I am currently pursuing a M.S. degree in computer science at Northeastern University, with a research forcus on Information Retrieval and Large Language Model (LLM).

My research interests include Information Retrieval, Multimodality, SFT, RAG and Multi agent. I am currently working on research releated to RAG-SFT Data Generation and Instruction Tuning for Large Language Model (LLM).

I graduated from Harbin Engineering University with a B.S. degree in Computer Science and Technology, supervised by Associate Professor Chao Li. Currently, I am doing a research internship at NEUIR in Northeastern University, supervised by Associate Professor Zhenghao Liu . In addition, I am also working at THUNLP in Tsinghua University, supervised by Yukun Yan .

We have established close academic cooperation and exchanges with research institutions such as THUNLP, Beijing Advanced Innovation Center for Language Resources, OpenBMB, Inspir.ai, Alibaba, etc. We welcome cooperation and exchanges!


Total page views: | Last edit: 2024-04-14


🔥 News

  • 2024.04:  🎉 We released a Github repo HEUOpenResource/heu-icicles , we welcome issues and PRs!
  • 2024.02:  🎉 Ph.D Ye’s paper is accepted by LREC-COLING 2024 (CCF-B)!
  • 2023.09:  🎉 Obtained the qualification for master’s degree recommendation exemption!
  • 2023.05:  🎉 We released a model, which can predict features of the Wordle game!

📝 Publications

* indicates equal contribution.

# indicates corresponding author.

LREC-COLING 2024
sym

MMAD: Multi-modal Movie Audio Description

Xiaojun Ye, Junhao Chen, Xiang Li, Haidong Xin, Chao Li, Sheng Zhou #, Jiajun Bu

Project |

  • This work has unlocked a whole new experience of watching movies for the visually impaired.
arXiv 2023
sym

Puzzle game: Prediction and Classification of Wordle Solution Words

Haidong Xin, Fang Wu, Zhitong zhou, Shujuan Wang #

arXiv

  • This work conducted a detailed numerical analysis of the Wordle game, revealing statistical patterns within it.

🏆 Awards

  • 2023.07 🥈National Second Prize of Chinese Collegiate Computing Competition (4C 2023).
  • 2023.05 🥈Honorable Mention of Mathematical Contest in Modeling (MCM 2023).
  • 2023.05 🥈Second Prize of College International College Students’ Innovation Competition (CICSIC 2023).
  • 2022.11 🥇First Prize of China Undergraduate Mathematical Contest in Modeling (CUMCM 2022).
  • 2022.10 🥈Second Prize of Mathematical Modeling of the Three Northeastern Provinces League (MMTNPL 2022).
  • 2022.05 🥇First Prize of Excellent Student Scholarship.
  • 2021.05 🥇First Prize of Excellent Student Scholarship.

🔨 Projects

Corpus Intelligent Retrieval System
sym

Corpus Intelligent Retrieval System

Haidong Xin, Fang Wu, Xiaojun Ye, Xianyu Zhang, Jingbo Sun

Project | | http://corpus.hrbeu.edu.cn

  • This project is a corpus intelligent retrieval system implemented in the previous backend approach. We have implemented data management and permission management for the corpus.
Bird Sound Classification
sym

Bird Sound Classification System

Xiang Li, Fang Wu, Haidong Xin

Project |

  • This project is the award-winning work of Chinese Collegiate Computing Competition (4C 2023). We have built a front-end and back-end system to display bird audio classification results and encyclopedia information.
Ray Tracing With OpenGL
sym

Ray Tracing With OpenGL

Haidong Xin, Xianyu Zhang, Guanlan Yue

Project |

  • This project is the award-winning work of Chinese Collegiate Computing Competition (4C 2023). We have implemented ray tracing using the OpenGL library and NVIDIA driver.

📖 Educations

💬 Invited Talks

💻 Internships

  • 2023.05 - 2023.06, China Unicom Research Centre, Harbin.
  • 2023.07 - 2023.08, Workforce Development Program of Oracle, Harbin.
  • 2022.09 - 2024.06, Modeling and Emulation in E-Government National Engineering Laboratory, Harbin.

🤝 Connections