PeopleofSuperintelligence

Researcher

Sangho Lee

Also known as 이상호

Sangho Lee is a computer vision researcher on Ai2's PRIOR team whose work connects video learning with multimodal models grounded in vision and language. He earned a B.S. in computer science and engineering at Seoul National University in 2017, with a statistics minor, and completed a Ph.D. there under Gunhee Kim in 2023. He coauthored Unified-IO 2, Molmo and PixMo, and Molmo2, covering image, text, audio, action, and video understanding. Molmo and PixMo received a CVPR 2025 Best Paper Honorable Mention.

Works
3

Publication numbers from OpenAlex, as of 22 October 2026. Citations and h-index are hidden because this OpenAlex record may be incomplete or mix in other authors.

Timeline

  1. 2010–2017

    A computer science degree

    At Seoul National University, he earns a B.S. in computer science and engineering in 2017, with a minor in statistics.

  2. 2017–2023

    A doctorate in video learning

    He earns a Ph.D. in computer science and engineering at Seoul National University under Gunhee Kim in 2023. His thesis is titled "Improving Efficiency in Large-Scale Self-Supervised Video Representation Learning."

  3. January 2023–July 2024

    Postdoctoral work at Ai2

    In January 2023, he joins Ai2's PRIOR team as a Postdoctoral Young Investigator.

  4. December 2023

    Unified-IO 2

    In December 2023, he coauthors Unified-IO 2, an autoregressive model that understands and generates image, text, audio, and action.

  5. 2024

    Molmo and PixMo

    In September 2024, he coauthors Molmo and PixMo, a paper that introduces Molmo, a family of vision-language models, and PixMo datasets for detailed image captions, image question answering, and 2D pointing.

  6. 2025

    A CVPR honorable mention

    The Molmo and PixMo paper receives a Best Paper Honorable Mention at CVPR 2025; Sangho Lee is one of its authors.

  7. January 2026

    Molmo2 for video understanding

    In January 2026, he coauthors Molmo2, a vision-language model family for video understanding and grounding. The paper introduces seven video datasets and two multi-image datasets.

  8. Since August 2024

    Research scientist at Ai2

    In August 2024, he becomes a research scientist at the Allen Institute for AI in Seattle, on its PRIOR team. He studies computer vision and multimodal foundation models grounded in vision and language.

Career

  1. Since 2023Allen Institute for AI (Ai2)Postdoctoral Young Investigator, Research scientist

Education

  1. 2023Seoul National UniversityPh.D. in computer science and engineering
  2. 2017Seoul National UniversityB.S. in computer science and engineering

From the biography.

  1. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Allen Institute for AI (Ai2). 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.
  2. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Allen Institute for AI (Ai2). Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.
  3. 72% of AI researchers with top works connect into a single 2,592-person co-author groupIncludes Allen Institute for AI (Ai2). We map the co-author network across 3,593 people shaping AI and 14,977 most-cited papers: 2,592 (72%) form one connected group with a median distance of 5 steps, led in 2-step reach by Yoshua Bengio (570) and in shortest-path bridging by Yoshua Bengio (6.7%).
  4. Direct Form 990 pay in the latest returns of 39 nonprofits with AI people on this site is highest at $2.1M at the Allen Institute for AI (Ai2) (2024)Includes Allen Institute for AI (Ai2). IRS Form 990 compensation across 39 nonprofits with AI people on this site from 2012 to 2025: in the latest returns, Mozilla reports $6.1M including related-company pay (2024) and the Allen Institute for AI (Ai2) leads direct nonprofit pay at $2.1M (2024).

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

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

  1. Sangho Lee | Research Scientist at Ai2 on the PRIOR team sangho-vision.github.io. Checked 22 October 2026.
  2. Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action arxiv.org. Checked 22 October 2026.
  3. Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models arxiv.org. Checked 22 October 2026.
  4. Papers | Ai2 allenai.org. Checked 22 October 2026.
  5. Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding arxiv.org. Checked 22 October 2026.