Yao Qin

Assistant Professor @ UCSB

Senior Research Scientist @ Google

I am an Assistant Professor at the Department of Electrical and Computer Engineering at UC Santa Barbara, affiliated with the Department of Computer Science. Meanwhile, I am also a senior research scientist at Google Research. I obtained my PhD degree at UC San Diego in Computer Science, advised by Prof. Garrison W. Cottrell.

My research interests primarily focus on the robustness of machine learning, such as adversarial robustness, out-of-distribution generalization, and fairness. In my lab, we explore various research themes that are focused on developing robust machine learning models. Specifically, our research themes include:

  • Robustness in multi-modality models
  • Fairness in generative modeling
  • AI alignment in large language models
  • AI for healthcare, particularly for diabetes

    • I am actively looking for self-motivated students interested in machine learning / computer vision / NLP to join my research lab. Wecome to reach me at yaoqin@ucsb.edu with your resume. If you are a current student at UCSB, please email me with [UCSB Student] in the title!

    NEWS!
    • Apr. 2023: New work on robust prompts for vision-language models.
    • Feb. 2023: New work on rethinking effective robustness for natural distribution shifts.
    • Feb. 2023: Invited talk at Information Theory and Applications.
    • Dec. 2022: Invited to serve as Local Arrangement Chair for KDD-2023.
    • Dec. 2022: Invited to serve as Area Chair for ICCV-2023.
    • Nov. 2022: Invited to serve as Area Chair for ICLR-2023.
    • Nov. 2022: One paper accepted to SaTML-2023.
    • Oct. 2022: One paper accepted to Findings of EMNLP-2022.
    • Sep. 2022: One paper accepted to NeurIPS-2022.
    • Jul. 2022: One paper accepted to ECCV-2022.
    • Jan. 2020: I defend my thesis and join Google Brain, New York.
    • Apr. 2019: Start my internship at Google Brain, Toronto advised by Geoffrey Hinton, Colin Raffel and Nicholas Frosst.
    • Sep. 2018: I work as a research intern at Google Brain, Mountain View advised by Ian Goodfellow, Colin Raffel and Nicholas Carlini.

    Preprints


    Towards Robust Prompts on Vision-Language Models
    Jindong Gu, Ahmad Beirami, Xuezhi Wang, Alex Beutel, Philip Torr and Yao Qin
    [Paper]

    Effective Robustness against Natural Distribution Shifts for Models with Different Training Data
    Zhouxing Shi, Nicholas Carlini, Ananth Balashankar, Ludwig Schmidt, Cho-Jui Hsieh, Alex Beutel and Yao Qin
    [Paper]

    Deflecting Adversarial Attacks
    Yao Qin, Nicholas Frosst, Colin Raffel, Garrison Cottrell and Geoffrey Hinton
    [Paper]

    Evaluation Methodology for Attacks Against Confidence Thresholding Models
    Ian Goodfellow, Yao Qin, David Berthelot
    [Paper]

    Selected Publications

    (* indicates equal contributions.)

    Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
    Yao Qin, Chiyuan Zhang, Ting Chen, Balaji Lakshminarayanan, Alex Beutel and Xuezhi Wang
    Advances in Neural Information Processing Systems (NeurIPS), 2022
    [Paper]

    Are Vision Transformers Robust to Patch Perturbations?
    Jindong Gu, Volker Tresp, Yao Qin
    European Conference on Computer Vision (ECCV), 2022
    [Paper][Code]

    Improving Calibration through the Relationship with Adversarial Robustness
    Yao Qin, Xuezhi Wang, Alex Beutel, Ed H. Chi
    Advances in Neural Information Processing Systems (NeurIPS), 2021
    [Paper]

    Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
    Yao Qin*, Nicholas Frosst*, Sara Sabour, Colin Raffel, Garrison Cottrell and Geoffrey Hinton
    International Conference on Learning Representations (ICLR), 2020
    [Paper]

    Imperceptible, Robust and Targeted Adversarial Examples for Automatic Speech Recognition
    Yao Qin, Nicholas Carlini, Ian Goodfellow, Garrison Cottrell, Colin Raffel
    International Conference on Machine Learning (ICML), 2019.
    [Paper][Project Page][Code]

    Autofocus Layer for Semantic Segmentation
    Yao Qin, Konstantinos Kamnitsas, Siddharth Ancha, Jay Nanavati, Garrison Cottrell, Antonio Criminisi, Aditya Nori
    International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2018.
    Oral presentation (4% acceptance rate)
    [Paper][Code]

    Hierarchical Cellular Automata for Visual Saliency
    Yao Qin*, Mengyang Feng*, Huchuan Lu, Garrison Cottrell
    International Journal of Computer Vision (IJCV), 2017.
    [Paper][Code]

    A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
    Yao Qin, Dongjin Song, Haifeng Chen, Wei Cheng, Guofei Jiang, Garrison Cottrell
    International Joint Conference on Artificial Intelligence (IJCAI), 2017.
    [Paper][Code][Data]

    Saliency Detection via Cellular Automata
    Yao Qin, Huchuan Lu , Yiqun Xu, He Wang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
    [Paper][Code][中文版]

    Research Experience


    Apr. 2019 - Nov. 2019
    Research intern at Google Brain, Toronto, Canada
    Advised by Geoffrey Hinton, Colin Raffel and Nicholas Frosst.

    Sep. 2018 - Jan. 2019
    Research intern at Google Brain, Mountain View, USA
    Advised by Ian Goodfellow, Colin Raffel and Nicholas Carlini.

    Jul. 2018 - Sep. 2018
    Research intern at Google Brain, Mountain View, USA
    Advised by Suharsh Sivakumar and Raghu Krishnamoorthi.

    Mar. 2018 - Jun. 2018
    Research intern at Microsoft Research, Asia
    Advised by advised by Jingdong Wang.

    Jun. 2017 - Sep. 2017
    Research intern at Microsoft Research, Cambridge, UK
    Advised by Antonio Criminisi and Aditya Nori.

    Jun. 2016 - Sep. 2016
    Research intern at NEC Lab, New Jersey, USA
    Advised by Haifeng Chen and Dongjin Song.