--- title: "Ross Wightman — author profile and papers" description: "Ross Wightman: 2 papers on Elamur Research (2022), h-index 7 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/ross-wightman/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/ross-wightman/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Ross Wightman # Ross Wightman Ross Wightman's papers here belong to [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) research, with a focus on training image-text models at very large scale using resources anyone can obtain. A recurring question is how to move this kind of work out of a handful of industry labs, where training sets and models have largely stayed private. The methods combine web-scale collection of paired images and captions, automatic filtering of those pairs, and contrastive language-image pre-training run on the open-source OpenCLIP codebase. The most cited of these works is [LAION-5B](https://md.research.elamur.ai/free/en/papers/schuhmann-2022-laion-5b-open-large-scale/), which released a public collection of billions of image-text pairs. The images and their alt-text were drawn from Common Crawl and downloaded in a distributed fashion. Pairs were kept only when an existing CLIP model judged the image and text similar enough. OpenCLIP models trained on a subset showed that the collection works as training material. A companion study, [Reproducible scaling laws for contrastive language-image learning](https://md.research.elamur.ai/free/en/papers/cherti-2022-reproducible-scaling-laws-contrastive-language/), used that public data to measure how CLIP performance changes as the vision encoder, the dataset and the number of training samples seen grow. Because both the data and the code are open, the study can be repeated in full, which earlier scaling work on closed models did not allow. Both papers date from 2022, and together they point in one direction: open datasets and open models as a shared foundation for multimodal research. The work is collaborative. Recurring co-authors include [Christoph Schuhmann](https://md.research.elamur.ai/free/en/authors/christoph-schuhmann/), [Romain Beaumont](https://md.research.elamur.ai/free/en/authors/romain-beaumont/), [Mehdi Cherti](https://md.research.elamur.ai/free/en/authors/mehdi-cherti/), [Mitchell Wortsman](https://md.research.elamur.ai/free/en/authors/mitchell-wortsman/) and [Cade Gordon](https://md.research.elamur.ai/free/en/authors/cade-gordon/), with [Jenia Jitsev](https://md.research.elamur.ai/free/en/authors/jenia-jitsev/) and [Ludwig Schmidt](https://md.research.elamur.ai/free/en/authors/ludwig-schmidt/) among other contributors. Ross Wightman has 2 papers in our library, in 2022, most of them on [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/); often with [Cade Gordon](https://md.research.elamur.ai/free/en/authors/cade-gordon/), [Christoph Schuhmann](https://md.research.elamur.ai/free/en/authors/christoph-schuhmann/), [Mehdi Cherti](https://md.research.elamur.ai/free/en/authors/mehdi-cherti/). 2 papers in our library · 2022 [OpenAlex](https://openalex.org/A5048883432) · [**h-index 7**](https://openalex.org/authors/A5048883432) · [12 works](https://openalex.org/works?filter=author.id:A5048883432) · [2,461 citations](https://openalex.org/works?filter=author.id:A5048883432&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/ross-wightman/#papers) · [🔗 477 citations in our library](https://md.research.elamur.ai/free/en/authors/ross-wightman/cited-by/) · [⭐ Paper Star rank #1119](https://md.research.elamur.ai/free/en/paper-stars/page/12/#star-1119) 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=Ross+Wightman) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Ross+Wightman) · [dblp](https://dblp.org/search?q=Ross+Wightman) · [ACL Anthology](https://aclanthology.org/search/?q=Ross+Wightman) ## Topics [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/ross-wightman/year/2022/) ## Papers The most cited first (OpenAlex and our library). 1. **[LAION-5B: An open large-scale dataset for training next generation image-text models](https://md.research.elamur.ai/free/en/papers/schuhmann-2022-laion-5b-open-large-scale/)** *(2022 · 1,400 citations)* Recent image-text models such as CLIP, ALIGN, BASIC and Imagen are trained on hundreds of millions to billions of image-text pairs collected from the web. 2. **[Reproducible scaling laws for contrastive language-image learning](https://md.research.elamur.ai/free/en/papers/cherti-2022-reproducible-scaling-laws-contrastive-language/)** *(2022 · 750 citations)* Earlier scaling-law research mostly used closed data and models, or looked only at language or only at vision. ## Co-authors here 12 co-authors with a page, the most papers together first. - [Cade Gordon](https://md.research.elamur.ai/free/en/authors/cade-gordon/) ×2 - [Christoph Schuhmann](https://md.research.elamur.ai/free/en/authors/christoph-schuhmann/) ×2 - [Mehdi Cherti](https://md.research.elamur.ai/free/en/authors/mehdi-cherti/) ×2 - [Mitchell Wortsman](https://md.research.elamur.ai/free/en/authors/mitchell-wortsman/) ×2 - [Romain Beaumont](https://md.research.elamur.ai/free/en/authors/romain-beaumont/) ×2 - [Aarush Katta](https://md.research.elamur.ai/free/en/authors/aarush-katta/) - [Clayton Mullis](https://md.research.elamur.ai/free/en/authors/clayton-mullis/) - [Gabriel Ilharco](https://md.research.elamur.ai/free/en/authors/gabriel-ilharco/) - [Jenia Jitsev](https://md.research.elamur.ai/free/en/authors/jenia-jitsev/) - [Ludwig Schmidt](https://md.research.elamur.ai/free/en/authors/ludwig-schmidt/) - [Richard Vencu](https://md.research.elamur.ai/free/en/authors/richard-vencu/) - [Theo Coombes](https://md.research.elamur.ai/free/en/authors/theo-coombes/) ## Cited by Papers of our library cite their works 477 times (of the 140,884 papers whose bibliographies we read); [34 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/ross-wightman/cited-by/).