Zhengqi Gao

PhD student Department of EECS Massachusetts Insitute of Technology E-mail: zhengqi@mit.edu

About me

Hi, I am a third year PhD student at MIT EECS, advised by Prof. Duane S. Boning. Previously, I obtained my M.S. and B.E. from School of Microelectronics, Fudan University, where I worked closely with Prof. Jun Tao and Prof. Xin Li (Duke Univ.) in the area of electronic design automation. My current research interests lie mainly in design automation for photonic integrated circuits (What is it?) and machine learning. In the summer before coming to MIT, I was very lucky to work with Prof. Ron Rohrer on the adjoint method and Prof. Hang Zhao on multimodal learning. I interned at Baidu, Shanghai Qizhi Insitutte, and Nvidia. My research was recognized by an editor's highlight in Photonics Research 2023, an ICLR’23 oral paper (top 5%), and the Biren scholarship (1 out of 3 nationwide) in 2020, among a few others.

Pin1: I dedicate one hour per week to mentor and offer suggestions to underrepresented students or anyone in need. Please fill in this form if you are interested.

Pin2: I am looking for interns and collaborators working on projects in the following areas, please shoot me an email if interested:

• Follow-ups of KirchhoffNet (especially hardware fabrication)

• Rare event probability estimation with novel deep generative models

• Algorithms for programmable photonic circuit

News

This is a queue (FIFO) of length 8.

• Jan, 2024: Won the Best Pitch Award at MIT MTL student conference MARC 2024.

• Jun, 2023: Ranked 2nd in CVPR’23 TTM Challenge.

• Apr, 2023: Presented on MIT MTL Mini Techical Symposium on Integrated Photonics.

• Apr, 2023: Selected as a DAC young fellow.

• Jan, 2023: Our joint work with Prof. Wim Bogaerts has been accepted by Photonics Research, and highlighted as an Editor's pick.

• Jan, 2023: One paper is accepte by ICLR 2023 (top 5%, oral); see our webpage.

• Sep, 2022: One paper is accepted by Neurips 2022. Big congrats to my friend Jiaqi.

• Jul, 2022: One paper is accepted by ECCV (see our code).

Selected Publications

Machine learning

• Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstruction
  Chih-Yu Lai, Fan-Keng Sun, Zhengqi Gao, Jeffrey Lang, and Duane S. Boning
  Conference on Neural Information Processing Systems (Neurips 2023)
  

• The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation
  Zihui Xue*, Zhengqi Gao*, Sucheng Ren*, and Hang Zhao
  International Conference on Learning Representations (ICLR 2023, top 5%, oral) (*Equal contribution)
  

• Learning from Multiple Annotator Noisy Labels via Sample-wise Label Fusion
  Zhengqi Gao, Fan-Keng Sun, Mingran Yang, Sucheng Ren, Zikai Xiong, Marc Engeler, Antonio Burazer, Linda Wildling, Luca Daniel, and Duane S. Boning
  European Conference on Computer Vision (ECCV 2022)
  

• NeurOLight: A Physics-Agnostic Neural Operator Enabling Parametric Photonic Device Simulation
  Jiaqi Gu, Zhengqi Gao, Chenghao Feng, Hanqing Zhu, Ray T. Chen, Duane S. Boning, and David Z. Pan
  Conference on Neural Information Processing Systems (Neurips 2022)
  

• Co-advise: Cross Inductive Bias Distillation
  Sucheng Ren, Zhengqi Gao, Tianyu Hua, Zihui Xue, Yonglong Tian, Shengfeng He, and Hang Zhao
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)
  

Design Automation

• Provable Routing Analysis of Programmable Photonics
  Zhengqi Gao, Xiangfeng Chen, Zhengxing Zhang, Chih-Yu Lai, Uttara Chakraborty, Wim Bogaerts, and Duane S. Boning
  Arxiv Preprint
  

• Automatic Synthesis of Light Processing Functions for Programmable Photonics: Theory and Realization
  Zhengqi Gao, Xiangfeng Chen, Zhengxing Zhang, Uttara Chakraborty, Wim Bogaerts, and Duane S. Boning
  Photonics Research (Editor's pick)
  

• Efficient Performance Trade-off Modeling for Analog Circuit based on Bayesian Neural Network
  Zhengqi Gao, Jun Tao, Fan Yang, Yangfeng Su, Dian Zhou, and Xuan Zeng
  IEEE/ACM International Conference on Computer Aided Design (ICCAD 2019)

• Efficient Parametric Yield Estimation over Multiple Process Corners via Bayesian Inference based on Bernoulli Distribution
  Zhengqi Gao, Jun Tao, Dian Zhou, and Xuan Zeng
  IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (IEEE TCAD)

• Circuit Theory of Time Domain Adjoint Sensitivity
  Jiahua Li*, Danyal Ahsanullah*, Zhengqi Gao*, and Ron Rohrer
  IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (IEEE TCAD) (*Equal contribution)
  

• Efficient Non-Monte-Carlo Yield Estimation
  Zhengqi Gao and Ron Rohrer
  IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (IEEE TCAD)

For a full publication list, please see my google scholar page.