PeopleofSuperintelligence

Researcher

Lu Jiang

Also known as Jiang Lu

Lu Jiang is a researcher in video and image generation whose work runs from learning with noisy labels to large language models for video. He earned his doctorate at Carnegie Mellon University, advised by Alexander Hauptmann and Teruko Mitamura. At Google Research he coauthored MaskGIT in 2022 and MAGVIT in 2023, and VideoPoet, announced in December 2023, won a Best Paper Award at ICML 2024. In 2024 he also shared the IJCAI-JAIR prize for “Confident Learning” and joined ByteDance as a Research Director leading video foundation models. He is now a Principal Research Scientist at Apple, working on visual generation and multimodal foundation models.

Now at
Apple
Badges

Timeline

  1. 2016

    PhD at Carnegie Mellon

    He receives a Yahoo! Fellowship in 2016 and earns his Ph.D. at Carnegie Mellon University, advised by Alexander Hauptmann and Teruko Mitamura. He is also affiliated with Xi'an Jiaotong University, under Jun Liu.

  2. 2017–2018

    MentorNet for noisy labels

    In December 2017, he posts MentorNet with Zhengyuan Zhou, Thomas Leung, Li-Jia Li and Li Fei-Fei: a neural network that supervises the training of a base network by weighting the samples whose labels are probably correct. The paper is published at ICML 2018.

  3. October 2021

    Adjunct faculty at Carnegie Mellon

    He joins Carnegie Mellon University as adjunct faculty in October 2021, in the School of Computer Science.

  4. 2022–2023

    MaskGIT and MAGVIT

    In 2022, he coauthors MaskGIT, which generates images with a bidirectional transformer that predicts randomly masked tokens and speeds up decoding by up to 64x. In 2023, he coauthors MAGVIT with colleagues at Google Research and Carnegie Mellon, a single model for many video synthesis tasks that appears at CVPR 2023 as a highlight.

  5. December 2023

    VideoPoet at Google Research

    Google Research announces VideoPoet in December 2023, a large language model for video generation tasks such as text-to-video, image-to-video and video stylization. He is one of its contributors and the last author of the paper.

  6. 2024

    Two best paper awards

    VideoPoet receives a Best Paper Award at ICML 2024. In 2024, he also shares the IJCAI-JAIR prize with Curtis Northcutt and Isaac Chuang for “Confident Learning: Estimating Uncertainty in Dataset Labels”, a paper on data label noise.

  7. 2024

    Video models at ByteDance

    He is hired by ByteDance in 2024 and becomes a Research Director at ByteDance USA, leading efforts on video foundation models. The Seedance 1.0 video generation report, submitted in June 2025, lists him among its authors.

  8. As of October 2026

    Principal Research Scientist at Apple

    He is a Principal Research Scientist at Apple, working on visual generation and multimodal foundation models. He serves as area chair for CVPR 2025, ICML 2025, ICCV 2025 and NeurIPS 2025.

Career

  1. NowApplePrincipal Research Scientist
  2. From 2024ByteDanceResearch Director
  3. From 2021Carnegie Mellon UniversityAdjunct Faculty

Education

  1. 2016Carnegie Mellon UniversityPhD

From the biography.

  1. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Lu Jiang. 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. 11% of AI doctorate holders from 2010 to 2016 founded or led a company or lab by 10 years after graduationIncludes Lu Jiang. We estimate how often AI doctorate holders founded or led a company or lab by 10 years after graduation, how waiting times compare between founders and top jobs, and which universities trained the most.
  3. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Lu Jiang. 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.
  4. 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.

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 Lu Jiang yet. Send us a free-licensed photo.

  1. Lu Jiang - Biography lujiang.info. Checked 21 October 2026.
  2. MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels arxiv.org. Checked 21 October 2026.
  3. Lu Jiang - Home lujiang.info. Checked 21 October 2026.
  4. MaskGIT: Masked Generative Image Transformer arxiv.org. Checked 21 October 2026.
  5. MAGVIT: Masked Generative Video Transformer magvit.cs.cmu.edu. Checked 21 October 2026.
  6. VideoPoet: A large language model for zero-shot video generation research.google. Checked 21 October 2026.
  7. VideoPoet: A Large Language Model for Zero-Shot Video Generation arxiv.org. Checked 21 October 2026.
  8. Award-winning paper in ICML 2024 on “VideoPoet: A large language model for zero-shot video generation.” irfanessa.gatech.edu. Checked 21 October 2026.
  9. IJCAI-JAIR Awards | Journal of Artificial Intelligence Research jair.org. Checked 21 October 2026.
  10. ByteDance goes all in with AI for social media english.scenarieconomici.it. Checked 21 October 2026.
  11. Seedance 1.0: Exploring the Boundaries of Video Generation Models arxiv.org. Checked 21 October 2026.