Bio

𝒯𝒾𝒶𝓃 𝒯𝒶𝓃 𝐵𝓊𝒹𝒹𝒽𝒶, 𝐻𝑜𝓃𝑔 𝒦𝑜𝓃𝑔

I am a Ph.D. student in Computer Engineering at Boston University. I am very fortunate to be advised by Prof. Vijaya Kolachalama and Prof. William Hsu. I have previously interned at Philips Research and Samsung Research. Prior to BU, I received my M.Phil. degree (2023) in Computer Science from City University of Hong Kong, supervised by Prof. Shiqi Wang, and B.Eng. degree (2020) in Intelligence Science and Technology from Northeast Electric Power University, supervised by Prof. Yimin Hou, Prof. Jinglei Lv, and Prof. Yang Li. In 2017, I attended a summer school at University of California, Irvine.

𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝘀: I put all my effort into Multimodal Foundation Models, Reasoning with Foundation Models, e.g., equip Language Models with strong mathematical reasoning capabilities, and AI for Medicine and Healthcare, e.g., Medical Imaging with AI and Digital Pathology.

Research Focus Illustration
Research Presentations and Resources
𝐖𝐡𝐚𝐭 𝐢𝐬 𝐭𝐡𝐞 𝐦𝐨𝐬𝐭 𝐬𝐮𝐫𝐩𝐫𝐢𝐬𝐢𝐧𝐠 𝐟𝐢𝐧𝐝𝐢𝐧𝐠 𝐢𝐧 𝐲𝐨𝐮𝐫 𝐫𝐞𝐬𝐞𝐚𝐫𝐜𝐡?

𝐏𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 - Artificial Intelligence (AI)

  • AI In the 2020s And Beyond
  • 𝐏𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 - Graph Neural Network (GNN)

  • Graph Convolutional Neural Networks
  • Attention-based BiLSTM-GCN
  • Dynamic Graph Convolutional Neural Networks
  • 𝐏𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 - Natural Language Processing (NLP)

  • Foundation Models for Sequential Decision Making
  • Factual Associations in LLMs
  • Graph Matching
  • Sub-word BPE Algorithm for NMT
  • Concept Matching for Medical Terms
  • 𝐏𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 - Computer Vision (CV)

  • Image Quality Assessment and Perceptual Optimization
  • Deep Learning Models Compression and Acceleration
  • 3D Human Pose Estimation and Human Body Reconstruction
  • YOLO Object Detection
  • 𝐏𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 - Tutorials and Useful Coding Scripts

  • Usage of Cloud Server and Setting-up
  • Python Environment Setting-up
  • TensorFlow for Deep Learning
  • Crypto Currency Return and Price Prediction with Machine Learning
  • Big Data Parallel Processing by PySpark and Horovod Distributed Deep Learning
  • Download Papers from Sci-Hub via Unix Shell
  • Retrieve and Download Google Scholar Citation Papers
  • Homepage Shows Real-time Google Scholar Citations through PHP
  • Dynamic (Ajax) Web Crawler in Python
  • Deploy Machine Learning and Deep Learning Models with Flask and Docker as Web Applications
  • Convert PowerPoint (PPT) to PDF with Animations
  • Download YouTube Videos with Unlimited Speed via youtube-dl
  • Compile Hadoop, Install Redis, Flink, Kafka, ZooKepper, and Spark on macOS
  • Hadoop HDFS Data
  • Hive Configuration on macOS
  • Spark Configuration on macOS
  • Hadoop Configuration on Linux
  • Hive Configuration on Linux
  • Storm Configuration on Linux
  • Compiling Kaldi ASR on macOS
  • Server SSH and SCP Scripts
  • Shell Tmux Usage
  • Go Programming Scripts
  • Julia Programming Scripts
  • Python Conda Scripts
  • Python PyPI Package Building Scripts
  • npm Scripts
  • R Packages
  • SQL Programming Scripts
  • CSV Shell Scripts
  • macOS Homebrew Scripts
  • Install LaTeX on Linux
  • LaTeX Package Installation on macOS and EPS to PDF
  • LaTeX Useful Newcommands
  • LaTeX IEEE Conference Useful Scripts
  • LaTeX IEEE Trans Useful Scripts
  • Matlab GPU Acceleration Tricks
  • Run Multiple Python Scripts via Shell sh
  • Build PyTorch (CPU) from Source on macOS
  • PyTorch Control the Usage of CPU Resources
  • Build TensorFlow (CPU) from Source on macOS
  • Build TensorFlow (CPU) from Source on Linux
  • Build TensorFlow (GPU) from Source on Linux
  • Docker Basic Commands
  • Vim Basic Commands
  • Git Basic Commands
  • M.Phil. Thesis (LaTeX), City University of Hong Kong
  • 𝐄𝐱𝐜𝐞𝐥𝐥𝐞𝐧𝐭 𝐏𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧

