Thomas Unterthiner

Computer Science · Physical Sciences

29h-index41.5kcitations59works25.52yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Advanced Neural Network Applications(14), Machine Learning in Materials Science(12), Computational Drug Discovery Methods(10), Generative Adversarial Networks and Image Synthesis(9), Domain Adaptation and Few-Shot Learning(8)

Publications59 total

Aligning machine and human visual representations across abstraction levels
Nature·2025· 2 citedOpen Access
Aligning Machine and Human Visual Representations across Abstraction Levels
arXiv (Cornell University)·2024· 2 citedOpen Access
PaliGemma: A versatile 3B VLM for transfer
arXiv (Cornell University)·2024· 9 citedOpen Access
Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments
Science Advances·2024· 89 citedOpen Access
Getting aligned on representational alignment
arXiv (Cornell University)·2023· 31 citedOpen Access
Set Learning for Accurate and Calibrated Models
arXiv (Cornell University)·2023Open Access
Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations
arXiv (Cornell University)·2022· 17 citedOpen Access
GradMax: Growing Neural Networks using Gradient Information
arXiv (Cornell University)·2022· 9 citedOpen Access
MLP-Mixer: An all-MLP Architecture for Vision
arXiv (Cornell University)·2021· 2 citedOpen Access
Understanding Robustness of Transformers for Image Classification
2021 IEEE/CVF International Conference on Computer Vision (ICCV)·2021· 380 cited
Do Vision Transformers See Like Convolutional Neural Networks?
arXiv (Cornell University)·2021· 109 citedOpen Access
Differentiable Patch Selection for Image Recognition
2021· 9 citedOpen Access
MLP-Mixer: An all-MLP Architecture for Vision
arXiv (Cornell University)·2021· 1.4k citedOpen Access
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
International Conference on Learning Representations·2021· 556 cited
Understanding Robustness of Transformers for Image Classification
arXiv (Cornell University)·2021· 2 citedOpen Access
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
arXiv (Cornell University)·2020· 21.2k citedOpen Access
Object-Centric Learning with Slot Attention
Neural Information Processing Systems·2020· 77 cited
Object-Centric Learning with Slot Attention
arXiv (Cornell University)·2020· 217 citedOpen Access
Predicting Neural Network Accuracy from Weights
arXiv (Cornell University)·2020· 38 citedOpen Access
FVD: A new Metric for Video Generation
International Conference on Learning Representations·2019· 47 cited
page 1 of 3Next →

Frequent Co-authors

Sepp Hochreiter(27), Günter Klambauer(16), Andreas Mayr(9), Alexey Dosovitskiy(8), Jakob Uszkoreit(7), Bernhard Nessler(7), Sylvain Gelly(6), Martin Heusel(6), Djork-Arné Clevert(6), Lucas Beyer(5), Alexander Kolesnikov(5), Dirk Weissenborn(5), Xiaohua Zhai(5), Neil Houlsby(5), Hubert Ramsauer(5), Kristina Preuer(5), Georg Heigold(4), Daniel Keysers(4), Philipp Renz(4), Jose A. Arjona-Medina(4)