin, Pascal, Dias, Mafalda et al.2022 · 15 citationsNature. 2022;601(7892):E7
Improving compute efficacy frontiers with SliceOut2007.10909v2 · Pascal Notin, Aidan N. Gomez, Joanna Yoo et al.2020 · 1 citationarXiv
Robustness to Pruning Predicts Generalization in Deep Neural Networks2103.06002v1 · Lorenz Kuhn, Clare Lyle, Aidan N. Gomez et al.2021 · 9 citationsarXiv
Large-scale clinical interpretation of genetic variants using evolutionary data and deep learning10.1101/2020.12.21.423785v1 · Frazer, J., Notin, P., Dias, M. et al.2020 · 13 citationsbioRxiv
The Difficulty of Training Sparse Neural Networks1906.10732v3 · Utku Evci, Fabian Pedregosa, Aidan Gomez et al.2019 · 30 citationsarXiv
Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers2006.08344v1 · Tim Z. Xiao, Aidan N. Gomez, Yarin Gal2020 · 19 citationsarXiv
A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks1912.10481v1 · Angelos Filos, Sebastian Farquhar, Aidan N. Gomez et al.2019 · 71 citationsarXiv
Learning Sparse Networks Using Targeted Dropout1905.13678v5 · Aidan N. Gomez, Ivan Zhang, Siddhartha Rao Kamalakara et al.2019 · 74 citationsarXiv
Tensor2Tensor for Neural Machine Translation1803.07416v1 · Ashish Vaswani, Samy Bengio, Eugene Brevdo et al.2018 · 14 citationsarXiv
Unsupervised Cipher Cracking Using Discrete GANs1801.04883v1 · Aidan N. Gomez, Sicong Huang, Ivan Zhang et al.2018 · 24 citationsarXiv
The Reversible Residual Network: Backpropagation Without Storing Activations1707.04585v1 · Aidan N. Gomez, Mengye Ren, Raquel Urtasun et al.2017 · 369 citationsarXiv
Depthwise Separable Convolutions for Neural Machine Translation1706.03059v2 · Lukasz Kaiser, Aidan N. Gomez, Francois Chollet2017 · 242 citationsarXiv
One Model To Learn Them All1706.05137v1 · Lukasz Kaiser, Aidan N. Gomez, Noam Shazeer et al.2017 · 255 citationsarXiv
Career total: 30 works. 24 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.