PeopleofSuperintelligence

Researcher

Ranjay Krishna

Ranjay Krishna is a computer vision researcher whose work connects visual reasoning with human interaction. At Stanford, he first-authored the Visual Genome dataset paper and earned a computer science PhD in 2021; his research introduced scene graphs and received Outstanding Paper honors at NeurIPS and ACL in 2021. He coauthored an AI decision-support paper that received a CSCW Best Paper Honorable Mention in 2023. His 2024 work included the open Molmo and PixMo models and datasets and Visual Sketchpad; Molmo received a CVPR Best Paper Honorable Mention in 2025, and MIT Technology Review named him to its Innovators Under 35 Asia Pacific list. He is an assistant professor at the University of Washington, co-directs RAIVN, and serves as a member of technical staff at Microsoft SuperIntelligence.

Works
239
Citations
15,606
h-index
36
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. By 2016

    Visual Genome and a thesis award

    With Cornell degrees in electrical and computer engineering and computer science, he earns a master's in computer science at Stanford. In 2016, he is first author of the Visual Genome paper, which presents over 100,000 images annotated with objects, attributes and relationships; his Visual Genome master's thesis wins the Christofer Stephenson Memorial Award for best Stanford CS thesis.

  2. 2021

    Stanford PhD and scene graphs

    He earns a Stanford PhD in computer science in 2021 with the dissertation Visual Intelligence Through Human Learning, co-advised by Fei-Fei Li and Michael Bernstein. His research connects computer vision and human interaction, and introduces dense scene graphs for representing visual information. His work receives Outstanding Paper honors at NeurIPS 2021 and ACL 2021.

  3. 2021–2022

    From Facebook AI to UW

    In 2021, he spends a year as a research scientist at Facebook AI Research after earning his PhD. In 2022, he joins the Paul G. Allen School of Computer Science & Engineering at the University of Washington as an assistant professor focused on artificial intelligence.

  4. 2023

    AI explanations at CSCW

    In 2023, he coauthors Explanations Can Reduce Overreliance on AI Systems during Decision-Making, which receives a Best Paper Honorable Mention at CSCW.

  5. 2024

    Molmo, PixMo and Sketchpad

    In September 2024, he is one of 50 authors of Molmo and PixMo, an open vision-language model and dataset project developed at Ai2. The 72B model outperforms larger proprietary systems including Claude 3.5 Sonnet and Gemini 1.5 Pro and Flash, with GPT-4o ahead. He also coauthors Visual Sketchpad, a framework that gives multimodal language models a visual sketchpad and tools to draw while reasoning.

  6. 2025

    Molmo CVPR award and MIT list

    In 2025, his Molmo paper receives a Best Paper Honorable Mention at CVPR. MIT Technology Review names him to its Innovators Under 35 Asia Pacific list. At UW, he directs the RAIVN lab and leads Ai2's PRIOR team.

  7. 2026

    CAREER Award and Molmo2

    In 2026, he receives an NSF CAREER Award to develop open-source video-language models. His Molmo2 paper on open weights and data for video understanding and grounding is nominated for the CVPR 2026 Best Paper award.

  8. As of October 2026

    Microsoft Superintelligence role

    In March 2026, Microsoft hires him, Ali Farhadi, Hanna Hajishirzi and Sophie Lebrecht for Mustafa Suleyman's Superintelligence team. As of October 2026, he is an assistant professor at the Paul G. Allen School, a member of technical staff at Microsoft SuperIntelligence, and co-directs UW's RAIVN lab.

Career

  1. Since 2026MicrosoftMember of technical staff
  2. Since 2022University of WashingtonAssistant professor
  3. 2023–2026Allen Institute for AI (Ai2)PRIOR team lead
  4. 2021–2022FAIR (Meta)Research scientist

Education

  1. 2021Stanford UniversityMaster's degree in Computer Science
  2. Cornell University

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations2017 · International Journal of Computer Vision · 5,095 citationsWith Fei-Fei Li, Li-Jia Li and Yuke Zhu
  2. On the Opportunities and Risks of Foundation Models2021 · 2,640 citationsWith Alex Tamkin, Antoine Bosselut, Christopher D. Manning, Christopher Potts, Christopher Ré and Dan Jurafsky
  3. Dense-Captioning Events in Videos2017 · IEEE International Conference on Computer Vision (ICCV) · 1,281 citationsWith Fei-Fei Li
  4. Visual Relationship Detection with Language Priors2016 · Lecture notes in computer science · 1,118 citationsWith Fei-Fei Li
  5. Image retrieval using scene graphs2015 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 1,100 citationsWith Fei-Fei Li and Li-Jia Li

From OpenAlex, as of 21 October 2026.

  1. 16% of AI career moves in the 2020s went from a university to a companyIncludes Ranjay Krishna. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  2. Among employers with 30+ full-time cases, OpenAI leads primary technical role H-1B pay at $310,000, and Amazon, Google and Microsoft file 57% of all casesIncludes Microsoft. Across 440,669 certified US H-1B filings from 44 employers (FY2020–FY2026), OpenAI leads primary technical role base pay at $310,000 and xAI leads overall base pay at $290,000.
  3. Google had the most people shaping AI every year from 2014 to 2025Includes Microsoft. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  4. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Microsoft. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Ranjay Krishna yet. Send us a free-licensed photo.

  1. Ranjay Krishna – Brown Institute brown.stanford.edu. Checked 21 October 2026.
  2. [1602.07332] Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations arxiv.org. Checked 21 October 2026.
  3. Ranjay Krishna - The Mathematics Genealogy Project mathgenealogy.org. Checked 21 October 2026.
  4. Recent faculty hires expand the Allen School’s leadership in machine learning, computational biology, systems security, and more news.cs.washington.edu. Checked 21 October 2026.
  5. Ranjay Krishna - Home ranjaykrishna.com. Checked 21 October 2026.
  6. Ranjay Krishna, Assistant Professor - Paul G. Allen School of Computer Science & Engineering cs.washington.edu. Checked 21 October 2026.
  7. Awards – CSCW 2023 cscw.acm.org. Checked 21 October 2026.
  8. [2409.17146] Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models arxiv.org. Checked 21 October 2026.
  9. Allen School faculty and alum recognized in MIT Technology Review’s Innovators Under 35 Asia Pacific news.cs.washington.edu. Checked 21 October 2026.
  10. [2406.09403] Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models arxiv.org. Checked 21 October 2026.
  11. Five faculty members receive NSF CAREER Awards cs.washington.edu. Checked 21 October 2026.
  12. Microsoft Hires Former Ai2 CEO Farhadi for Suleyman AI Team winbuzzer.com. Checked 21 October 2026.