Weixin Bu

Weixin Bu

REVERSIBLE INC

Hello, this is Weixin Bu (Also, Bryson), an ordinary but curious person.

I persistently explore the things that spark my interest, while striving to learn from those who are both pure-hearted and outstanding. I believe that life is a vast wilderness, and the key is to live it in a way you truly love.

  • I am now working at REVERSIBLE INC as a [Search and Recommendation Engineer], maintaining the pipeline construction, performance optimization and multimodal implementation of the search and recommendation system. Additionally, I’m also exploring innovative applications of LLMs for automated code bug fix, while also researching on advanced image inpainting / outpainting technologies.

  • I graduated from School of Computer and Software, Nanjing University of Information Science and Technology (南京信息工程大学计算机与软件学院) with a bachelor’s degree; and from School of Artificial Intelligence, Jilin University (吉林大学人工智能学院) with a master’s degree.

  • I am passionate about researching on Artificial Intelligence (Graph Neural Networks[Homogeneous/Heterogeneous, Static/Dynamic Graphs], Self/Semi-supervised Learning, Multimodal Learning, and Large Foundation Models, etc) and Software Development (AI for Software Development, etc).

Please feel free to contact me via Email: brysonwx@163.com / bwxhhjy@gmail.com.

🔥 News

📝 Publications

Graph Neural Networks

Pattern Recognition
sym

Improving Augmentation Consistency for Graph Contrastive Learning
Weixin Bu*, Xiaofeng Cao*, Yizhen Zheng, Shirui Pan
[Paper] | [Code]

  • A novel augmentation consistency perspective in GCL
  • Integrate semantic and structural properties to better capture node consistency
  • An effective consistency improvement loss to maintain augmentation consistency among positive node pairs
ICML 2025 Spotlight
sym

Nonparametric Teaching for Graph Property Learners
Chen Zhang*, Weixin Bu*, Zeyi Ren, Zhengwu Liu, Yik-Chung Wu, Ngai Wong
[Project] | [Code]

  • A novel paradigm that interprets graph property learning within the theoretical context of nonparametric teaching (NT)
  • Reveal the consistency between the evolution of GCN driven by parameter updates and that under functional gradient descent in NT
  • Demonstrate the effectiveness of GraNT through extensive experiments (graph/node-level regression / classification) in graph property learning

Self / Semi-supervised Learning

Multimodal Learning

Large Foundation Models

AI for Software Development

Others

📖 Educations

  • 2021.09 - 2024.06, Computer Science, Msc, Jilin University, Changchun.
  • 2014.09 - 2018.06, Network Engineering, Bsc, Nanjing University of Information Science and Technology, Nanjing.

💻 Work and Internships

  • 2024.11 - now, Search and Recommendation Engineer in REVERSIBLE INC, Remote.
  • 2024.06 - 2024.09, AI Researcher in CAICT, Nanjing.
  • 2022.07 - 2022.10, Algorithm Software Intern in Shanghai AI Lab, Remote.
  • 2021.01 - 2021.06, Software Engineer(Part-time) in Beyond APP, Shanghai.
  • 2018.07 - 2020.05, Software Engineer(Full-time) in Beyond APP, Shanghai.