Biography
–> I am currently looking for phd position. If you are interested in me, please feel free to contact me! 😊
I am an undergraduate student of computer science in Nanjing University. I am supervised by Prof. Linzhang Wang and Dr.Yu Wang at Software Engineering Group. My research interests lie in the intersection of Software Engineering and Machine Learning, especially in the area of the testing of program languages. I have also done research regarding Computer Graphics before.
You can also have a look at some of my working projects in my Github or check out my curriculum vitae.
Interests
- Software Engineering
- Machine Learning
- Programming Language
Education
-
BSc in Computer Science and Technology, Sept.2020 - present
Nanjing University, China
Research Experiences
Content-Adapted Image Super-resolution Based on Random Scale
- Trying to devise a novel comprehensive scheme to integrate scene adaptation, resolution adaptation and content adaptation to boost efficiency and robustness of image supersampling.
- Developing the study around the neural network and trying to realize the image super-resolution based on random scale with kernel prediction.
- Preparing manuscript for submission to SIGGRAPH (Expected submission date: December 2023).
- Sparked the keen interest to conduct a more in-depth study in the field of image rendering and image super-resolution.
LLM-Based Code Generation Method for Golang Compiler Testing
- Implemented a LLM-based high-quality code generation method to the Golang compiler, generating test-cases with 3.38% average coverage and only 2.79% of them had syntax errors.
- Utilized Python and Pytorch to finetune the large model CodeT5 to generate go code testcases both qualitatively and quantitatively.
- Published a paper as the independent first author at ESEC/FSE Conference 2023, LLM-Based Code Generation Method for Golang Compiler Testing.
- Kept on exploring software testing technique and improving the performance of program analysis by machine learning.
Automatic Detection of Intracranial Aneurysms Based on Deep Learning
- Utilized Python and Pytorch to perform a clinically applicable deep-learning model for detecting intracranial aneurysm in computed tomography angiography images.
- Set an online website for medical institutions to apply the model conveniently.
- Focused on back-end development and improved the manipulation of Java web.
- Designed a complete business plan for project implementation.
Development of A Physically Based Renderer using Monte Carlo Path Tracing
- Utilized C++ to realize the Monte Carlo Path Tracing algorithm, estabishing a ”easy to deploy and develop” rendering platform.
- Realized BVH, Octree accelerator, multiple importance sampling, Gaussian filtering and bilateral filtering, and integrated Intel Open Image Denoise.
Projects
*
A platform fro automatic detection of intracranial aneurysms.
A Code Generation Method Based on CodeT5 for Golang Compiler Testing
Building a graphic renderer based on the Monte Carlo path tracing framework.
Contact
- qiuhan.gu8@gmail.com
- (+86)-15062761000
- No.163 Xianlin Road, Qixia District, Nanjing, Jiangsu Province 210023