--- title: "Arthur Mensch — author profile and papers" description: "Arthur Mensch: 2 papers on Elamur Research (2022), h-index 10 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/arthur-mensch/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/arthur-mensch/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Arthur Mensch # Arthur Mensch Arthur Mensch works on large neural models for language and vision. The papers here, both from 2022, ask how such models should be built and trained. One looks at how model size and training data should grow together under a limited compute budget. The other looks at how a single model can handle images, video and text without task-specific fine-tuning. The methods are large-scale empirical ones: many models are trained and compared to find rules that guide practice. The work sits within [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) and [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/). The most cited of these papers is [Flamingo: a Visual Language Model for Few-Shot Learning](https://md.research.elamur.ai/free/en/papers/alayrac-2022-flamingo-visual-language-model-few/). It presents a family of visual language models that learn new image and video tasks from a handful of examples placed in the prompt. Unlike contrastive image–text systems, which can only rate how well a caption matches a picture, these models write open-ended text. The second paper, [Training Compute-Optimal Large Language Models](https://md.research.elamur.ai/free/en/papers/hoffmann-2022-training-compute-optimal-large-language/), studies how a fixed amount of compute should be shared between parameter count and training tokens. Three separate estimation methods point to the same answer: the two should be scaled in equal proportion. The study concludes that many language models of the time were oversized and trained on too little text. Both papers are also the most recent ones here, and together they show the work moving between efficient language-model scaling and multimodal few-shot learning. The papers are described as coming from DeepMind teams. Bylines from 2021 and 2022 also list the [Centre National de la Recherche Scientifique](https://md.research.elamur.ai/free/en/labs/centre-national-de-la-recherche-scientifique/). The most frequent co-author here is [Eliza Rutherford](https://md.research.elamur.ai/free/en/authors/eliza-rutherford/). Other collaborators include [Jean-Baptiste Alayrac](https://md.research.elamur.ai/free/en/authors/jean-baptiste-alayrac/), [Sebastian Borgeaud](https://md.research.elamur.ai/free/en/authors/sebastian-borgeaud/) and [Johannes Welbl](https://md.research.elamur.ai/free/en/authors/johannes-welbl/). Arthur Mensch has 2 papers in our library, in 2022, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/); often with [Eliza Rutherford](https://md.research.elamur.ai/free/en/authors/eliza-rutherford/), [Aidan Clark](https://md.research.elamur.ai/free/en/authors/aidan-clark/), [Jean-Baptiste Alayrac](https://md.research.elamur.ai/free/en/authors/jean-baptiste-alayrac/). 2 papers in our library · 2022 [OpenAlex](https://openalex.org/A5110691380) · [ORCID](https://orcid.org/0000-0001-7866-0461) · [**h-index 10**](https://openalex.org/authors/A5110691380) · [19 works](https://openalex.org/works?filter=author.id:A5110691380) · [3,961 citations](https://openalex.org/works?filter=author.id:A5110691380&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/arthur-mensch/#papers) · [🔗 4,216 citations in our library](https://md.research.elamur.ai/free/en/authors/arthur-mensch/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Star rank #796](https://md.research.elamur.ai/free/en/paper-stars/page/8/#star-796) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Arthur+Mensch) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Arthur+Mensch) · [dblp](https://dblp.org/search?q=Arthur+Mensch) · [ACL Anthology](https://aclanthology.org/search/?q=Arthur+Mensch) ## Affiliations [🔬**Centre National de la Recherche Scientifique** Paris · France 2021–2022 · 2 papers](https://md.research.elamur.ai/free/en/labs/centre-national-de-la-recherche-scientifique/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 more institutions on single bylines are not listed. ## Topics [Language models & pretraining (2)](https://md.research.elamur.ai/free/en/topics/language-models/) · [Vision & language (1)](https://md.research.elamur.ai/free/en/topics/multimodal/) ## Works by year ### 2020s [**2022** 2 papers](https://md.research.elamur.ai/free/en/authors/arthur-mensch/year/2022/) ## Papers The most cited first (OpenAlex and our library). 1. **[Flamingo: a Visual Language Model for Few-Shot Learning](https://md.research.elamur.ai/free/en/papers/alayrac-2022-flamingo-visual-language-model-few/)** *(2022 · 2,108 citations)* Most vision systems still need thousands of labelled examples and careful fine-tuning for each new task. Contrastive image–text models avoid fine-tuning, but they only score text–image similarity and cannot generate free-form language. This DeepMind paper introduces Flamingo, a family of Visual Language Models (3B… 2. **[Training Compute-Optimal Large Language Models](https://md.research.elamur.ai/free/en/papers/hoffmann-2022-training-compute-optimal-large-language/)** *(2022 · 1,110 citations)* The authors from DeepMind investigate how best to split a fixed compute budget (FLOPs) between two things: the size of a transformer language model and the number of tokens it is trained on. ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 10 co-authors with a page, the most papers together first. - [Eliza Rutherford](https://md.research.elamur.ai/free/en/authors/eliza-rutherford/) ×2 - [Aidan Clark](https://md.research.elamur.ai/free/en/authors/aidan-clark/) - [Jean-Baptiste Alayrac](https://md.research.elamur.ai/free/en/authors/jean-baptiste-alayrac/) - [Jeff Donahue](https://md.research.elamur.ai/free/en/authors/jeff-donahue/) - [Johannes Welbl](https://md.research.elamur.ai/free/en/authors/johannes-welbl/) - [Katie Millican](https://md.research.elamur.ai/free/en/authors/katie-millican/) - [Lisa Anne Hendricks](https://md.research.elamur.ai/free/en/authors/lisa-anne-hendricks/) - [Roman Ring](https://md.research.elamur.ai/free/en/authors/roman-ring/) - [Sebastian Borgeaud](https://md.research.elamur.ai/free/en/authors/sebastian-borgeaud/) - [Trevor Cai](https://md.research.elamur.ai/free/en/authors/trevor-cai/) ## Cited by Papers of our library cite their works 4,216 times (of the 140,884 papers whose bibliographies we read); [320 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/arthur-mensch/cited-by/).