嗨👋欢迎来到 mojimoon 的博客！直达我的 GitHub

关于本站

关于我

  • Academic background:
    • BSc in Computer Science, City University of Hong Kong (2022-2026)
      • GPA: 4.12/4.30 (Rank: 1/190), summa cum laude
      • HKSAR Government Scholarship for Outstanding Students (2024-2026)
    • MPhil in Machine Learning and Machine Intelligence (MLMI), University of Cambridge (anticipated 2026-2027)
  • Research interests: Machine Learning, Natural Language Processing, Software Testing, Concept Drift

一些成就

参与的一些开源项目：

FishHawk/auto-novel
  • 轻小说机翻机器人 - books.fishhawk.top
  • 前端：Vite + Vue + Naive UI + Pinia
  • 后端：Kotlin + Ktor + Exposed, Docker
  • 机翻：GPT or SakuraLLM
  • 主要参与了前端开发，如可展开折叠的章节目录、阅读器样式
ximu3/vnite
  • 一个适用于 Galgame/视觉小说的管理软件，包含刮削器、记录器、启动器和云同步功能
  • 前端：Electron + React
  • 后端：Kotlin + Ktor + Exposed, Docker
  • 主要参与了前端开发
mojimoon/wenku8
  • 轻小说文库 EPUB 搜索、下载工具
  • 从 Playwright 爬虫到前端展示完全托管给自动化的 GitHub Actions
  • 试试看吧：mojimoon.github.io/wenku8
mojimoon/bangumi-anime-ranking
  • Bangumi 动画排名分析
  • 基于 Bangumi15M 构建的偏序网络排名 (Partial Order Network Ranking) - 链接

参与的研究：

  1. Ensemble-based Testing for Deep Neural Networks through Scale Unification
    • Proposed a DNN testing and retraining framework based on ensemble metrics that unify different test selection metrics’ scales.
    • Accepted by Information and Software Technology (IST) in May 2026
    • Guided by Professor Jacky Keung
  2. Empirical Insights of Test Selection Metrics under Multiple Testing Objectives and Distribution Shifts
    • Conducted an empirical study on the effectiveness of various test selection metrics for deep learning systems under multiple testing objectives and out-of-distribution scenarios.
    • Accepted by ACM International Conference on the Foundations of Software Engineering (FSE) 2026, Link
    • Guided by Professor Jacky Keung
  3. Modeling Salary and Job Attractiveness from LinkedIn Descriptions with NLP
    • Implemented a framework combining NLP and machine learning to predict salaries and proposed a Job Attractiveness Index (JAI) based on job description analysis.
    • First author and presenter, accepted by ICCTech 2026, Link
    • Guided by Professor Patrick Houlihan at Columbia University
  4. DSFANet: Dual-Stream Feature Aggregation Network with Adaptive Retraining for Robust Network Intrusion Detection
    • Proposed a novel dual-stream feature aggregation network (DSFANet) integrating CNN, LSTM, and attention mechanisms for robust network intrusion detection, along with an adaptive retraining strategy to enhance model performance against adversarial attacks and concept drift.
    • First author, under review by International Conference on Neural Information Processing (ICONIP) 2026
    • Guided by Professor Ka-Chun Wong

快来参与讨论吧~