Patrick Schramowski

2.1k total citations · 1 hit paper
24 papers, 456 citations indexed

About

Patrick Schramowski is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Sociology and Political Science. According to data from OpenAlex, Patrick Schramowski has authored 24 papers receiving a total of 456 indexed citations (citations by other indexed papers that have themselves been cited), including 16 papers in Artificial Intelligence, 8 papers in Computer Vision and Pattern Recognition and 3 papers in Sociology and Political Science. Recurrent topics in Patrick Schramowski's work include Explainable Artificial Intelligence (XAI) (7 papers), Generative Adversarial Networks and Image Synthesis (4 papers) and Topic Modeling (4 papers). Patrick Schramowski is often cited by papers focused on Explainable Artificial Intelligence (XAI) (7 papers), Generative Adversarial Networks and Image Synthesis (4 papers) and Topic Modeling (4 papers). Patrick Schramowski collaborates with scholars based in Germany, France and United States. Patrick Schramowski's co-authors include Kristian Kersting, Constantin A. Rothkopf, Cigdem Turan, Anne‐Katrin Mahlein, Anna Brugger, Ulrike Steiner, Stefan Paulus, Felix Friedrich, Matheus Thomas Kuśka and Jan Behmann and has published in prestigious journals such as Remote Sensing, Plant Pathology and Journal of Artificial Intelligence Research.

In The Last Decade

Patrick Schramowski

22 papers receiving 445 citations

Hit Papers

Large pre-trained language models contain human-like bias... 2022 2026 2023 2024 2022 50 100 150
What are hit papers?

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.

  1. Large pre-trained language models contain human-like biases of what is right and wrong to do
    2022 170 citations Patrick Schramowski, Cigdem Turan et al. Nature Machine Intelligence profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Patrick Schramowski Germany 12 198 113 43 42 37 24 456
Ishita Dasgupta United States 10 172 0.9× 39 0.3× 11 0.3× 18 0.4× 70 1.9× 27 378
Reid Pryzant United States 11 324 1.6× 76 0.7× 5 0.1× 44 1.0× 4 0.1× 15 448
Youssef Es-Saady Morocco 12 156 0.8× 78 0.7× 5 0.1× 9 0.2× 7 0.2× 32 558
Ioannis Karydis Greece 9 66 0.3× 100 0.9× 4 0.1× 18 0.4× 22 0.6× 44 337
Cigdem Turan Hong Kong 8 111 0.6× 126 1.1× 23 0.5× 25 0.6× 44 1.2× 11 347
Mohamad Nizam Bin Ayub Malaysia 11 87 0.4× 84 0.7× 3 0.1× 33 0.8× 31 0.8× 24 449
Jack Hessel United States 10 416 2.1× 384 3.4× 9 0.2× 39 0.9× 18 0.5× 28 768
John Wenskovitch United States 10 143 0.7× 226 2.0× 10 0.2× 26 0.6× 7 0.2× 33 351
Joshua C. Klontz United States 8 83 0.4× 352 3.1× 50 1.2× 21 0.5× 59 1.6× 8 527
Ilia Shumailov United Kingdom 8 188 0.9× 38 0.3× 40 0.9× 53 1.3× 13 0.4× 19 396

Countries citing papers authored by Patrick Schramowski

Since Specialization
Citations

This map shows the geographic impact of Patrick Schramowski'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 Patrick Schramowski with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Patrick Schramowski more than expected).

Fields of papers citing papers by Patrick Schramowski

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Patrick Schramowski. 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 Patrick Schramowski. The network helps show where Patrick Schramowski may publish in the future.

