World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
37
Citations
22432
World Ranking
10427
National Ranking
4352

Overview

Yann N. Dauphin is a researcher primarily affiliated with Google in the United States. Their body of work is situated within the field of computer science, with a focus on artificial intelligence, computer vision and pattern recognition, health informatics, signal processing, and safety research.

Their research interests cover a range of topics, including:

  • Domain Adaptation and Few-Shot Learning
  • Advanced Neural Network Applications
  • Machine Learning and Data Classification
  • Generative Adversarial Networks and Image Synthesis
  • Machine Learning and Extreme Learning Machines (ELM)
  • Anomaly Detection Techniques and Applications
  • Adversarial Robustness in Machine Learning

Dauphin has contributed substantially to the academic literature, with publications primarily in prominent venues such as arXiv (Cornell University), the Proceedings of the AAAI Conference on Artificial Intelligence, PLoS ONE, and the Leibniz-Zentrum für Informatik (Schloss Dagstuhl).

Some of the recent papers authored or co-authored by Dauphin include:

  • Static Analysis of Shape in TensorFlow Programs, 2020, arXiv (Cornell University)
  • Mixup: Beyond empirical risk minimization, 2024, arXiv (Cornell University)
  • Continental-Scale Building Detection from High Resolution Satellite Imagery, 2021, Leibniz-Zentrum für Informatik (Schloss Dagstuhl)
  • Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions, 2021, arXiv (Cornell University)
  • Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win, 2022, Proceedings of the AAAI Conference on Artificial Intelligence

Their collaborations include frequent co-authorship with individuals such as:

  • Alina Beygelzimer
  • Percy Liang
  • Utku Evci
  • Atish Agarwala
  • Ekin D. Cubuk

Throughout their career, Dauphin has maintained a focus on advancing machine learning techniques, particularly in areas that intersect with neural networks and domain adaptation challenges. Their work has been disseminated through a variety of channels favored in the AI research community, reflecting engagement with both theoretical and applied aspects of artificial intelligence.

Best Publications

  • mixup: Beyond Empirical Risk Minimization

    Hongyi Zhang;Moustapha Cisse;Yann N. Dauphin;David Lopez-Paz

  • Convolutional Sequence to Sequence Learning

    Jonas Gehring;Michael Auli;David Grangier;Denis Yarats

  • Theano: A Python framework for fast computation of mathematical expressions

    Rami Al-Rfou;Guillaume Alain;Amjad Almahairi

  • Language modeling with gated convolutional networks

    Yann N. Dauphin;Angela Fan;Michael Auli;David Grangier

  • Identifying and attacking the saddle point problem in high-dimensional non-convex optimization

    Yann N Dauphin;Razvan Pascanu;Caglar Gulcehre;Kyunghyun Cho

  • Hierarchical Neural Story Generation

    Angela Fan;Mike Lewis;Yann N. Dauphin

  • Using recurrent neural networks for slot filling in spoken language understanding

    Grégoire Mesnil;Yann Dauphin;Kaisheng Yao;Yoshua Bengio

  • Parseval networks: improving robustness to adversarial examples

    Moustapha Cisse;Piotr Bojanowski;Edouard Grave;Yann Dauphin

  • Pay Less Attention with Lightweight and Dynamic Convolutions

    Felix Wu;Angela Fan;Alexei Baevski;Yann N. Dauphin

  • EmoNets: Multimodal deep learning approaches for emotion recognition in video

    Samira Ebrahimi Kahou;Xavier Bouthillier;Pascal Lamblin;Çaglar Gülçehre

  • A Convolutional Encoder Model for Neural Machine Translation

    Jonas Gehring;Michael Auli;David Grangier;Yann N. Dauphin

  • Combining modality specific deep neural networks for emotion recognition in video

    Samira Ebrahimi Kahou;Christopher Pal;Xavier Bouthillier;Pierre Froumenty

  • Unsupervised and Transfer Learning Challenge: a Deep Learning Approach

    Grégoire Mesnil;Yann N. Dauphin;Xavier Glorot;Salah Rifai

  • Deal or No Deal? End-to-End Learning of Negotiation Dialogues

    Mike Lewis;Denis Yarats;Yann N. Dauphin;Devi Parikh

  • Better Mixing via Deep Representations

    Yoshua Bengio;Gregoire Mesnil;Gregoire Mesnil;Yann Dauphin;Salah Rifai

  • Higher order contractive auto-encoder

    Salah Rifai;Grégoire Mesnil;Pascal Vincent;Xavier Muller

  • The Manifold Tangent Classifier

    Salah Rifai;Yann N Dauphin;Pascal Vincent;Yoshua Bengio

  • Equilibrated adaptive learning rates for non-convex optimization

    Yann N. Dauphin;Harm de Vries;Yoshua Bengio

  • Strategies for Structuring Story Generation

    Angela Fan;Mike Lewis;Yann N. Dauphin

  • Empirical Analysis of the Hessian of Over-Parametrized Neural Networks

    Levent Sagun;Utku Evci;V. Ugur Güney;Yann N. Dauphin

  • RMSProp and equilibrated adaptive learning rates for non-convex optimization.

    Yann N. Dauphin;Harm de Vries;Junyoung Chung;Yoshua Bengio

  • Deal or No Deal? End-to-End Learning for Negotiation Dialogues

    Mike Lewis;Denis Yarats;Yann N. Dauphin;Devi Parikh

Frequent Co-Authors

Yoshua Bengio
Yoshua Bengio University of Montreal
Michael Auli
Michael Auli Facebook (United States)
David Grangier
David Grangier Google (United States)
Pascal Vincent
Pascal Vincent Facebook (United States)
Aaron Courville
Aaron Courville University of Montreal
Gokhan Tur
Gokhan Tur Amazon (United States)
Larry P. Heck
Larry P. Heck Georgia Institute of Technology
Dilek Hakkani-Tur
Dilek Hakkani-Tur University of Illinois at Urbana-Champaign
Michael Lewis
Michael Lewis University of Pittsburgh
Caglar Gulcehre
Caglar Gulcehre DeepMind (United Kingdom)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online education opens up numerous flexible and affordable opportunities for those interested in Computer Science and related fields. If you’re seeking an advanced credential, you might consider a cheap doctorate degree online. These programs can provide specialized expertise without the financial burden of traditional, on-campus options.

For educators or professionals looking to quickly advance, 1 year edd programs online offer efficient pathways to earning a Doctor of Education in as little as twelve months. Similarly, those new to higher education can look into an accelerated associate degree online, which allows students to earn their qualifications in a short time frame—sometimes just six months.

If your interests intersect with technology and business, an affordable online business degree can provide versatile skills that complement Computer Science, such as management and entrepreneurship. These varied online pathways make career growth more accessible and customizable for busy adults and working professionals.

Best Scientists Citing Yann N. Dauphin

Trending Scientists

Recently Published Articles