Elamur Research⌕
☰
home / authors / Alexandre Rame

Alexandre Rame

Alexandre Rame has 2 papers in our library, in 2023–2024, most of them on Language models & pretraining, Efficient models & compression; often with Geoffrey Cideron, Jean-Baptiste Gaya, Johan Ferret.

2 papers in our library · 2023–2024

OpenAlex · h-index 10 · 36 works · 931 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 2,440 times in our library · 3 more in our library without a page yet · ⭐ Paper Stars ranking: #8104

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢GoogleMountain View · United States2024–2026 · 2 paperscurrent🎓Sorbonne UniversitéParis · France2018–2023 · 9 papers🔬Institut Systèmes Intelligents et de RobotiqueParis · France2021–2023 · 4 papers🔬Centre National de la Recherche ScientifiqueParis · France2018–2022 · 3 papers🔬LIP6Paris · France2020–2021 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Fields, topics and concepts

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

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 2Research subjects and languages the work is about.Efficient models & compression · 1 workLanguage models & pretraining · 1 work

 Works by year

2020s

20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards (2023 · 90 citations)
    Reinforcement learning, including RLHF, aligns foundation models using proxy rewards that only approximate what users really want, and people disagree about what a good output is.
  2. BOND: Aligning LLMs with Best-of-N Distillation (2024 · 23 citations)
    Best-of-N sampling draws N responses from a reference model and keeps the one a reward model scores highest.

All works

5 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. Gemma 2: Improving Open Language Models at a Practical Size ↗arXiv:2408.00118 · no summary yetGemma Team et al.2024 · 1,302 citations
  2. Gemma 3 Technical Report ↗arXiv:2503.19786 · no summary yetGemma Team et al.2025 · 1,147 citations
  3. DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetArthur Douillard et al.2022 · 368 citations
  4. Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewardsConference on Neural Information Processing Systems (NeurIPS)Alexandre Rame, Guillaume Couairon, Mustafa Shukor, et al.2023 · 90 citations
  5. BOND: Aligning LLMs with Best-of-N DistillationarXiv:2407.14622Pier Giuseppe Sessa, Robert Dadashi, Leonard Hussenot, et al.2024 · 23 citations

 Co-authors here

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

Venues

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

 Cited by

Papers of our library cite their works 2,440 times (of the 149,439 papers whose bibliographies we read); 640 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/alexandre-rame/