Sebastian Nowozin

Microsoft Research (United Kingdom) — United Kingdom

Computer Science · Physical Sciences

49h-index12.9kcitations157works4.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(28), Advanced Image and Video Retrieval Techniques(25), Generative Adversarial Networks and Image Synthesis(23), Advanced Neural Network Applications(20), Machine Learning and Data Classification(20)

Publications157 total

Laser writing in glass for dense, fast and efficient archival data storage
Nature·2026· 3 citedOpen Access
AlphaEvolve: A coding agent for scientific and algorithmic discovery
ArXiv.org·2025· 4 citedOpen Access
Project Silica: Towards Sustainable Cloud Archival Storage in Glass
ACM Transactions on Storage·2024· 6 cited
Project Silica: Towards Sustainable Cloud Archival Storage in Glass
2023· 15 citedOpen Access
Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics
arXiv (Cornell University)·2023· 20 citedOpen Access
Efficient data transport over multimode light-pipes with Megapixel images using differentiable ray tracing and Machine-learning
arXiv (Cornell University)·2023· 3 citedOpen Access
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
arXiv (Cornell University)·2022· 3 citedOpen Access
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
arXiv (Cornell University)·2022· 9 citedOpen Access
Cloud-Scale Archival Storage Using Ultrafast Laser Nanostructuring
Conference on Lasers and Electro-Optics·2022
Memory Efficient Meta-Learning with Large Images
arXiv (Cornell University)·2021· 1 citedOpen Access
Precise characterization of the prior predictive distribution of deep\n ReLU networks
arXiv (Cornell University)·2021· 7 citedOpen Access
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
arXiv (Cornell University)·2021· 2 citedOpen Access
Disentangling the Roles of Curation, Data-Augmentation and the Prior in\n the Cold Posterior Effect
arXiv (Cornell University)·2021· 5 citedOpen Access
Precise characterization of the prior predictive distribution of deep ReLU networks
arXiv (Cornell University)·2021· 5 citedOpen Access
Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations.
International Conference on Artificial Intelligence and Statistics·2020· 11 cited
TaskNorm: Rethinking Batch Normalization for Meta-Learning
Apollo (University of Cambridge)·2020· 21 citedOpen Access
TaskNorm: Rethinking Batch Normalization for Meta-Learning
arXiv (Cornell University)·2020· 30 citedOpen Access
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
arXiv (Cornell University)·2020· 22 citedOpen Access
The k-tied Normal Distribution: A Compact Parameterization of Gaussian\n Mean Field Posteriors in Bayesian Neural Networks
arXiv (Cornell University)·2020· 7 citedOpen Access
How Good is the Bayes Posterior in Deep Neural Networks Really?
arXiv (Cornell University)·2020· 33 citedOpen Access
page 1 of 8Next →

Frequent Co-authors

Carsten Rother(8), Lars Mescheder(6), Andreas Geiger(6), Pushmeet Kohli(5), Jeremy Jancsary(5), Ryota Tomioka(4), Sungwoong Kim(4), Peter Gehler(3), Koji Tsuda(3), Toby Sharp(3), Christoph H. Lampert(3), Yaniv Ovadia(2), Emily Fertig(2), Jie Ren(2), Zachary Nado(2), D. Sculley(2), Joshua V. Dillon(2), Balaji Lakshminarayanan(2), Jasper Snoek(2), Botond Cseke(2)