🧑‍🔬 Samy Jelassi

🏛️ Affiliations

🎓Harvard UniversityCambridge · United States2024–2026 · 9 paperscurrent🏢Microsoft Research New York CityNew York · United States2026 · 1 papercurrent🎓Princeton UniversityPrinceton · United States2018–2024 · 15 papers🎓Courant Institute of Mathematical SciencesNew York · United States2019–2021 · 4 papers🎓New York UniversityNew York · United States2019–2021 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 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. Repeat After Me: Transformers are Better than State Space Models at Copying (2024 · 57 citations)
   The paper asks what models with a constant-size memory give up in exchange for cheap inference. The authors call this family "generalized state space models" (GSSMs). It includes S4, Mamba, LSTMs and linear-attention variants. The authors find that the main loss is the ability to reproduce or retrieve arbitrary parts…
2. Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining (2025 · 34 citations)
   The paper asks why reinforcement-learning fine-tuning improves mathematical reasoning in language models. Pretraining data for popular base models such as Qwen is usually undisclosed, which makes it hard to separate the effect of RL from the effect of pretraining. To get around this, the authors train decoder-only…
3. 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.

All works

10 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. Repeat After Me: Transformers are Better than State Space Models at CopyingarXiv:2402.01032Samy Jelassi, David Brandfonbrener, Sham M. Kakade, et al.2024 · 57 citations
2. Echo Chamber: RL Post-training Amplifies Behaviors Learned in PretrainingarXiv:2504.07912Rosie Zhao, Alexandru Meterez, Sham Kakade, et al.2025 · 34 citations
3. Length Generalization in Arithmetic TransformersarXiv:2306.15400Samy Jelassi, Stéphane d'Ascoli, Carles Domingo-Enrich, et al.2023 · 29 citations
4. Vision Transformers Provably Learn Spatial Structure ↗neural information processing systems · no summary yetSamy Jelassi, Michael Sander, Yuanzhi Li2022 · 23 citations
5. LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks ↗Proceedings of the 31st International Conference on Computational Linguistics: Industry Track · no summary yetAkshara Prabhakar et al.2025 · 14 citations
6. Towards understanding how momentum improves generalization in deep learning ↗arXiv (Cornell University) · no summary yetSamy Jelassi, Yuanzhi Li2022 · 11 citations
7. Mixture of Parrots: Experts improve memorization more than reasoning ↗arXiv (Cornell University) · no summary yetSamy Jelassi et al.2024 · 4 citations
8. Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models ↗arXiv (Cornell University) · no summary yetSamy Jelassi et al.2026 · 1 citation
9. How Does Overparameterization Affect Features? ↗arXiv (Cornell University) · no summary yetAhmet Cagri Duzgun, Samy Jelassi, Yuanzhi Li2024
10. Dissecting adaptive methods in GANs ↗arXiv (Cornell University) · no summary yetSamy Jelassi et al.2022

🤝 Co-authors here

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

• Eran Malach ×2
• Sham M. Kakade ×2
• David Brandfonbrener
• François Charton
• Stéphane d'Ascoli
• Yuanzhi Li
• Yuhuai Wu

Venues

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

• Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
• neural information processing systems

🔗 Cited by

Papers of our library cite their works 148 times (of the 149,439 papers whose bibliographies we read); 47 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/samy-jelassi/