I am a Ph.D. Candidate (2022.08-) in Computing Information & Science here at Rochester Institute of Technology (RIT) supervised by Prof. Weijie Zhao. My research interests span Security, Scalable Machine Learning, and Trustworthy Machine Learning.

Prior to RIT, I worked as a research assistant at the Institute of Computer Vision (ICV), Shenzhen University, China, and was supervised by Prof. Linlin Shen (Honorary Professor at the University of Nottingham, UK). Besides, I used to work as a software engineer (intern) at AI Lab of ByteDance inc. (TikTok’s Parent Company).

I got the bachelor’s degree in Computer Science and Technology in July 2021. I was the leader of a project funded by the National Ministry of Education of China for undergraduates in 2019. During my period of undergraduate, I received an ACM-ICPC Asia Bronze Medal in the ACM-ICPC International Collegiate Programming Contest, and a Silver Medal in the ACM-ICPC Shaanxi Province Contest of China.

My curriculum vitae can be found at here.

🔥 I am looking for research internship opportunities in Large Language Models (LLMs) and Machine Learning for the summer of 2024.


Feb. 12, 2024: Invited as a reviewer for KDD 2024.
Oct. 02, 2023: Invited as a reviewer for NeurIPS 2023 Workshop.
Aug. 05, 2023: Received the KDD’23 Student Travel Award. Thanks to KDD!
May. 16, 2023: Our paper (Machine Unlearning in Gradient Boosting Decision Trees) is accepted by KDD 2023! [Promotion Video, Poster]
Sep. 12, 2022: Our paper (Activation Template Matching Loss for Explainable Face Recognition) is accepted by the 2023 IEEE Conference on Automatic Face and Gesture Recognition (FG 2023)!

Tech Talks

  • “Machine Unlearning in Gradient Boosting Decision Trees” at Long Beach, CA, Aug. 9, 2023. [Slides, Video]
  • “Activation Template Matching Loss for Explainable Face Recognition” at Rochester Institute of Technology, Nov. 17, 2022. [Slides, Video]
  • “Toward Explainable Face Recognition” at Shenzhen University, Oct. 28, 2021. [Slides]
  • “Trust in Black-Box Models: Interpretability & Explainability for Deep Learning” at Shenzhen University, Aug. 13, 2021. [Slides]

Selected Publications

Research Experience


Machine Unlearning in Gradient Boosting Decision Trees (GBDT)

  • Propose an unlearning framework that efficiently and effectively unlearns a given collection of data without retraining the model from scratch.
  • Introduce a collection of techniques, including random split point selection and random partitioning layers training, to the training process of the original tree models to ensure that the trained model requires few subtree retrainings during the unlearning.
  • To the best of our knowledge, this is the first work that considers machine unlearning on GBDT.

[Paper, Code, Slides, Video, Poster]


Activation Template Matching Loss for Explainable Face Recognition

  • Propose a novel method named Explainable Channel Loss (ECLoss) to construct an explainable face recognition network, which can directly explain that what face recognition networks have learned.
  • To the best of our knowledge, this is the first method to construct a feature level explainable face recognition network that does not require any additional dataset or manual annotation.

[Paper, Slides, Video]


Parameter-free Attention in fMRI Decoding

  • Led a team working on a research project that was selected as a National Training Program of Innovation and Entrepreneurship for Undergraduates and funded by the Chinese National Ministry of Education.
  • Proposed a parameter-free attention module named Parameter-free Attention Module (SAM) to reduce the average error rate by 1.2%-3.1% while without involving any parameter.

[Paper, Poster, Patent]


Gender-Related Feature Extraction from Fingerprints

  • Designed an architecture called Dense Dilated Convolution ResNet (DDCResNet) to improve the decoding performance of the feature extraction algorithms.
  • Achieved an average extraction accuracy of 95%, which significantly exceeds traditional feature extraction methods.
  • Improved the interpretability of the algorithms by using Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize the high-score regions of gender information in fingerprint images.


Internship Experience

Institute of Computer Vision, Shenzhen University, Shenzhen, China
July 2021 - July 2022
Research Assistant | Supervisor: Prof. Linlin Shen

  • Responsible for interpretability and explainability on deep learning, especially on Biometrics.
  • In charge of a project about explainability on Face Recognition, which aim at propose a novel method to directly explain that what face recognition networks have learned.

AI Lab, ByteDance Inc., Beijing, China
Oct. 2020 - July 2021
Software Engineer

  • Responsible for Audio Recognition and Understanding research and development, and technical supports for ByteDance’s applications, including TikTok.
  • Proposed Stream Audio Understanding Chain method which enabled real-time audio processing and achieved precise extraction of information from audios, including speakers’ genders, tones, emotions, etc.
  • Designed a pipeline processing flow that significantly increased the throughput of CPUs and reduced processing time by 65%, by optimizing the usage of CPUs/GPUs using multiprocessing and multithreading.

Fellowships & Awards


  • KDD23, Student Travel AwardsAug. 2023
  • Zhou Lian Academic Scholarship (Only 1 of ~20,000 Students)Oct. 2020
  • Academic Innovation and Technology Scholarship (Only 10 of ~20,000 Students) May 2020
  • IAPR/IEEE Winter School on Biometrics 2020, Student Travel GrantsJan. 2020
  • Academic Innovation and Technology Scholarship (Only 10 of ~20,000 Students) May 2019


  • ACM-ICPC National Programming Contest (Shaanxi), Bronze Medal June 2021
  • ACM-ICPC Programming Contest (Shaanxi Province), Silver MedalSept. 2020
  • ACM-ICPC National Programming Contest (Shaanxi), Bronze Medal June 2020
  • ACM-ICPC National Programming Contest (Yinchuan), Bronze Medal May 2019
  • ACM-ICPC Asia Regional Contest, Bronze Medal Nov. 2018
  • ACM-ICPC Chinese Collegiate Programming Contest, Bronze Medal Jan. 2018

Professional Services


  • KDD 2024
  • NeurIPS 2023 Workshop

Open Source Project Contribution


  • Programming Languages: C/C++, Python, Go, Java, Shell, HTML
  • Deep Learning Tools: Transformers, OpenAI, DeepSpeed, FSDP, PEFT
  • Machine Learning Tools: PyTorch, CUDA, TensorFlow, Keras
  • Mathematical Tools: MATLAB, Octive
  • Document Processing: LaTex
  • Operation System: Linux, Mac OS, Windows
  • Database: Hadoop, SQL, MySQL, Redis
  • Others: Slurm, Docker, Kubernetes, Kafka