Elamur Research⌕
☰
home / authors / Nicolas Le Roux

Nicolas Le Roux

Nicolas Le Roux has 2 papers in our library, in 2023–2024, most of them on Language models & pretraining, Reasoning; often with Alessandro Sordoni, Aaron Courville, Adam Trischler.

2 papers in our library · 2023–2024

OpenAlex · ORCID · h-index 24 · 84 works · 5,973 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 80 times in our library · ⭐ Paper Stars ranking: #8217

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

🏢MicrosoftRedmond · United States2025 · 2 paperscurrent🏢GoogleMountain View · United States2017–2021 · 12 papers🎓Université de MontréalMontreal · Canada2003–2022 · 9 papers🔬Institut national de recherche en sciences et technologies du numériqueLe Chesnay-Rocquencourt · France2011–2013 · 8 papers🔬École Normale Supérieure - PSLParis · France2011–2012 · 7 papers🏢CriteoParis · France2015–2017 · 4 papers🔬SIERRA: Apprentissage Statistique et optimisationParis · France2011–2012 · 3 papers🎓McGill UniversityMontreal · Canada2021–2022 · 2 papers🏢Microsoft ResearchCambridge · United Kingdom2010 · 2 papers🔬Centre de recherches mathématiquesMontreal · Canada2004–2006 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 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.

📚 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.Language models & pretraining · 2 worksReasoning · 1 work

 Works by year

2020s

20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. VinePPO: Refining Credit Assignment in RL Training of LLMs (2024 · 63 citations)
    When large language models are trained with reinforcement learning on multi-step reasoning, the reward arrives only at the end.
  2. Joint Prompt Optimization of Stacked LLMs using Variational Inference (2023 · 23 citations)
    The paper treats an instruction-following LLM as a stochastic "language layer." The layer maps a text input to a distribution over text outputs, and its trainable parameters are natural-language prompts rather than weights.

 Co-authors here

9 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 80 times (of the 149,439 papers whose bibliographies we read); 23 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/nicolas-le-roux/