SUN Maojun (Stephen)

Took a detour way before.

EN/中文

Introduction

Research Interests

  • Large language model: Supervised Fine-tuning(SFT) and In-context Learning(ICL).
  • AI Agent: LLM Agent, Retrieval Augmentation Generation(RAG).
  • AI4Science: Health Informatics, Medical Image, Medical language model.

News📢

  • Registered as a Ph.D. student at Hong Kong Polytechnic University. August 30, 2024
  • Graduated and got the Distinction Honor 🥇 from Msc in Data Science & Analytics, PolyU. July 15, 2024
  • I am happy to announce that I will pursue a PhD degree at Hong Kong Polytechnic University in September 2024. My research interests include Large Language Model, Multi-agent Collaboration, Diffusion Model, etc. Welcome like-minded friends for discussions 😃. May 16, 2024
  • My fans exceed 1000 on CSDN 🔥. December, 2023

Papers & Manuscripts📰

  • LAMBDA: A Large Model Based Data Agent
    Maojun Sun, Ruijian Han, Binyan Jiang, Houduo Qi, Defeng Sun, Yancheng Yuan*, and Jian Huang*.
    arXiv preprint arXiv:2407.17535, 2024
    Paper Page Code PapersWithCode
  • LlamaCare: A Large Medical Language Model for Enhancing Healthcare Knowledge Sharing
    Maojun Sun.
    Technical Report. arXiv preprint arXiv:2406.02350, 2024.
    Paper Code HuggingFace PapersWithCode
  • Data Enhancement for Melanoma Classification
    Maojun Sun, Anxing Jiang, and Zixiong Li.
    2021 2nd International Conference on Artificial Intelligence and Computer Engineering.
    Paper Code

Research & Industry Experiences

  • Hong Kong Polytechnic University Research Assistant & Pt Project Assistant Feb 2024 - Present
    LAMBDA: Large Model Based Data Agent : [LAMBDA]
    Research and design LLM Agents for data science and analytics.
    Systems Development of Research Centre: [CMFAI] [RCNA] [RCQF] [CIOR]
    Responsible for website design and front-end development.
  • AI Lab, Hong Kong Hospital Authority Student Researcher July 2023 - December 2023
    Large Language Model in diagnostic systems :
    Responsible for research and development of the latest LLM, including fine-tuning, evaluation and prompt engineering.
  • Bacara Energy Technology Co., Ltd. Image Algorithm Intern June 2022 - August 2022
    Intelligent inspection solutions for wind power drones : [Page]
    Responsible for target detection and image segmentation, including algorithm design and implementation, fine-tuning and model deployment.
  • DXC Technology Artificial Intelligence Engineer Nov 2021 - June 2022
    Intelligent web robot “Xiao D” in low code platform :
    Responsible for back-end development and optimization of speech recognition solution.
    Recruitment module of the internship management system :
    Responsible for algorithm design and implementation of resume content classification and key information extraction.
  • Chinasoft International Co., Ltd. Software Development Intern June 2020 - August 2020
    Choco BOX applet (Micro-service e-commerce system) :
    Responsible for back-end development. Participating in performance tuning, service splitting and high concurrency design.

Awards🏅

  • National Scholarship of China, (Highest scholarship honor in China | 0.2%) 12/2020
  • The Outstanding Graduation of Zhejiang Province, (4%) 06/2022
  • Government Scholarship of Zhejiang Province (5%) 12/2021
  • Elite Scholarship × 2 (Highest honor in the university, 1%) 07/2021 & 07/2020
  • First Class Scholarship for Academic Excellence × 5, (3%) 2018 & 2019 & 2020 & 2021
  • Winning Prize of DJI RoboMaster Intelligent perception technology competition (Ranking 28th Nationally) 12/2022
  • Second Prize of National Artificial Intelligence & Innovation Competition 05/2021
  • Merit Student Award × 7 2018 & 2019 & 2020 & 2021
  • Outstanding Chief Award of Computer Hospital Association 06/2020

Professional Skills

  • Familiar with machine learning, and deep learning theory; familiar with AI tasks such as data mining, image classification, target detection, image segmentation, text categorization, LLM, etc.; Proficient in Pytorch.
  • Familiar with common data structures and algorithms (table, stack, queue, search, sort, etc.), computer network protocols (TCP, UDP, HTTP, WebSocket, etc.) and operating systems (scheduling, management, etc.).
  • Familiar with programming languages like Python, and Java; Knowledge of C, JavaScript, PHP and R; Familiar with markup languages HTML and CSS; Familiar with Linux common shell commands.
  • Familiar with development frameworks like SSM, SpringBoot, SpringCloud, Flask, and VUE; Familiar with development tools and cloud ecosystems Git, Swagger, Postman, Docker, AWS, Aliyun, etc.
  • Familiar with relational database such as MySQL (indexing, transaction, SQL tuning) and SQLServer; understand non-relational database like Redis and MongoDB.
  • Understanding of distributed systems, microservice architecture and message middleware such as RabbitMQ; understanding of high concurrency design, load balancing, multi-threading, and locking mechanism.
  • Understanding of components of big data framework such as Hadoop, Hive, Spark and Flink; understanding of ETL process, data warehousing, and common data analysis tools such as Tableau.

Others