PeopleofSuperintelligence

Researcher

Enze Xie

Also known as 谢恩泽

Enze Xie is a computer-vision researcher whose work spans image segmentation and efficient generative models. He joined HKU MMLab as a PhD student in October 2019, earned a PhD in computer science at the University of Hong Kong in August 2022, and joined Huawei Noah's Ark Lab as a generative AI research lead. He coauthored PolarMask and SegFormer, SANA 1.5 for text-to-image generation, and LongLive-2.0 for long-video generation. As of October 2026, he is a Senior Research Scientist at NVIDIA Research and a visiting researcher at MIT HAN Lab, focused on efficient video-generation pre-training, post-training and acceleration.

Works
127
Citations
21,371
h-index
38
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2019–2022

    A PhD at HKU

    In October 2019, he joins HKU MMLab as a PhD student. He earns a PhD in computer science at the University of Hong Kong in August 2022, advised by Ping Luo and co-advised by Wenping Wang.

  2. 2020

    PolarMask at CVPR

    In 2020, he coauthors PolarMask, a single-shot instance-segmentation method that predicts object contours through center classification and distance regression in polar coordinates.

  3. 2021

    SegFormer at NeurIPS

    At NeurIPS in 2021, he coauthors SegFormer, a semantic-segmentation framework with a hierarchical Transformer encoder and a lightweight MLP decoder.

  4. August 2022

    Research lead at Huawei

    In August 2022, he joins Huawei Noah's Ark Lab as a researcher and generative AI research lead.

  5. April 2024

    Back to NVIDIA Research

    In April 2024, he returns to NVIDIA Research and joins its Efficient AI team.

  6. 2025

    SANA 1.5 at ICML

    At ICML in 2025, he coauthors SANA 1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation.

  7. 2026

    LongLive-2.0 for video

    In 2026, he coauthors LongLive-2.0, an NVFP4-based parallel infrastructure for training and inference in long-video generation.

  8. As of October 2026

    Senior Research Scientist at NVIDIA

    He is a Senior Research Scientist at NVIDIA Research and a visiting researcher at MIT HAN Lab. His current research focuses on efficient video-generation pre-training, post-training and acceleration.

Career

  1. Since 2024NVIDIASenior Research Scientist
  2. NowMassachusetts Institute of TechnologyVisiting researcher
  3. 2022–2024HuaweiGenerative AI Research Lead
  4. 2022–2024Chinese Academy of Sciences

Education

  1. 2022University of Hong KongPhD

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

  1. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Enze Xie. 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. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Massachusetts Institute of Technology. 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 Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Massachusetts Institute of Technology. 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. Google had the most people shaping AI every year from 2014 to 2025Includes Massachusetts Institute of Technology. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.

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 Enze Xie yet. Send us a free-licensed photo.

  1. Enze Xie (谢恩泽) xieenze.github.io. Checked 22 October 2026.
  2. Enze Xie | Efficient AI research.nvidia.com. Checked 22 October 2026.
  3. PolarMask: Single Shot Instance Segmentation With Polar Representation openaccess.thecvf.com. Checked 22 October 2026.
  4. SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers proceedings.neurips.cc. Checked 22 October 2026.
  5. SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer proceedings.mlr.press. Checked 22 October 2026.
  6. LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation arxiv.org. Checked 22 October 2026.
  7. Enze Xie | Research research.nvidia.com. Checked 22 October 2026.