Co-authorship network of co-authors of Patrick Schramowski

This figure shows the co-authorship network connecting the top 25 collaborators of Patrick Schramowski. A scholar is included among the top collaborators of Patrick Schramowski 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 Patrick Schramowski. Patrick Schramowski is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
Friedrich, Felix, et al.. (2025). Multilingual Text-to-Image Generation Magnifies Gender Stereotypes. 19656–19679.
2.
Suárez, Pedro Ortiz, Javier Sáiz, Patrick Schramowski, et al.. (2024). Community OSCAR: A Community Effort for Multilingual Web Data. 232–235.
3.
Schramowski, Patrick, et al.. (2024). Divergent Token Metrics: Measuring degradation to prune away LLM components – and optimize quantization. 6764–6783. 2 indexed citations
4.
Friedrich, Felix, et al.. (2024). Auditing and instructing text-to-image generation models on fairness. AI and Ethics. 5(3). 2103–2123. 13 indexed citations
5.
Friedrich, Felix, et al.. (2024). LEDITS++: Limitless Image Editing Using Text-to-Image Models. 8861–8870. 20 indexed citations
6.
Schramowski, Patrick, et al.. (2024). T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings. 21829–21851. 1 indexed citations
7.
Schramowski, Patrick, et al.. (2023). Speaking Multiple Languages Affects the Moral Bias of Language Models. 2137–2156. 11 indexed citations
8.
Friedrich, Felix, et al.. (2023). A typology for exploring the mitigation of shortcut behaviour. Nature Machine Intelligence. 5(3). 319–330. 4 indexed citations
9.
Schramowski, Patrick, et al.. (2023). Explanatory Interactive Machine Learning. Business & Information Systems Engineering. 65(6). 677–701. 12 indexed citations
10.
Schramowski, Patrick, et al.. (2023). Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge. 24–28. 2 indexed citations
11.
Friedrich, F., et al.. (2023). Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis. Journal of Artificial Intelligence Research. 78. 1017–1068. 15 indexed citations
12.
Schramowski, Patrick, et al.. (2023). Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models. 22522–22531. 57 indexed citations
13.
Schramowski, Patrick, et al.. (2022). Large pre-trained language models contain human-like biases of what is right and wrong to do. Nature Machine Intelligence. 4(3). 258–268. 170 indexed citations breakdown →
14.
Brugger, Anna, Patrick Schramowski, Stefan Paulus, et al.. (2021). Spectral signatures in the UV range can be combined with secondary plant metabolites by deep learning to characterize barley–powdery mildew interaction. Plant Pathology. 70(7). 1572–1582. 20 indexed citations
15.
Schramowski, Patrick, et al.. (2020). Right for the Wrong Scientific Reasons: Revising Deep Networks by Interacting with their Explanations.. arXiv (Cornell University). 5 indexed citations
16.
Molina, Alejandro, Patrick Schramowski, & Kristian Kersting. (2020). Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks. International Conference on Learning Representations. 6 indexed citations
17.
Schramowski, Patrick, et al.. (2020). The Moral Choice Machine. Frontiers in Artificial Intelligence. 3. 36–36. 16 indexed citations
18.
Zintler, Alexander, Shuai Wang, Matúš Krajňák, et al.. (2020). Machine Learning Assisted Pattern Matching: Insight into Oxide Electronic Device Performance by Phase Determination in 4D-STEM Datasets. Microscopy and Microanalysis. 26(S2). 1908–1909. 3 indexed citations
19.
Brugger, Anna, Jan Behmann, Stefan Paulus, et al.. (2019). Extending Hyperspectral Imaging for Plant Phenotyping to the UV-Range. Remote Sensing. 11(12). 1401–1401. 31 indexed citations
20.
Schramowski, Patrick, et al.. (2019). Semantics Derived Automatically from Language Corpora Contain Human-like Moral Choices. 37–44. 30 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.

Explore authors with similar magnitude of impact

Breakdown of academic impact, for papers by Ishita Dasgupta Breakdown of academic impact, for papers by Reid Pryzant Breakdown of academic impact, for papers by Youssef Es-Saady Breakdown of academic impact, for papers by Ioannis Karydis Breakdown of academic impact, for papers by Cigdem Turan Breakdown of academic impact, for papers by Mohamad Nizam Bin Ayub Breakdown of academic impact, for papers by Jack Hessel Breakdown of academic impact, for papers by John Wenskovitch Breakdown of academic impact, for papers by Joshua C. Klontz Breakdown of academic impact, for papers by Ilia Shumailov
Rankless by CCL
2026