Stéphane d’Ascoli

1.5k total citations · 1 hit paper
10 papers, 674 citations indexed

About

Stéphane d’Ascoli is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Statistical and Nonlinear Physics. According to data from OpenAlex, Stéphane d’Ascoli has authored 10 papers receiving a total of 674 indexed citations (citations by other indexed papers that have themselves been cited), including 7 papers in Artificial Intelligence, 3 papers in Computer Vision and Pattern Recognition and 3 papers in Statistical and Nonlinear Physics. Recurrent topics in Stéphane d’Ascoli's work include Neural Networks and Applications (3 papers), Neural Networks and Reservoir Computing (2 papers) and Stochastic Gradient Optimization Techniques (2 papers). Stéphane d’Ascoli is often cited by papers focused on Neural Networks and Applications (3 papers), Neural Networks and Reservoir Computing (2 papers) and Stochastic Gradient Optimization Techniques (2 papers). Stéphane d’Ascoli collaborates with scholars based in France, Switzerland and Italy. Stéphane d’Ascoli's co-authors include Giulio Biroli, Levent Sagun, Matthew L. Leavitt, Ari S. Morcos, Hugo Touvron, Matthieu Wyart, Stefano Spigler, Mario Geiger, Julian H. Krolik and Vassilios Mewes and has published in prestigious journals such as Nature Communications, The Astrophysical Journal and Journal of Physics A Mathematical and Theoretical.

In The Last Decade

Stéphane d’Ascoli

10 papers receiving 645 citations

Hit Papers

ConViT: improving vision transformers with soft convoluti... 2022 2026 2023 2024 2022 100 200 300 400
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. ConViT: improving vision transformers with soft convolutional inductive biases*
    2022 478 citations Stéphane d’Ascoli, Hugo Touvron et al. Journal of Statistical Mechanics Theory and Experiment profile →

Peers — A (Enhanced Table)

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

Name h Career Trend Papers Cites
Stéphane d’Ascoli France 5 298 282 68 57 54 10 674
Edward Kim United States 12 203 0.7× 190 0.7× 84 1.2× 62 1.1× 44 0.8× 36 572
Andrey Zhmoginov United States 8 264 0.9× 137 0.5× 33 0.5× 34 0.6× 64 1.2× 18 553
Michael Rudzsky Israel 15 612 2.1× 175 0.6× 40 0.6× 33 0.6× 36 0.7× 28 821
Søren Hauberg Denmark 15 279 0.9× 152 0.5× 14 0.2× 53 0.9× 56 1.0× 37 804
Kang Li China 18 298 1.0× 239 0.8× 23 0.3× 144 2.5× 24 0.4× 56 982
K. Somasundaram India 15 429 1.4× 184 0.7× 98 1.4× 130 2.3× 27 0.5× 81 828
Jubo Zhu China 13 280 0.9× 196 0.7× 23 0.3× 10 0.2× 54 1.0× 88 677
Jelena Kovačević United States 15 105 0.4× 143 0.5× 273 4.0× 14 0.2× 62 1.1× 57 933
Heggere S. Ranganath United States 11 345 1.2× 175 0.6× 18 0.3× 28 0.5× 74 1.4× 39 660

Countries citing papers authored by Stéphane d’Ascoli

Since Specialization
Citations

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

Fields of papers citing papers by Stéphane d’Ascoli

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Stéphane d’Ascoli. 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 Stéphane d’Ascoli. The network helps show where Stéphane d’Ascoli may publish in the future.

Co-authorship network of co-authors of Stéphane d’Ascoli

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

All Works

10 of 10 papers shown
1.
d’Ascoli, Stéphane, et al.. (2025). Towards decoding individual words from non-invasive brain recordings. Nature Communications. 16(1). 10521–10521. 1 indexed citations
2.
Chemla, Emmanuel, et al.. (2024). A Polar coordinate system represents syntax in large language models. arXiv (Cornell University). 105375–105396. 1 indexed citations
3.
d’Ascoli, Stéphane, et al.. (2022). Align, then memorise: the dynamics of learning with feedback alignment*. Journal of Statistical Mechanics Theory and Experiment. 2022(11). 114002–114002. 4 indexed citations
4.
d’Ascoli, Stéphane, Hugo Touvron, Matthew L. Leavitt, et al.. (2022). ConViT: improving vision transformers with soft convolutional inductive biases*. Journal of Statistical Mechanics Theory and Experiment. 2022(11). 114005–114005. 478 indexed citations breakdown →
5.
d’Ascoli, Stéphane, et al.. (2021). Align, then memorise: the dynamics of learning with feedback alignment*. Journal of Physics A Mathematical and Theoretical. 55(4). 44002–44002. 3 indexed citations
6.
d’Ascoli, Stéphane, Levent Sagun, & Giulio Biroli. (2021). Triple descent and the two kinds of overfitting: where and why do they appear?*. Journal of Statistical Mechanics Theory and Experiment. 2021(12). 124002–124002. 8 indexed citations
7.
Geiger, Mario, Arthur Paul Jacot, Stefano Spigler, et al.. (2020). Scaling description of generalization with number of parameters in deep learning. Journal of Statistical Mechanics Theory and Experiment. 2020(2). 23401–23401. 67 indexed citations
8.
d’Ascoli, Stéphane, Levent Sagun, & Giulio Biroli. (2020). Triple descent and the two kinds of overfitting: Where & why do they appear?. SPIRE - Sciences Po Institutional REpository. 2 indexed citations
9.
Geiger, Mario, Stefano Spigler, Stéphane d’Ascoli, et al.. (2019). Jamming transition as a paradigm to understand the loss landscape of deep neural networks. Physical review. E. 100(1). 12115–12115. 43 indexed citations
10.
d’Ascoli, Stéphane, et al.. (2018). Electromagnetic Emission from Supermassive Binary Black Holes Approaching Merger. The Astrophysical Journal. 865(2). 140–140. 67 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 Edward Kim Breakdown of academic impact, for papers by Andrey Zhmoginov Breakdown of academic impact, for papers by Michael Rudzsky Breakdown of academic impact, for papers by Søren Hauberg Breakdown of academic impact, for papers by Kang Li Breakdown of academic impact, for papers by K. Somasundaram Breakdown of academic impact, for papers by Jubo Zhu Breakdown of academic impact, for papers by Jelena Kovačević Breakdown of academic impact, for papers by Heggere S. Ranganath
Rankless by CCL
2026