--- title: "Girish Sastry — author profile and papers" description: "Girish Sastry: 2 papers on Elamur Research (2020–2021), h-index 9 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/girish-sastry/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/girish-sastry/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Girish Sastry # Girish Sastry Girish Sastry's papers here deal with large-scale pretraining of neural networks on text and images gathered from the web. A shared question runs through them: can models trained on broad, loosely curated data take on new tasks without collecting labeled examples and fine-tuning for each one? The method is to train very large models and then test them across many benchmarks, with the task described in natural language rather than learned from task-specific training sets. This places the work within [language models and pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) and the extension of those ideas to vision. The most cited of these papers is [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/) (2020), which introduced GPT-3. That paper scaled an autoregressive transformer and showed that it could handle many language tasks when given only an instruction and a handful of demonstrations inside the prompt, with no change to its weights. The authors named this behaviour in-context learning. Close behind it is [Learning Transferable Visual Models From Natural Language Supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/) (2021), the CLIP paper. It trained paired image and text encoders on internet image–caption pairs, teaching them to match each image with its caption. Embedding class names or short text prompts then gives an image classifier without any training on the target dataset. The later of the two papers moves from text alone to vision, applying the web-scale, language-driven pretraining approach to image recognition. Both papers carry the byline of [OpenAI](https://md.research.elamur.ai/free/en/companies/openai/) and come from large team efforts. Co-authors include [Alec Radford](https://md.research.elamur.ai/free/en/authors/alec-radford/), [Ilya Sutskever](https://md.research.elamur.ai/free/en/authors/ilya-sutskever/), [Aditya Ramesh](https://md.research.elamur.ai/free/en/authors/aditya-ramesh/), and [Amanda Askell](https://md.research.elamur.ai/free/en/authors/amanda-askell/) and [Sandhini Agarwal](https://md.research.elamur.ai/free/en/authors/sandhini-agarwal/), who appear on both papers. Girish Sastry has 2 papers in our library, in 2020–2021, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Amanda Askell](https://md.research.elamur.ai/free/en/authors/amanda-askell/), [Sandhini Agarwal](https://md.research.elamur.ai/free/en/authors/sandhini-agarwal/), [Aditya Ramesh](https://md.research.elamur.ai/free/en/authors/aditya-ramesh/). 2 papers in our library · 2020–2021 [OpenAlex](https://openalex.org/A5059260582) · [**h-index 9**](https://openalex.org/authors/A5059260582) · [17 works](https://openalex.org/works?filter=author.id:A5059260582) · [10,269 citations](https://openalex.org/works?filter=author.id:A5059260582&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/girish-sastry/#papers) · [14,053 citations in our library](https://md.research.elamur.ai/free/en/authors/girish-sastry/cited-by/) · 1 more work in our library · [⭐ Paper Star rank #75](https://md.research.elamur.ai/free/en/paper-stars/#star-75) 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=Girish+Sastry) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Girish+Sastry) · [dblp](https://dblp.org/search?q=Girish+Sastry) · [ACL Anthology](https://aclanthology.org/search/?q=Girish+Sastry) ## Affiliations [🏢**OpenAI** San Francisco · United States 2021–2024 · 4 papers](https://md.research.elamur.ai/free/en/companies/openai/) 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. ## Topics [Language models & pretraining 1](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2021** 1 paper](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/) · [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/) ## Papers The most cited first (OpenAlex and our library). 1. **[Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)** *(2020 · 10,782 citations)* The standard approach in NLP has a significant drawback: after pre-training, a model is usually fine-tuned on thousands of labeled examples for each individual task. 2. **[Learning Transferable Visual Models From Natural Language Supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/)** *(2021 · 8,295 citations)* Most computer vision systems learn a fixed list of categories, so each new concept needs more labeled data. ## 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 12 of 18 co-authors with a page, the most papers together first. - [Amanda Askell](https://md.research.elamur.ai/free/en/authors/amanda-askell/) ×2 - [Sandhini Agarwal](https://md.research.elamur.ai/free/en/authors/sandhini-agarwal/) ×2 - [Aditya Ramesh](https://md.research.elamur.ai/free/en/authors/aditya-ramesh/) - [Alec Radford](https://md.research.elamur.ai/free/en/authors/alec-radford/) - [Ariel Herbert-Voss](https://md.research.elamur.ai/free/en/authors/ariel-herbert-voss/) - [Arvind Neelakantan](https://md.research.elamur.ai/free/en/authors/arvind-neelakantan/) - [Benjamin Mann](https://md.research.elamur.ai/free/en/authors/benjamin-mann/) - [Chris Hallacy](https://md.research.elamur.ai/free/en/authors/chris-hallacy/) - [Gabriel Goh](https://md.research.elamur.ai/free/en/authors/gabriel-goh/) - [Gretchen Krueger](https://md.research.elamur.ai/free/en/authors/gretchen-krueger/) - [Ilya Sutskever](https://md.research.elamur.ai/free/en/authors/ilya-sutskever/) - [Jack Clark](https://md.research.elamur.ai/free/en/authors/jack-clark/) ## Cited by Papers of our library cite their works 14,053 times (of the 140,884 papers whose bibliographies we read); [878 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/girish-sastry/cited-by/).