PeopleofSuperintelligence

Researcher

Yue Yang

Yue Yang is a multimodal AI researcher who coauthored Molmo and PixMo, a paper on open weights and open data for vision-language models. They earned robotics and computer-science degrees at the University of Pennsylvania. At Penn, they coauthored KnoBo, which uses medical knowledge in image analysis. In 2025, they coauthored CoSyn, a framework for generating synthetic data for text-rich images. They worked as a research scientist in Ai2’s PRIOR group through 2026 and are a Member of Technical Staff at Thinking Machines Lab.

Works
99
Citations
956
h-index
17

Publication numbers from OpenAlex, as of 15 October 2026.

Timeline

  1. 2024

    A Penn doctoral researcher

    In 2024, they are a Penn doctoral student and coauthor KnoBo, a method that uses knowledge from medical textbooks and PubMed to guide medical-image analysis. Their Penn training includes an M.S. in robotics and a Ph.D. in Computer and Information Science, advised by Mark Yatskar and Chris Callison-Burch.

  2. 2024

    Molmo and PixMo

    In 2024, they coauthor Molmo and PixMo, a paper on open weights and open data for vision-language models.

  3. 2025

    Synthetic data for text-rich images

    In 2025, they coauthor CoSyn, a framework that uses text-only language models to generate code-rendered synthetic images for text-rich image tasks.

  4. 2025–2026

    Research scientist at Ai2

    They join Ai2’s PRIOR group as a research scientist in 2025 and work in vision and language research through 2026.

  5. Since 2026

    Member of Technical Staff

    In 2026, they join Thinking Machines Lab as a Member of Technical Staff.

Sources and credits

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

  1. Yue Yang - Multimodal AI yueyang.ai. Checked 15 October 2026.
  2. Yue Yang | alphaXiv alphaxiv.org. Checked 15 October 2026.
  3. Training Medical AI with Knowledge, Not Shortcuts | Penn Engineering engineering.upenn.edu. Checked 15 October 2026.
  4. A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis arxiv.org. Checked 15 October 2026.
  5. Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models arxiv.org. Checked 15 October 2026.
  6. Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation - ACL Anthology aclanthology.org. Checked 15 October 2026.
  7. Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation yueyang.ai. Checked 15 October 2026.
  8. Perceptual Reasoning and Interaction Research - People prior.allenai.org. Checked 15 October 2026.