--- title: "Sebastian Goodman — author profile and papers" description: "Sebastian Goodman, Google: 2 papers on Elamur Research (2018–2022), h-index 10 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/sebastian-goodman/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/sebastian-goodman/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Sebastian Goodman # Sebastian Goodman Sebastian Goodman works on vision and language. The questions are how to gather large amounts of paired image and text material from the web, and how to train models that turn an image into fluent text. The two papers here share a concern with scale. Both draw their training material automatically from web pages rather than from small hand-annotated sets. Both treat captioning and related tasks as text generation conditioned on an image. The work sits within [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) and extends into [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/). The most cited of these papers is [Conceptual Captions](https://md.research.elamur.ai/free/en/papers/sharma-2018-conceptual-captions-cleaned-hypernymed-image/) (2018). It introduced a dataset of roughly 3.3 million image–caption pairs, built by filtering alt-text from billions of web images. The filtering checked image properties, text quality and the agreement between picture and words. Specific names, places and dates were then swapped for more general terms, so that captions describe what is visible rather than who or where. The resulting resource is far larger than the hand-curated MS-COCO set that captioning models had mostly relied on. The later paper, [PaLI](https://md.research.elamur.ai/free/en/papers/chen-2022-pali-jointly-scaled-multilingual-language/) (2022), turns from building data to scaling the model itself. It casts every task as image plus prompt in, text out. Vision Transformer patch features are passed to an mT5 encoder-decoder. To balance the two halves, the work trains a 4-billion-parameter vision encoder, ViT-e. For pre-training it assembles WebLI, which gathers roughly 10 billion images and their accompanying text from across the web in many languages. Goodman's papers carry a [Google](https://md.research.elamur.ai/free/en/companies/google/) (United States) affiliation in Mountain View, appearing from 2018 to 2024. Co-authors on these papers include [Radu Soricut](https://md.research.elamur.ai/free/en/authors/radu-soricut/), [Xi Chen](https://md.research.elamur.ai/free/en/authors/xi-chen/), [Lucas Beyer](https://md.research.elamur.ai/free/en/authors/lucas-beyer/), Xiao Wang, Alexander Kolesnikov and Basil Mustafa. Sebastian Goodman has 2 papers in our library, in 2018–2022, most of them on [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/), [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/); often with [Alexander Kolesnikov](https://md.research.elamur.ai/free/en/authors/alexander-kolesnikov/), [Basil Mustafa](https://md.research.elamur.ai/free/en/authors/basil-mustafa/), [Lucas Beyer](https://md.research.elamur.ai/free/en/authors/lucas-beyer/). 2 papers in our library · 2018–2022 [OpenAlex](https://openalex.org/A5090365098) · [**h-index 10**](https://openalex.org/authors/A5090365098) · [14 works](https://openalex.org/works?filter=author.id:A5090365098) · [3,150 citations](https://openalex.org/works?filter=author.id:A5090365098&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/sebastian-goodman/#papers) · [🔗 711 citations in our library](https://md.research.elamur.ai/free/en/authors/sebastian-goodman/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Star rank #1052](https://md.research.elamur.ai/free/en/paper-stars/page/11/#star-1052) 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=Sebastian+Goodman) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Sebastian+Goodman) · [dblp](https://dblp.org/search?q=Sebastian+Goodman) · [ACL Anthology](https://aclanthology.org/search/?q=Sebastian+Goodman) ## Affiliations [🏢**Google** Mountain View · United States 2018–2024 · 12 papers*current*](https://md.research.elamur.ai/free/en/companies/google/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Concepts, shelves and topics Of its works in our library: the number of works on each and its rating among them. 📚 Shelves 2[Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Computer Vision and Pattern Recognition · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) 🧭 Topics 2[Vision & language · 2 works](https://md.research.elamur.ai/free/en/topics/multimodal/) · [Multilingual & cross-lingual NLP · 1 work](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) ## Works by year ### 2020s [**2022** 1 paper](https://md.research.elamur.ai/free/en/papers/chen-2022-pali-jointly-scaled-multilingual-language/) ### 2010s [**2018** 1 paper](https://md.research.elamur.ai/free/en/papers/sharma-2018-conceptual-captions-cleaned-hypernymed-image/) ## Papers The most cited first (OpenAlex and our library). 1. **[Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning](https://md.research.elamur.ai/free/en/papers/sharma-2018-conceptual-captions-cleaned-hypernymed-image/)** *(2018 · 2,285 citations)* Image captioning models had been trained mostly on MS-COCO. That dataset is hand-curated and fairly small for deep networks, at around 120K images. The authors address this with Conceptual Captions, a dataset of about 3.3M image–caption pairs harvested automatically from the web. A Flume pipeline started from the… 2. **[PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://md.research.elamur.ai/free/en/papers/chen-2022-pali-jointly-scaled-multilingual-language/)** *(2022 · 341 citations)* PaLI (Pathways Language and Image model), from Google Research, explores how to scale vision-language models so that one network can handle many image, text and multimodal tasks across many languages. ## All works 3 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. **[Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning](https://md.research.elamur.ai/free/en/papers/sharma-2018-conceptual-captions-cleaned-hypernymed-image/)**Piyush Sharma, Nan Ding, Sebastian Goodman, et al.*[Annual Meeting of the Association for…](https://md.research.elamur.ai/free/en/venues/acl/) · 2,285 citations* 2. [**PaLI: A Jointly-Scaled Multilingual Language-Image Model**Xi Chen, Xiao Wang, Soravit Changpinyo, et al.*arXiv:2209.06794 · 341 citations*](https://md.research.elamur.ai/free/en/papers/chen-2022-pali-jointly-scaled-multilingual-language/) 3. **[Scaling Up Models and Data with t5x and seqio](https://arxiv.org/abs/2203.17189) (original ↗)**Adam Roberts et al.*2022 · arXiv:2203.17189 · 123 citations · no summary yet* ## Co-authors here 7 co-authors with a page, the most papers together first. - [Alexander Kolesnikov](https://md.research.elamur.ai/free/en/authors/alexander-kolesnikov/) - [Basil Mustafa](https://md.research.elamur.ai/free/en/authors/basil-mustafa/) - [Lucas Beyer](https://md.research.elamur.ai/free/en/authors/lucas-beyer/) - [Radu Soricut](https://md.research.elamur.ai/free/en/authors/radu-soricut/) - [Soravit Changpinyo](https://md.research.elamur.ai/free/en/authors/soravit-changpinyo/) - [Xi Chen](https://md.research.elamur.ai/free/en/authors/xi-chen/) - [Xiao Wang](https://md.research.elamur.ai/free/en/authors/xiao-wang/) ## Venues Where their works here were published, the most works first. - [Annual Meeting of the Association for Computational…](https://md.research.elamur.ai/free/en/venues/acl/) ## Cited by Papers of our library cite their works 711 times (of the 141,840 papers whose bibliographies we read); [93 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/sebastian-goodman/cited-by/). Updated 24 October 2026