Ziyin Zhang

Graduate Student, SJTU

About Me

Hi guys, I'm a graduate student in Computer Science and Technology with a passion for machine learning, linear algebra, and linguistics. I also love nature, sports, movies, American TV shows and Chinese-style music!

Area of Interests

  • 🤖 Machine Learning: Deep Learning, Natural Language Processing, Computer Vision, Reinforcement Learning
  • 💻 Software Engineering: Web Development, Software Design
  • 💬 Linguistics: General Linguistics, Computational Linguistics, Translation, Interpretation
  • ⚽ Sports: Running, Soccer, Basketball, Badminton, Table Tennis
  • 🎥 Movies: Action, Adventure, Fantasy, Creature Feature, learn more on IMDb
  • 🎧 Music: Lin Yin, Shifu Huang, learn more on NetEase
  • 📚 Literature: Tolkien, George Martin, and other dark fantasies
  • 👚 Adidas: Not Sponsored!

Education

  • Shanghai Jiao Tong University

    2023-09 - 2026-03

    Working on Master of Science in Computer Science and Technology.

    7 courses and 17 credits as of June 2023

    Details
    • MATH
      • Matrix Theory: A-
    • AI
      • Statistical Learning and Inference: A+
      • Natural Language Understanding: A+
      • Machine Learning: A+
      • Neural Network Theory and Applications: A+


  • Shanghai Jiao Tong University

    2019-09 - 2023-06

    Majored in Naval Architecture and Ocean Engineering as a freshman, ranked 1/210, transferred to Computer Science and Technology as a sophomore, also minored in Translation and Interpretation.

    A total of 82 courses and 204 credits

    Details
    • MATH
      • Calculus: A
      • Probability Theory and Statistics: 92/100
      • Linear Algebra: 94/100
      • Discrete Mathematics: 99/100
      • Algorithm and Complexity: 94/100
    • CS
      • C++ programming: 98/100
      • Data Structure: 94/100
      • Operating System: 95/100
      • Computer System Architecture: 95/100
      • Principles of Compiler: 97/100
      • Computer Graphics: 94/100
      • Computer Networking: 98/100
    • AI
      • Principles of Data Science: 100/100
      • Artificial Intelligence: 98/100
      • Machine Learning: 97/100
      • Reinforcement Learning: 92/100
      • Natural Language Processing: 98.5/100
      • Data Mining: 97/100
    • LANG
      • English Reading and Writing: 96/100
      • Basic Latin: 98/100
      • Interpretation: 98/100
    Certificates
    • CET-4: 650
    • CET-6: 631
    • TEM-4: 90
    • TEM-8: 80


Honors

Dongshi Scholarship (￥10000) Nov. 2022
SJTU Undergraduate Class B Scholarship (￥1000) Nov. 2022
Huawei Scholarship (￥5000) Nov. 2021
SJTU Undergraduate Class C Scholarship (￥500) Nov. 2021
SJTU Undergraduate Class B Scholarship (￥1000) Nov. 2020

Experiences

Intern at Ant Group

Hangzhou, ZheJiang, China

2023.07 -

- Training code LLM


Special Coach in State Grid Digitization and Data Application Contest 2022

Tai'an, Shandong, China

2022.11 - 2022.12

- Advise State Grid tech personnel on automatic document processing, lead Shangdong team in the final on behalf of Alibaba Cloud Computing Co. Ltd.
- Won the national championship.


Assistant in SJTU Student Innovative Practice Project

SJTU, Shanghai, China

2022.10 - 2023.09

- Develop project website, guide students in natural language inference.


Teaching Assistant of EN397 Linguistic Intelligence

School of Foreign Languages, SJTU

2022.10 - 2023.1

- Guide senior linguistic students in NLP, assist the weekly teaching, design the coursework.


See all 5 experiences

Projects

Chinese Spoken Language Understanding 2023.01

Deep Learning Natural Language Processing Spoken Language Understanding

Chinese SLU with @Reginald. We formulated SLU as a sequence tagging task, and applied both discriminative token labeling models and seq2seq models to it. We also introduced a dual-branch decoder architecture to utilize manually corrected ASR transcriptions for denoising.

Paper Code
RoBERTa Is All You Need 2022.12

Deep Learning Natural Language Processing Sentiment Analysis

Twitter Sentiment Analysis with @Reginald. We verified that RoBERTa's embedding is better for SVM than Word2vec, and that RoBERTa itself is better than LSTM 🤪. We also investigated the strengths and weaknesses of fine-tuning and prompot-tuning with limited training data.

Paper Code
Tensor Core 2022.11

Parallel Computation CUDA Computer Vision

In this project I assembled a ResNet from scratch using CUDA. Particularly, I used Tensor Cores (proposed in Volta architecture) to implement convolution (by im2col) and linear layers. Forward pass only, no gradients!

Code
Free-hand Sketch Recognition 2022.06

Deep Learning Computer Vision Sketch Recognition

Image classification? ResNet Is All You Need!
Or... is it? For free-hand sketches, RNN can be useful as well!
Even better, we applied a dual-branch model to it, and fused the decision values of RNN and CNN.

Paper Code
It's Mahjong Time! 2022.06

Reinforcement Learning Variational Auto-Encoder Mahjong

Playing mahjong with reinforcement learning algorithms including DQN, double DQN, dueling DQN, and parametric noise under the Bayesian learning framework of Variational Oracle Guiding.

Paper

See all 9 projects