Yann Dauphin

Researcher, Google

Joined

December 2017

Names

Yann Dauphin

Emails

****@dauphin.io (Confirmed)

,

****@google.com (Confirmed)

Personal Links

Career & Education History

Researcher

Google (google.com)

2019 – Present

Researcher

Facebook (fb.com)

2015 – 2018

PhD student

University of Montreal (umontreal.ca)

2010 – 2015

Advisors, Relations & Conflicts

PhD Advisor

2010 – 2015

Expertise

machine learning

Present

deep learning

Present

Publications

Capturing Individual Human Preferences with Reward Features
Andre Barreto, Vincent Dumoulin, Yiran Mao, Mark Rowland, Nicolas Perez-Nieves, Bobak Shahriari, Yann Dauphin, Doina Precup, Hugo Larochelle
- NeurIPS 2025 poster
- Readers: Everyone
Avoiding spurious sharpness minimization broadens applicability of SAM
Sidak Pal Singh, Hossein Mobahi, Atish Agarwala, Yann Dauphin
- ICML 2025 poster
- Readers: Everyone
Towards Optimal Adapter Placement for Efficient Transfer Learning
Aleksandra Nowak, Otniel-Bogdan Mercea, Anurag Arnab, Jonas Pfeiffer, Yann Dauphin, Utku Evci
- Submitted to ICLR 2025
- Readers: Everyone
Neglected Hessian component explains mysteries in sharpness regularization
Yann Dauphin, Atish Agarwala, Hossein Mobahi
- NeurIPS 2024 spotlight
- Readers: Everyone
A density estimation perspective on learning from pairwise human preferences
Vincent Dumoulin, Daniel D. Johnson, Pablo Samuel Castro, Hugo Larochelle, Yann Dauphin
- Accepted by TMLR
- Readers: Everyone
How Hessian structure explains mysteries in sharpness regularization
Yann Dauphin, Atish Agarwala, Hossein Mobahi
- Submitted to ICLR 2024
- Readers: Everyone
Jaxpruner: A Concise Library for Sparsity Research
Joo Hyung Lee, Wonpyo Park, Nicole Elyse Mitchell, Jonathan Pilault, Johan Samir Obando Ceron, Han-Byul Kim, Namhoon Lee, Elias Frantar, Yun Long, Amir Yazdanbakhsh, Woohyun Han, Shivani Agrawal, Suvinay Subramanian, Xin Wang, Sheng-Chun Kao, Xingyao Zhang, Trevor Gale, Aart J.C. Bik, Milen Ferev, Zhonglin Han et al. (5 additional authors not shown)
- CPAL 2024 (Proceedings Track) Oral
- Readers: Everyone
Tied-Augment: Controlling Representation Similarity Improves Data Augmentation
Emirhan Kurtuluş, Zichao Li, Yann Dauphin, Ekin Dogus Cubuk
- ICML 2023 Poster
- Readers: Everyone
SAM operates far from home: eigenvalue regularization as a dynamical phenomenon
Atish Agarwala, Yann Dauphin
- ICML 2023 Poster
- Readers: Everyone
Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets
Jonas Ngnawe, Marianne ABEMGNIGNI NJIFON, Jonathan Heek, Yann Dauphin
- Published: 21 Oct 2022, Last Modified: 05 May 2023
- NeurIPS 2022 Workshop DistShift Poster
- Readers: Everyone

View all 53 publications

Co-Authors

View all 216 co-authors