  • On the Inductive Bias of Language Modeling | Oral Presentation (Tatsunori B. Hashimoto)
  • 智能制造优化调度及展望
  • 𝐓𝐞𝐜𝐡𝐧𝐢𝐜𝐚𝐥 𝐁𝐨𝐨𝐤𝐬

  • Foundation Models for Natural Language Processing Pre-trained Language Models Integrating Media (Gerhard Paaß and Sven Giesselbach)
  • Pattern Recognition and Machine Learning (Christopher Bishop)
  • Reinforcement Learning: An Introduction (Richard S. Sutton and Andrew G. Barto)
  • Digital Image Processing (Rafael C. Gonzalez and Richard E. Woods)
  • Multiple View Geometry in Computer Vision (Richard Hartley and Andrew Zisserman)
  • Graph Representation Learning (William L. Hamilton)
  • Computer Systems: A Programmer's Perspective (Randal E. Bryant and David R. O'Hallaron)
  • Computer Organization and Design: The Hardware/Software Interface (David A. Patterson and John L. Hennessy)
  • 𝐀𝐜𝐚𝐝𝐞𝐦𝐢𝐜 𝐑𝐞𝐬𝐨𝐮𝐫𝐜𝐞𝐬

  • Writing and Technical Presentations by Prof. Ayse Coskun
  • The Most Common Habits from more than 200 English Papers written by Graduate Chinese Engineering Students by Felicia Brittman
  • How to Write Good Research Articles by Prof. Xiaohua Jia
  • 业余做研究的经验 by Dr. Yuandong Tian
  • What is Research and How to do it? by Prof. Yi Ma
  • How to Write a Good CVPR Submission? by Prof. Bill Freeman
  • Tips on Writing Papers with Mathematical Content by Prof. John N. Tsitsiklis
  • How to Be a Responsible Reviewer by Prof. Jiebo Luo
  • How to Use the IEEEtran LaTeX Class
  • IEEE Editing Mathematics Guide (Standard)
  • IEEE Math Typesetting Guide (LaTeX)
  • IEEE Formula Comma and Period
  • IEEE Reference Guide (2021)
  • IEEE Citation Examples
  • Science and Engineering Journal Abbreviations
  • Standard abbreviations used in the IEEE Reference list
  • IEEE Editorial Style Manual (2021)
  • LaTeX Mathematical Symbols
  • Writing Mathematical Formulas in Markdown
  • InCites Journal Citation Reports (2021)
  • 中国计算机学会推荐国际学术会议和期刊目录 (2019)
  • 中国科学院SCI分区表 (2019)
  • 中国科学院国际期刊预警名单
  • Python编码风格与规范 @ Tencent
  • C++编码风格与规范 @ Tencent
  • JavaScript编码风格与规范 @ Tencent
  • Go编码风格与规范 @ Tencent
  • CVPR Paper, Supplementary Materials, and Rebuttal LaTeX Templates
  • PowerPoint (PPT) and LaTeX Demos of Academic Posters
  • National Science Foundation (NSF) Proposal & Award Policies & Procedures Guide (PAPPG)
  • National Science Foundation (NSF) Biographical Sketch
  • NSF's Proposal Preparation & Submission Guidelines
  • ACL Fellow Nomination Form
  • CityU AP Promotion
  • RICE AP Offer
  • MIT EECS Courses
  • MIT EECS Organization and Labs (2019)
  • 𝐑𝐞𝐜𝐨𝐦𝐦𝐞𝐧𝐝𝐞𝐝 𝐑𝐞𝐚𝐝𝐢𝐧𝐠𝐬

  • 文章千古事, 得失寸心知 by Prof. Song-Chun Zhu
  • Statement of Purpose by Dr. Kai-Fu Lee
  • Dartmouth Summer Project on Artificial Intelligence (1956)
  • Turing Test (1950) by Alan Mathison Turing
  • The Bitter Lesson from 70 years of AI research by Richard Sutton
  • AI创业江湖里的师徒帮
  • 清华大学计算机系与人工智能40年
  • Academic Achievements of Prof. Richard Yi-Da Xu
  • Brief Bio of Prof. Richard Yi-Da Xu
  • Prompt Template Engineering Experiment by Prof. Edward Chang
  • 心灵之旅 by Prof. Edward Chang
  • 生命是什么? by Prof. Edward Chang
  • 读博那些事儿 by Prof. Yiqing Xu
  • The Ph.D. Grind by Prof. Philip J. Guo
  • You and Your Research by Prof. Richard Hamming
  • You’ve Got to Find What You Love by Steve Jobs
  • How to Be a Successful Ph.D. CS Student by Prof. Mark Dredze and Prof. Hanna M. Wallach
  • A Brief History of Computational Vision by Prof. Song-Chun Zhu
  • Artificial Intelligence by Prof. Song-Chun Zhu
  • Ph.D. in Computer Vision Summary by Prof. Mike Shou
  • 博士这五年 by Dr. Mu Li
  • 博士五年总结系列 by Dr. Yuandong Tian
  • What My PhD Was Like by Prof. Jean Yang
  • CVPR之感想 by Dr. Yuandong Tian
  • 上海交通大学学生生存手册
  • 李琳山教授个人数位典藏
  • Randy Pausch Last Lecture: Achieving Your Childhood Dreams

