Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
20172.0k citationsMartin Heusel, Hubert Ramsauer et al.arXiv (Cornell University)profile →
DeepTox: Toxicity Prediction using Deep Learning
2016638 citationsAndreas Mayr, Günter Klambauer et al.profile →
Large-scale comparison of machine learning methods for drug target prediction on ChEMBL
2018352 citationsAndreas Mayr, Günter Klambauer et al.Chemical Scienceprofile →
Understanding Robustness of Transformers for Image Classification
2021227 citationsSrinadh Bhojanapalli, Ayan Chakrabarti et al.2021 IEEE/CVF International Conference on Computer Vision (ICCV)profile →
Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments
202467 citationsOliver T. Unke, Martin Stöhr et al.Science Advancesprofile →
Citations per year, relative to Thomas Unterthiner Thomas Unterthiner (= 1×)
peers
Emanuele Rodolà
Countries citing papers authored by Thomas Unterthiner
Since
Specialization
Citations
This map shows the geographic impact of Thomas Unterthiner's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Thomas Unterthiner with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Thomas Unterthiner more than expected).
Fields of papers citing papers by Thomas Unterthiner
This network shows the impact of papers produced by Thomas Unterthiner. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Thomas Unterthiner. The network helps show where Thomas Unterthiner may publish in the future.
Co-authorship network of co-authors of Thomas Unterthiner
This figure shows the co-authorship network connecting the top 25 collaborators of Thomas Unterthiner.
A scholar is included among the top collaborators of Thomas Unterthiner based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Thomas Unterthiner. Thomas Unterthiner is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Unke, Oliver T., Martin Stöhr, Stefan Ganscha, et al.. (2024). Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments. Science Advances. 10(14). eadn4397–eadn4397.67 indexed citations breakdown →
3.
Dosovitskiy, Alexey, Lucas Beyer, Alexander Kolesnikov, et al.. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations.143 indexed citations
Bhojanapalli, Srinadh, Ayan Chakrabarti, Daniel Gläsner, et al.. (2021). Understanding Robustness of Transformers for Image Classification. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 10211–10221.227 indexed citations breakdown →
6.
Locatello, Francesco, Dirk Weissenborn, Thomas Unterthiner, et al.. (2020). Object-Centric Learning with Slot Attention. Neural Information Processing Systems. 33. 11525–11538.13 indexed citations
7.
Unterthiner, Thomas, Sjoerd van Steenkiste, Karol Kurach, et al.. (2019). FVD: A new Metric for Video Generation. International Conference on Learning Representations.27 indexed citations
8.
Arjona-Medina, Jose A., et al.. (2019). RUDDER: Return Decomposition for Delayed Rewards. arXiv (Cornell University). 32. 13544–13555.7 indexed citations
9.
Preuer, Kristina, Philipp Renz, Thomas Unterthiner, Sepp Hochreiter, & Günter Klambauer. (2018). Fréchet ChemblNet Distance: A metric for generative models for molecules.. arXiv (Cornell University).2 indexed citations
10.
Unterthiner, Thomas, Bernhard Nessler, Günter Klambauer, et al.. (2018). Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields. International Conference on Learning Representations.6 indexed citations
11.
Mayr, Andreas, Günter Klambauer, Thomas Unterthiner, et al.. (2018). Large-scale comparison of machine learning methods for drug target prediction on ChEMBL. Chemical Science. 9(24). 5441–5451.352 indexed citations breakdown →
12.
Heusel, Martin, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, & Sepp Hochreiter. (2017). GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. arXiv (Cornell University). 30. 6626–6637.1986 indexed citations breakdown →
Arjona-Medina, Jose A., Thomas Unterthiner, Rupesh Durgesh, et al.. (2016). Speeding up Semantic Segmentation for Autonomous Driving.165 indexed citations
16.
Clevert, Djork-Arné, Andreas Mayr, Thomas Unterthiner, & Sepp Hochreiter. (2015). Rectified factor networks. Neural Information Processing Systems. 28. 1855–1863.2 indexed citations
17.
Unterthiner, Thomas, Eric B. Larson, Sander Dieleman, et al.. (2015). scikit-cuda 0.5.1. Zenodo (CERN European Organization for Nuclear Research).5 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.