Thomas Unterthiner
Artificial Intelligence · 2015–2024
A researcher in the Science corpus: 23 papers; trusts 1,893 researchers and is trusted by 6,442 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 580 citations into it; #558 of 36,961 by trust here, #334 by citations
- Computer Vision and Pattern Recognition — 483 citations into it; #547 of 21,973 by trust here, #227 by citations
- Model Architectures — 168 citations into it; #91 of 2,288 by trust here, #46 by citations
- Computational Theory and Mathematics — 130 citations into it; #2,647 of 12,489 by trust here, #690 by citations
- Generative Models — 130 citations into it; #80 of 1,963 by trust here, #65 by citations
- Optimization & Training — 109 citations into it; #68 of 2,605 by trust here, #38 by citations
- Molecular Biology — 96 citations into it; #2,557 of 17,836 by trust here, #3,928 by citations
- Materials Chemistry — 94 citations into it; #533 of 11,531 by trust here, #1,990 by citations
Whom Thomas Unterthiner trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Sepp Hochreiter
- Yann LeCun
- Diederik P. Kingma
- Ilya Sutskever
- Kaiming He
- J. Urgen Schmidhuber
- Alex Graves
Who trusts Thomas Unterthiner overall
- Yoshua Bengio
- Yang Song
- Trevor Darrell
- Quoc V. Le
- Sergey Levine
- Dan Hendrycks
- Ting-Li Chen
- Dacheng Tao
- Yilun Du
- Ali Borji
Papers from Thomas Unterthiner's perspective
Ordered by how strongly the researchers Thomas Unterthiner trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Learning Multiple Layers of Features from Tiny Images
Their papers
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (2020) — 66,490 citations
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) (2015) — 6,140 citations
- MLP-Mixer: An all-MLP Architecture for Vision (2021) — 3,705 citations
- Object-Centric Learning with Slot Attention (2020) — 1,186 citations
- GANs Trained by a Two Time-Scale Update Rule Converge to a Nash Equilibrium (2017) — 506 citations
- Towards Accurate Generative Models of Video: A New Metric & Challenges (2018) — 1,343 citations
- Self-Normalizing Neural Networks (2017) — 2,892 citations
- RUDDER: Return Decomposition for Delayed Rewards (2018) — 277 citations
- Do Vision Transformers See Like Convolutional Neural Networks? (2021) — 1,440 citations
- Understanding Robustness of Transformers for Image Classification (2021) — 515 citations
- Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields (2017) — 81 citations
- Rectified Factor Networks (2015) — 17 citations
- DeepTox: Toxicity Prediction using Deep Learning (2016) — 921 citations
- Toxicity Prediction using Deep Learning (2015) — 165 citations
- Fréchet ChemNet Distance: A Metric for Generative Models for Molecules in Drug Discovery (2018) — 454 citations
- Large-scale comparison of machine learning methods for drug target prediction on ChEMBL (2018) — 442 citations
- Differentiable Patch Selection for Image Recognition (2021) — 123 citations
- PaliGemma: A versatile 3B VLM for transfer (2024) — 728 citations
- Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations (2022) — 20 citations
- FVD: A new Metric for Video Generation (2019) — 601 citations