🧑‍🔬 Stéphane d'Ascoli

🏛️ Affiliations

🔬École Normale Supérieure - PSLParis · France2018–2025 · 16 papers🎓École Polytechnique Fédérale de LausanneLausanne · Switzerland2023–2024 · 6 papers🎓Université Paris Sciences et LettresParis · France2019–2022 · 6 papers🔬Laboratoire de Physique de l'Ecole Normale SupérieureParis · France2018–2022 · 5 papers🏢MetaMenlo Park · United States2020–2022 · 4 papers🔬Centre National de la Recherche ScientifiqueParis · France2019–2021 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 8 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Length Generalization in Arithmetic Transformers (2023 · 29 citations)
   The paper asks whether transformers can learn integer arithmetic on short operands and still be correct on much longer ones.
2. Deep Symbolic Regression for Recurrent Sequences (2022 · 27 citations)
   The paper tackles symbolic regression for sequences. Given the first terms of an integer or float sequence, the goal is to recover a recurrence relation u_n = f(n, earlier terms) that generates it. This is the familiar "guess the next number" puzzle from IQ tests, and earlier symbolic regression work, which targeted…
3. End-to-end symbolic regression with transformers (2022 · 27 citations)
   Symbolic regression (SR) looks for a readable mathematical formula that reproduces observed data. Usual pipelines first guess an expression "skeleton" and then fit its constants with BFGS. Genetic programming (GP) repeats this loop many times, so it is accurate but slow. Earlier Transformer methods predicted only…

All works

4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Régression symbolique de bout en bout avec des transformers. ↗HAL (Le Centre pour la Communication Scientifique Directe) · no summary yetPierre-Alexandre Kamienny et al.2022 · 37 citations
2. Length Generalization in Arithmetic TransformersarXiv:2306.15400Samy Jelassi, Stéphane d'Ascoli, Carles Domingo-Enrich, et al.2023 · 29 citations
3. Deep Symbolic Regression for Recurrent SequencesarXiv:2201.04600Stéphane d'Ascoli, Pierre-Alexandre Kamienny, Guillaume Lample, et al.2022 · 27 citations
4. End-to-end symbolic regression with transformersarXiv:2204.10532Pierre-Alexandre Kamienny, Stéphane d'Ascoli, Guillaume Lample, et al.2022 · 27 citations

🤝 Co-authors here

6 co-authors with a page, the most papers together first.

• François Charton ×3
• Guillaume Lample ×2
• Pierre-Alexandre Kamienny ×2
• Samy Jelassi
• Yuanzhi Li
• Yuhuai Wu

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• HAL (Le Centre pour la Communication Scientifique Directe)

🔗 Cited by

Papers of our library cite their works 52 times (of the 149,439 papers whose bibliographies we read); 22 citing papers with a page here →.

Updated 3 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/stephane-d-ascoli/