PeopleofSuperintelligence

Researcher

Qifeng Chen

Also known as 陳启峰

Qifeng Chen is a computer vision researcher at the Hong Kong University of Science and Technology whose work spans image synthesis, low-light imaging and video generation. A gold medalist at IOI 2007 and second-place finisher at the 2011 ACM-ICPC World Finals, he earned a Stanford PhD in 2017 and published Cascaded Refinement Networks with Vladlen Koltun in 2017 and Learning to See in the Dark in 2018. In 2018, MIT Technology Review named him to its China-region 35 Innovators under 35 list, and in 2023 he co-authored VideoCrafter1, a pair of open video diffusion models. HKUST promoted him to Associate Professor with tenure in 2024, and MIT Technology Review China and DeepTech presented him with a 100 Young Pioneers in AI award in 2025. He is an Associate Professor in computer science and engineering and in electronic and computer engineering at HKUST, and an Associate Editor of TPAMI and ACM Computing Surveys.

Badges

Timeline

  1. 2007–2017

    Olympiads, HKUST and Stanford

    He earns a gold medal at IOI 2007 and second place worldwide at the ACM-ICPC World Finals in 2011. A bachelor's degree in computer science and maths from HKUST follows in 2012, and a PhD in computer science from Stanford University in 2017.

  2. 2017

    Cascaded Refinement Networks

    With Vladlen Koltun, he publishes Photographic Image Synthesis with Cascaded Refinement Networks at ICCV 2017. A single feedforward network turns a semantic label map into a photographic image, trained end to end with a direct regression objective, and the images reach 2-megapixel resolution.

  3. 2018

    Learning to See in the Dark

    With Chen Chen, Jia Xu and Vladlen Koltun, he presents Learning to See in the Dark at CVPR 2018. The paper introduces a dataset of raw short-exposure low-light images with long-exposure references, and a fully-convolutional network trained end to end on raw sensor data.

  4. 2018

    Innovators under 35 in China

    In 2018, MIT Technology Review inducts him, at the age of 29, into its China-region 35 Innovators under 35 list for work on image decomposition and synthesis and on optical flow. He is then an assistant professor in computer science and engineering and in electronic and computer engineering at HKUST, and a co-founder of the Silicon Valley startup Lino.

  5. October 2023

    VideoCrafter1 open video models

    In October 2023, he is one of twelve authors of VideoCrafter1, which introduces open text-to-video and image-to-video diffusion models. The authors describe the image-to-video model as the first open-source foundation model that turns a given image into a video clip while preserving its content.

  6. 2024

    Tenure at HKUST

    In June 2024, he announces that he will be promoted to Associate Professor with substantiation (tenure) at HKUST. He holds the rank in both the Department of Computer Science and Engineering and the Department of Electronic and Computer Engineering.

  7. 2025

    100 Young Pioneers in AI

    In 2025, MIT Technology Review China and DeepTech present him with a 100 Young Pioneers in AI award. The first selection names 65 young innovators across China.

  8. As of October 2026

    Associate Professor and editor

    He is an Associate Professor of CSE and ECE at HKUST, affiliated with the Robotics Institute and the Division of Arts and Machine Creativity, and Acting Director of the Center for Artificial Intelligence Research. He becomes an Associate Editor for TPAMI in November 2025 and for ACM Computing Surveys in April 2026.

Career

  1. Since 2018Hong Kong University of Science and TechnologyAssistant Professor, Associate Professor
  2. NowCarnegie Mellon University
  3. From 2018LinoCo-founder

Education

  1. 2017Stanford UniversityPhD
  2. 2012Hong Kong University of Science and TechnologyBachelor's degree

From the biography.

  1. 11% of AI doctorate holders from 2010 to 2016 founded or led a company or lab by 10 years after graduationIncludes Qifeng Chen. 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.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Carnegie Mellon 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 company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Carnegie Mellon University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. Google has the highest combined h-index among AI organizationsIncludes Carnegie Mellon University. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI 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 Qifeng Chen yet. Send us a free-licensed photo.

  1. Qifeng CHEN | HKUST CSE cse.hkust.edu.hk. Checked 22 October 2026.
  2. Photographic Image Synthesis with Cascaded Refinement Networks arxiv.org. Checked 22 October 2026.
  3. Learning to See in the Dark arxiv.org. Checked 22 October 2026.
  4. Prof. Qifeng CHEN named one of “35 Innovators under 35” in China in 2018 by MIT Technology Review ece.hkust.edu.hk. Checked 22 October 2026.
  5. VideoCrafter1: Open Diffusion Models for High-Quality Video Generation arxiv.org. Checked 22 October 2026.
  6. Qifeng Chen (陳启峰) cqf.io. Checked 22 October 2026.
  7. Qifeng CHEN 陳启峰 | HKUST School of Engineering seng.hkust.edu.hk. Checked 22 October 2026.
  8. Dr. Qifeng Chen Receives 100 Young Pioneers in AI Award | HKUST CSE cse.hkust.edu.hk. Checked 22 October 2026.