Elamur Research⌕
☰
home / authors / Fabian Gloeckle

Fabian Gloeckle

Fabian Gloeckle has 2 papers in our library, in 2024, most of them on Language models & pretraining; often with Baptiste Rozière, David Lopez-Paz, Gabriel Synnaeve.

2 papers in our library · 2024

OpenAlex · h-index 3 · 14 works · 457 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 1,076 times in our library · ⭐ Paper Stars ranking: #1984

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

🔬CERMICSChamps-sur-Marne · France2023–2026 · 4 paperscurrent🎓École nationale des ponts et chausséesChamps-sur-Marne · France2023–2026 · 3 paperscurrent🔬Centre National de la Recherche ScientifiqueParis · France2026 · 1 papercurrent

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.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksInformation Systems · 2 worksLanguage and Linguistics · 2 worksComputer Science Applications · 1 work

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 2 works

💡 Concepts 1Key ideas and methods explained on our concept pages.Large language models · 1 work

 Works by year

2020s

20242 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Code Llama: Open Foundation Models for Code (2024 · 1,430 citations)
    Code Llama is Meta AI's family of open code-oriented language models. Rather than training a code model from scratch, the authors take pretrained Llama 2 weights and specialize them through a chain of training stages. The main stage trains on a code-dominated, near-deduplicated corpus of public code, with some…
  2. Better & Faster Large Language Models via Multi-token Prediction (2024 · 90 citations)
    LLMs such as GPT and Llama learn by guessing only the single next token. The authors argue this objective needs a lot of data and favours short-range patterns. Gloeckle et al. (FAIR at Meta) instead train models to forecast several upcoming tokens from every position. A shared transformer trunk feeds n separate…

 Co-authors here

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

 Cited by

Papers of our library cite their works 1,076 times (of the 149,439 papers whose bibliographies we read); 263 citing papers with a page here →.

Updated

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