  • Email: brucejia@bu.edu
    Strava Scholar 🤗 HuggingFace GitHub

    News

    Publications

    1. No-reference Image Quality Assessment via Non-local Dependency Modeling

      Shuyue Jia, Dingquan Li, Shiqi Wang
      Poster Slides Codes 🤗 HuggingFace Paper

      IEEE 24th International Workshop on Multimedia Signal Processing (IEEE MMSP'22)
      See More
        A no-reference image quality assessment method based on non-local features learned by a graph neural network (GNN). The proposed quality assessment framework is rooted in the view that the human visual system perceives image quality with long-dependency constructed among different regions, inspiring us to explore the non-local interactions in quality prediction.
        NL-Net

    2. GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-resolved EEG Motor Imagery Signals
      Shuyue Jia, Yimin Hou, Xiangmin Lun, Yan Shi, Yang Li, Rui Zeng, Jinglei Lv
      IEEE Transactions on Neural Networks and Learning Systems (IEEE T-NNLS)
      Slides Codes Paper

      See More
        Traditional works classify EEG signals without considering the topological relationship among electrodes. Thus, a graph convolutional neural network is presented while cooperating with the functional topological relationship of electrodes.
        Project2

    3. Deep Feature Mining via Attention-based BiLSTM-GCN for Human Motor Imagery Recognition

      Yimin Hou, Shuyue Jia (Corresponding Author), Xiangmin Lun, Shu Zhang, Jinglei Lv
      Slides Codes Paper

      Frontiers in Bioengineering and Biotechnology
      See More
        This paper presents a novel deep learning approach designed toward both remarkably accurate and responsive motor imagery (MI) recognition based on scalp EEG. Bidirectional long short-term memory (BiLSTM) with the attention mechanism is employed, and the graph convolutional neural network (GCN) promotes the decoding performance by cooperating with the topological structure of features.
        Project3.1 Project3.2

    4. A Novel Approach of Decoding EEG Four-Class Motor Imagery Tasks via Scout ESI and CNN
      Codes Paper

      Yimin Hou, Lu Zhou, Shuyue Jia, Xiangmin Lun
      Journal of Neural Engineering
      See More
        We presented a novel approach that could potentially improve the current stroke rehabilitation strategies by implementing a deep learning approach for an Electroencephalogram (EEG) based on MI Brain-Computer Interface System.
        • Constructed 6 convolutional layers, 2 max-pooling layers, and 3 FC layers CNNs for four-class motor imagery classification through TensorFlow, with 50% dropout (spatial dropout after every Conv layer and regular dropout for FC layers) – 11.44% accuracy improvement, batch normalization (BN) – 10.15% improvement, and Short-cut Connection – 1.76% improvement to prevent overfitting, and achieved SOTA results: 94.50% accuracy on scout R5, 94.54% at subject level, and 96% for left fist prediction.
        • Took charge of DNNs design, including methods comparisons, such as MLPs, CNNs, RNNs, and LSTMs, classification results calculations, and programming. 10 and 14 subjects’ data were utilized (19,320 and 27,048 samples in the experiments)
        • Benchmark Dataset: EEG Motor Movement/Imagery Dataset.
        EEG-CNN-1 EEG-CNN-2

    Academic Services

    1. Reviewer of IEEE T-MM, IEEE T-CSVT, and IEEE Journal of Biomedical and Health Informatics
    2. Student Member of IEEE, ACM, ACL, and AAAI

    Selected Awards

    1. CityU Top 5 Runner, City University of Hong Kong

      Athlete
      marathon-2021
    2. Outstanding Athlete, Northeast Electric Power University

      Athlete
      Elite Athlete
    3. 3000-meter Steeplechase, The 45th Northeast Electric Power University Games

      The 7th Place in college
      Steeplechase
    4. 2015 National High School Math League, China

      Second Prize
      Math
    5. The 32nd Chinese Physics Olympiad (CPhO), China

      Third Prize
      Physics