PeopleofSuperintelligence

Researcher

Fan Bao

Also known as 鲍凡

Fan Bao is a diffusion researcher whose work spans sampling, image and multimodal generation, and video. He earned a B.S. in computer science and technology at Tsinghua in 2019 and completed a Ph.D. through its TSAIL Group under Jun Zhu and Bo Zhang in 2023. Analytic-DPM won an ICLR Outstanding Paper Award in 2022, and he coauthored DPM-Solver, U-ViT, and UniDiffuser. MIT Technology Review named him to its 2023 Innovators Under 35 list, and he coauthored Vidu in 2024 and Diffusion Bridge Implicit Models in 2025. As of October 2026, he is co-founder and CTO of ShengShu Technology; in September 2026, he coauthored Vidu S2, whose models support real-time character interaction and video editing.

Now at
ShengShu Technology
Badges

Timeline

  1. 2019–2023

    Degrees at Tsinghua

    He earns a B.S. in computer science and technology from Tsinghua University in July 2019. In 2023, he completes a Ph.D. through the university's TSAIL Group in the Department of Computer Science and Technology, advised by Jun Zhu and Bo Zhang.

  2. 2022

    Analytic-DPM wins an ICLR award

    In 2022, he coauthors Analytic-DPM, which derives analytic forms for the optimal reverse variance and optimal KL divergence in diffusion probabilistic models. The paper wins an Outstanding Paper Award at ICLR in 2022.

  3. 2022

    DPM-Solver speeds sampling

    At NeurIPS in 2022, he coauthors DPM-Solver, a high-order solver for diffusion ODEs that generates high-quality samples in 10 to 20 function evaluations without further training.

  4. 2023

    U-ViT and UniDiffuser

    In 2023, he coauthors U-ViT, a ViT backbone for diffusion image generation, and UniDiffuser, a transformer framework that fits marginal, conditional, and joint multimodal distributions in one model.

  5. 2023

    Innovators Under 35

    MIT Technology Review names him to its 2023 Innovators Under 35 list in artificial intelligence and robotics.

  6. 2024

    Vidu text-to-video generation

    In 2024, he coauthors Vidu, a text-to-video diffusion model built on U-ViT that can produce 1080p videos up to 16 seconds in one generation.

  7. 2025

    Diffusion Bridge Implicit Models

    In 2025, he coauthors Diffusion Bridge Implicit Models, which generalizes denoising diffusion bridge models with non-Markovian diffusion bridges and samples up to 25 times faster than the vanilla DDBM sampler.

  8. As of October 2026

    ShengShu CTO and Vidu S2

    As of October 2026, he is co-founder and CTO of ShengShu Technology. In September 2026, he coauthors Vidu S2, which comprises a real-time interactive digital-character model and a real-time video-editing model.

Career

  1. NowShengShu TechnologyCo-founder and CTO

Education

  1. 2023Tsinghua UniversityPhD
  2. 2019Tsinghua UniversityB.S. in computer science and technology

From the biography.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Fan Bao. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Tsinghua University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  3. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Tsinghua University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  4. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes Tsinghua University. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.

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 Fan Bao yet. Send us a free-licensed photo.

  1. Fan Bao baofff.github.io. Checked 22 October 2026.
  2. Chongxuan Li's Homepage zhenxuan00.github.io. Checked 22 October 2026.
  3. Announcing the ICLR 2022 Outstanding Paper Award Recipients – ICLR Blog blog.iclr.cc. Checked 22 October 2026.
  4. DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps proceedings.neurips.cc. Checked 22 October 2026.
  5. All Are Worth Words: A ViT Backbone for Diffusion Models openaccess.thecvf.com. Checked 22 October 2026.
  6. One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale proceedings.mlr.press. Checked 22 October 2026.
  7. Fan Bao | Innovators Under 35 innovatorsunder35.com. Checked 22 October 2026.
  8. Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models arxiv.org. Checked 22 October 2026.
  9. Diffusion Bridge Implicit Models proceedings.iclr.cc. Checked 22 October 2026.
  10. 演讲嘉宾 | 香港金融科技周 x StartmeupHK 2026 fintechweek.hk. Checked 22 October 2026.
  11. Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation arxiv.org. Checked 22 October 2026.