Weihuang Wen (温伟煌)

A programmer for the fun of it.

github
linkedin
instagram

About Me

I am now a research assistant in The Chinese University of Hong Kong, Shenzhen (opens new window) with Prof.Yu (opens new window). Before this, I worked as an engineer in Shenzhen Health Development Research and Data Management Center (opens new window).

Interests

  • Machine Learning for Boolean Satisfiability Problem
  • Machine Learning Systems
  • Natural Language Processing

Education & Experiences

Selected Projects

→ Full list

1. A steganography scheme based on adversarial examples (master thesis)

In this work, we regard the adversarial nature of the adversarial examples itself as information, which can be decoded by the specific model only.

[demo (opens new window)]

2. Multi-task Learning for Aspect-based Sentiment Analysis (bachelor thesis)

This work proposes a deep multi-task learning framework for aspect term extraction (ATE). Furthermore, it presents a novel way to combines aspect term extraction and aspect sentiment classification into an individual task, which can avoid the error propagation from the pipeline approach.

[demo (opens new window)]

3. ServingAgent

ServingAgent is designed as a middleware for model serving between web server and model server to help the server improve the GPU utilization then speedup online inference.

[code (opens new window)]

4. ServingTemplate

ServingTemplate is a tool to auto gereate the model serving project template.

[code (opens new window)]

5. MagicComment

MagicComment is a Visual Studio Code extension, which will comment the uncomment part and uncomment the comment part when the selection content contains both of them.

[code (opens new window)]

Awards & Honors

Scholarship

  • University Scholarship, SUSTech 2018 – 2019
  • College Student Start-up Scholarship, SUSTech 2014 – 2017

Skills

  • Language: Python, Javascript, Go, Java, C/C++
  • Tool: Git, Docker, Kubernetes, etc.
Last Updated: 5/21/2022, 3:52:46 PM