Blog Posts:

---

• Resilience
  Aidan N. Gomez, March 23, 2026. [link]

Selected Papers:

---

• Prioritized training on points that are learnable, worth learning, and not yet learned
  
  {Sören Mindermann, Muhammed Razzak, Winnie Xu}, Andreas Kirsch, Mrinank Sharma, Adrien Morisot, Aidan N. Gomez, Sebastian Farquhar, Jan Brauner, and Yarin Gal
  Published at ICML 2022 [pdf]
• Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
  
  {Jannik Kossen, Neil Band}, Clare Lyle, Aidan N. Gomez, Tom Rainforth, and Yarin Gal
  Published at NeurIPS 2021 [pdf]
• Interlocking Backpropagation: Improving depthwise model-parallelism
  
  {Aidan N. Gomez, Oscar Key}, Kuba Perlin, Stephen Gou, Nick Frosst, Jeff Dean, and Yarin Gal
  Published in JMLR 2022 [pdf]
• SliceOut: Training Transformers and CNNs faster while using less memory
  
  Pascal Notin, Aidan N. Gomez, Joanna Yoo, and Yarin Gal
  [pdf]
• Large-scale clinical interpretation of genetic variants using evolutionary data and deep learning
  
  {Jonathan Frazer, Pascal Notin, Mafalda Dias}, Aidan N. Gomez, Kelly Brock, Yarin Gal, and Debora S. Marks
  Published in Nature [Nature, pdf]
• Predicting Twitter Engagement With Deep Language Models
  
  Many Authors
  2nd Place at RecSys 2020 [pdf]
• Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers
  
  Tim Z. Xiao, Aidan N. Gomez, and Yarin Gal
  Presented at BDL 2019 [pdf]
• Learning Sparse Networks Using Targeted Dropout
  
  A. N. Gomez, I. Zhang, K. Swersky, Y. Gal, and G. E. Hinton
  Presented at CDNNIA at NeurIPS 2018 [pdf]
• Unsupervised Cipher Cracking Using Discrete GANs
  
  A. N. Gomez, S. Huang, I. Zhang, B. M. Li, M. Osama, and Ł. Kaiser
  Published at ICLR 2018 [pdf]
• The Reversible Residual Network: Backpropagation Without Storing Activations
  
  {A. N. Gomez, M. Ren}, R. Urtasun, and R. B. Grosse
  
  Published at NIPS 2017 [pdf]
• One Model To Learn Them All
  
  Ł. Kaiser, A. N. Gomez, N. Shazeer, A. Vaswani, N. Parmar, J. Uszkoreit, and L. Jones
  [pdf]
• Depthwise Separable Convolutions for Neural Machine Translation
  
  {Ł. Kaiser, A. N. Gomez, and F. Chollet}
  Published at ICLR 2018 [pdf]
• Attention Is All You Need
  
  {A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin}
  Published at NIPS 2017 [pdf]
• Tensor2tensor for neural machine translation
  
  A. Vaswani, S. Bengio, E. Brevdo, F. Chollet, A. N. Gomez, S. Gouws, L. Jones, Ł. Kaiser, N. Kalchbrenner, N. Parmar, R. Sepassi, N. Shazeer, and J. Uszkoreit
  [pdf]

{}: equal contribution

Talks/Posters:

---

• An Imminent Threat From AI (clickbait title, ik ik)
  The threat posed to our wellbeing by recommender systems. [video]
  
• Targeted Dropout
  Slides from MIS presentation. [pdf]
  
• Transformer
  Slides from Deep Learning Indaba presentation. [pdf]
  
• Reversible Residual Network
  Slides from TMLS oral presentation. [pdf]
  Poster from NIPS 2017. [pdf]
• Multi-task Learning: One Model To Learn Them All
  Slides from CUCSC oral presentation. [pdf]