PeopleofSuperintelligence

Researcher

Tsu-Jui Fu

Also known as Ray

Tsu-Jui Fu is a computer scientist whose research spans vision+language, image editing and visual generation. He earned a computer science B.S. at National Tsing Hua University and completed a computer science Ph.D. at UC Santa Barbara, where he worked with UCSB NLP. His research includes fashion-guided 3D human generation, multimodal instruction-based image editing and reward-guided text-to-video generation. In August 2026, he coauthored a register-based method to reduce artifacts in diffusion-transformer image generation. His career includes research roles at Apple AI/ML and Meta GenAI; since 2025, he is a senior research scientist at Apple AI/ML, working on vision+language and unified visual generation.

Now at
Apple
Badges

Timeline

  1. 2014–2018

    Computer science bachelor's degree

    From 2014 to 2018, he earns a B.S. in computer science at National Tsing Hua University.

  2. 2019–2024

    Doctoral research at UCSB NLP

    From 2019 to 2024, he works as a research assistant with UCSB NLP and completes a computer science Ph.D. at UC Santa Barbara, advised by William Yang Wang.

  3. 2023

    Fashion-guided 3D human generation

    In 2023, he coauthors Text-guided 3D Human Generation from 2D Collections. Its Compositional Cross-modal Human model uses cross-modal attention to fuse compositional human rendering with fashion semantics.

  4. 2024

    MGIE and T2V-Turbo

    In 2024, he coauthors Guiding Instruction-based Image Editing via Multimodal Large Language Models, which introduces MGIE to derive expressive instructions and provide explicit guidance for image editing. He also coauthors T2V-Turbo, which integrates differentiable reward feedback into consistency distillation for fast, high-quality video generation.

  5. 2024–2025

    Research scientist at Apple AI/ML

    From 2024 to 2025, he works as a research scientist at Apple AI/ML. In 2025, he coauthors UniVG, a generalist diffusion model for unified image generation and editing, and STIV, a scalable text- and image-conditioned video-generation model.

  6. 2025

    Senior scientist at Meta GenAI

    In 2025, he serves as a senior research scientist at Meta GenAI.

  7. August 2026

    Taming outlier tokens

    In August 2026, he coauthors Taming Outlier Tokens in Diffusion Transformers, which introduces Dual-Stage Registers to reduce outlier artifacts and improve image-generation quality.

  8. Since 2025

    Senior research scientist at Apple AI/ML

    Since 2025, he is a senior research scientist at Apple AI/ML, where his research spans vision+language and unified visual generation.

Career

  1. Since 2024AppleResearch Scientist, Senior Research Scientist
  2. 2025MetaSenior Research Scientist
  3. 2019–2024University of California, Santa BarbaraResearch Assistant

Education

  1. 2024University of California, Santa BarbaraPh.D. in Computer Science
  2. 2018National Tsing Hua UniversityB.S. in Computer Science

From the biography.

  1. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Tsu-Jui Fu. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  2. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Apple. Our estimates of where the 943 people shaping AI who worked at Google and Google DeepMind work now: 446 at Google and 452 across 278 other organizations.
  3. 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 Apple. 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.
  4. The top 10 organizations employed 22% of people shaping AI in 2025: 51% of company researchers and 21% of university researchersIncludes Apple. We estimate the share of people shaping AI who worked at the top 10 organizations each year from 1955 to 2025, comparing concentration across companies, universities, and institutes and labs.

Colleagues

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

Sources and credits

Photo: We have no published photo of Tsu-Jui Fu yet. Send us a free-licensed photo.

  1. Tsu-Jui Fu | Apple AI/ML Senior Research Scientist｜影像生成×多模態AI×模擬面試與研究指導 | 大大帶我飛 dada-fly.com. Checked 21 October 2026.
  2. UC Santa Barbara AI Group nlp.cs.ucsb.edu. Checked 21 October 2026.
  3. Ray@Apple tsujuifu.github.io. Checked 21 October 2026.
  4. Text-guided 3D Human Generation from 2D Collections - ACL Anthology aclanthology.org. Checked 21 October 2026.
  5. Guiding Instruction-based Image Editing via Multimodal Large Language Models proceedings.iclr.cc. Checked 21 October 2026.
  6. T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback proceedings.neurips.cc. Checked 21 October 2026.
  7. International Conference on Computer Vision (ICCV) 2025 - Apple Machine Learning Research pr-mlr-shield-prod.apple.com. Checked 21 October 2026.
  8. STIV: Scalable Text and Image Conditioned Video Generation - Apple Machine Learning Research machinelearning.apple.com. Checked 21 October 2026.
  9. Taming Outlier Tokens in Diffusion Transformers - Apple Machine Learning Research machinelearning.apple.com. Checked 21 October 2026.