--- title: "Michael S. Ryoo — author profile and papers in our library" description: "Michael S. Ryoo, Stony Brook University: 2 papers on Elamur Research (2022–2026), h-index 40 — affiliations, topics, co-authors and who…" canonical: "https://research.elamur.ai/free/en/authors/michael-s-ryoo/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/michael-s-ryoo/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Michael S. Ryoo # Michael S. Ryoo Michael S. Ryoo has 2 papers in our library, in 2022–2026, most of them on [Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/); often with [Brian Ichter](https://md.research.elamur.ai/free/en/authors/brian-ichter/), [Donghyun Kim](https://md.research.elamur.ai/free/en/authors/donghyun-kim/), [Krzysztof Choromanski](https://md.research.elamur.ai/free/en/authors/krzysztof-choromanski/). 2 papers in our library · 2022–2026 [OpenAlex](https://openalex.org/A5084829008) · [ORCID](https://orcid.org/0000-0002-5452-8332) · [**h-index 40**](https://openalex.org/authors/A5084829008) · [186 works](https://openalex.org/works?filter=author.id:A5084829008) · [9,216 citations](https://openalex.org/works?filter=author.id:A5084829008&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/michael-s-ryoo/#papers) · [🔗 Cited 171 times in our library](https://md.research.elamur.ai/free/en/authors/michael-s-ryoo/cited-by/) · [6 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #4857](https://md.research.elamur.ai/free/en/paper-stars/page/49/#star-4857) 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=Michael+S.+Ryoo) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Michael+S.+Ryoo) · [dblp](https://dblp.org/search?q=Michael+S.+Ryoo) · [ACL Anthology](https://aclanthology.org/search/?q=Michael+S.+Ryoo) ## Affiliations [🎓**Stony Brook University** Stony Brook · United States 2019–2026 · 53 papers*current*](https://md.research.elamur.ai/free/en/universities/stony-brook-university/) · [🎓**Indiana University** Bloomington · United States 2016–2020 · 26 papers](https://md.research.elamur.ai/free/en/universities/indiana-university/) · [🏢**Google** Mountain View · United States 2019–2024 · 21 papers](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**The University of Texas at Austin** Austin · United States 2005–2011 · 18 papers](https://md.research.elamur.ai/free/en/universities/the-university-of-texas-at-austin/) · [🎓**Indiana University Bloomington** Bloomington · United States 2016–2019 · 17 papers](https://md.research.elamur.ai/free/en/universities/indiana-university-bloomington/) · [🔬**Electronics and Telecommunications Research Institute** Daejeon · South Korea 2009–2011 · 14 papers](https://md.research.elamur.ai/free/en/labs/electronics-and-telecommunications-research-institute/) · [🔬**Jet Propulsion Laboratory** Pasadena · United States 2012–2017 · 12 papers](https://ror.org/027k65916) · [🏢**Salesforce** San Francisco · United States 2024–2025 · 7 papers](https://md.research.elamur.ai/free/en/companies/salesforce/) · [🎓**California Institute of Technology** Pasadena · United States 2012–2015 · 6 papers](https://md.research.elamur.ai/free/en/universities/california-institute-of-technology/) · [🎓**Korea Advanced Institute of Science and Technology** Daejeon · South Korea 2005 · 2 papers](https://md.research.elamur.ai/free/en/universities/korea-advanced-institute-of-science-and-technology/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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 5 The field of science this work belongs to (OpenAlex fields).[Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computer Vision and Pattern Recognition · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Language and Linguistics · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) 🧭 Topics 3 Research subjects and languages the work is about.[Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Vision & language · 1 work](https://md.research.elamur.ai/free/en/topics/multimodal/) · [Question answering · 1 work](https://md.research.elamur.ai/free/en/topics/question-answering/) ## Works by year ### 2020s [**2026** 1 paper](https://md.research.elamur.ai/free/en/authors/michael-s-ryoo/year/2026/) · [**2022** 1 paper](https://md.research.elamur.ai/free/en/authors/michael-s-ryoo/year/2022/) ## Papers The most cited first (OpenAlex and our library). 1. **[Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://md.research.elamur.ai/free/en/papers/zeng-2022-socratic-models-composing-zero-shot/)** *(2022 · 302 citations)* Pretrained foundation models pick up different kinds of commonsense depending on their training data. Vision-language models (VLMs) connect text to images, while large language models (LMs) also learn from text-only sources such as code or exam questions. Zeng et al. argue that these differences complement each… 2. **[Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA](https://md.research.elamur.ai/free/en/papers/park-2026-too-many-frames-not-all/)** *(2026 · 13 citations)* Long videos contain a great deal of redundant content, and answering a question about them usually depends on only a few moments. ## All works 8 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. [**Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language arXiv:2204.00598**Andy Zeng, Maria Attarian, Brian Ichter, et al.*2022 · 302 citations*](https://md.research.elamur.ai/free/en/papers/zeng-2022-socratic-models-composing-zero-shot/) 2. **[First-Person Activity Recognition: What Are They Doing to Me? ↗](https://doi.org/10.1109/cvpr.2013.352) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Michael S. Ryoo, Larry H. Matthies*2013 · 283 citations* 3. **[Representation Flow for Action Recognition ↗](https://doi.org/10.1109/cvpr.2019.01018) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**AJ Piergiovanni, Michael S. Ryoo*2019 · 185 citations* 4. **[Privacy-Preserving Human Activity Recognition from Extreme Low Resolution ↗](https://doi.org/10.1609/aaai.v31i1.11233) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Michael S. Ryoo et al.*2017 · 180 citations* 5. **[TokenLearner: Adaptive Space-Time Tokenization for Videos ↗](https://openalex.org/W3214661002) neural information processing systems · no summary yet**Michael S. Ryoo et al.*2021 · 83 citations* 6. **[Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA](https://md.research.elamur.ai/free/en/papers/park-2026-too-many-frames-not-all/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Jongwoo Park, Kanchana Ranasinghe, Kumara Kahatapitiya, et al.*2026 · 13 citations* 7. **[Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding ↗](https://arxiv.org/abs/2512.05774) arXiv (Cornell University) · no summary yet**Ziyang Wang et al.*2025 · 2 citations* 8. **[VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making ↗](https://arxiv.org/abs/2505.03181) arXiv (Cornell University) · no summary yet**Grigsby, Jake et al.*2025* ## Co-authors here 3 co-authors with a page, the most papers together first. - [Brian Ichter](https://md.research.elamur.ai/free/en/authors/brian-ichter/) - [Donghyun Kim](https://md.research.elamur.ai/free/en/authors/donghyun-kim/) - [Krzysztof Choromanski](https://md.research.elamur.ai/free/en/authors/krzysztof-choromanski/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×2 - [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/): [EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/) - Proceedings of the AAAI Conference on Artificial Intelligence - neural information processing systems ## Cited by Papers of our library cite their works 171 times (of the 149,439 papers whose bibliographies we read); [31 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/michael-s-ryoo/cited-by/). Updated 1 November 2026