Jindong Gu

Senior Research Fellow, University of Oxford

Faculty Researcher, Google DeepMind

I am a Senior Research Fellow at University of Oxford, a member of Torr Vision Group.   I also partially work in Google DeepMind as a faculty researcher in Gemini Safety team. Prior to that, I received my Ph.D. Degree from University of Munich in 2022, advised by Prof. Volker Tresp.

My research goal is to build Responsible AI. Specifically, I am interested in the interpretability, robustness, privacy, and safety of

  • Visual Perception,
  • Foundation Model-based Understanding and Reasoning,
  • Robotic Policy and Planning,
  • and their Fusion towards General Intelligence Systems.

[Hiring!] If you like to work together with me as Ph.D/visiting student in the area of Responsible AI, please drop me an email (jindong DOT gu AT outlook DOT com), or contact me on LinkedIn or Twitter. I am unable to provide feedback to all queries due to a high volume of applications. You will be contacted if you are a good match.


News

  • 07 / 2024:   Six papers on AI Safety & Privacy are accepted to ECCV 2024.
  • 07 / 2024:   Papers on AI Safety & Interpretability are accepted to ICML, COLM, and BMVC 2024.
  • 06 / 2024:   I will serve as Area Chair in NeurIPS 2024 Datasets and Benchmarks Track.
  • 04 / 2024:   Our survey paper on Adversarial Transferability is accepted to TMLR.
  • 02 / 2024:   Three papers on AI safety are accepted to CVPR 2024.
  • 01 / 2024:   Three papers on AI safety (two Spotlight) are accepted to ICLR 2024.
  • 01 / 2024:   Two Journal papers on AI safety is accepted to TIFS.
  • 12 / 2023:   Three papers on AI safety and robustness are accepted to AAAI 2024.
Previous News
  • 11 / 2023:   I started a part-time Faculty Scientist position at Google DeepMind.
  • 10 / 2023:   I was promoted to Senior Research Fellow at University of Oxford.
  • 09 / 2023:   One paper is accepted to BMVC 2023 and One Benchmark paper to NeurIPS 2023.
  • 07 / 2023:   Three papers on VLM Understanding and Robustness are accepted to ICCV 2023.
  • 05 / 2023:   Selected as CVPR 2023 Outstanding Reviewer.
  • 05 / 2023:   One paper has been accepted to ACL Findings 2023.
  • 02 / 2023:   One paper has been accepted to CVPR 2023.
  • 11 / 2022:   I join Torr Vision Group as Postdoctoral Researcher at University of Oxford.
  • 08 / 2022:   I join Google Responsible ML Team as a Research Intern.
  • 07 / 2022:   Four papers on Robustness of Vision Systems are accepted to ECCV 2022.
  • 04 / 2021:   I join Microsoft Research Asia as a Research Intern.
  • 03 / 2021:   One paper has been accepted as oral to CVPR 2021.
  • 01 / 2021:   One paper has been accepted to ICLR 2021.

Experience

  • 11 / 2023 - present:   Faculty Scientist at Google, New York, USA
  • 10 / 2023 - present:   Senior Researcher at University of Oxford, Oxford, UK
  • 11 / 2022 - 09 / 2023:   Postdoctoral Researcher at University of Oxford, Oxford, UK
  • 08 / 2022 - 11 / 2022:   Research Intern at Google, New York, USA
  • 04 / 2021 - 02 / 2022:   Research Intern at Microsoft Research Asia, Beijing, China
  • 08 / 2020 - 03 / 2021:   Research Intern at Tencent AI Lab, Shenzhen, China
  • 09 / 2017 - 08 / 2020:   Doctoral Researcher at Siemens Technology, Munich, Germany

Selected Publications

Full Publication List

    • Responsible Generative AI: What to Generate and What Not [PDF]
      Jindong Gu
      Under Review, 2024
    • Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation [PDF][CODE]
      Hang Li, Chengzhi Shen, Philip Torr, Volker Tresp, Jindong Gu
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2024
    • An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models [PDF][CODE]
      Haochen Luo*, Jindong Gu*, Fengyuan Liu, Philip Torr
      International Conference on Learning Representations (ICLR) , 2024
    • Are Vision Transformers robust to Patch-wise Perturbation? [PDF][CODE]
      Jindong Gu, Volker Tresp, Yao Qin
      European Conference on Computer Vision (ECCV) , 2022
    • SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness [PDF]
      Jindong Gu, Hengshuang Zhao, Volker Tresp, Phillip Torr
      European Conference on Computer Vision (ECCV) , 2022
Great Honor to be in this Academic Family Tree [PDF] and [Link], which includes three Nobel prize winners!