Zirui "Colin" Wang

I am a Staff Research Associate at the University of California, San Diego. I obtained B.S. in Data Science at the Halicioglu Data Science Institute (HDSI) and B.A. in Cognitive Science at the CogSci Department at the University of California, San Diego (UCSD). I work on the practical aspect of domain generalization and transfer in machine learning. I am a recipient of the HDSI Undergraduate Scholarship.

During my undergraduate studies & research, I have acquired/am currently acquiring experience in Reinforcement Learning, Hierachical Visual Reasoning, as well as Question-Answering in Language Models. I am fortunate to be advised by Prof. Zhuowen Tu and Prof. Zhiting Hu at UCSD. I have been primarily mentored by Dr. Yifan Xu and Nicklas Hansen for research.

I have also been committed to education. I have served as a Teaching Asssiant for various CS/ML courses at UCSD, tutored 10+ class offerings across the Computer Science and Engineering department, Data Science department, and Cognitive Science department, helped 1,000+ individual students, and worked with 6 teaching faculties for building better course experiences for students. I was primarily mentored by Prof. Marina Langlois for teaching.

Email  /  Resume  /  CV  /  GitHub  /  Twitter  /  Google Scholar  /  LinkedIn

profile photo


My calendar. Note that all the schedulings are tentative and subjective to change


project image

On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning

Yifan Xu*, Nicklas Hansen*, Zirui Wang, Yung-Chieh Chan, Hao Su, Zhuowen Tu
International Conference on Learning Representations (ICLR), 2023
website / arxiv / code

We investigate whether internal models learned by modern model-based RL algorithms can be leveraged to solve new, distinctly different tasks faster.


Full lists and details about classes I have served as a teaching assistant in the past. Instructor names are listed based on the time I worked with them. Staff names are listed in alphebatical order based on their first names. Instructor names and staff names are separated by a semicolon. Instructor evaluation is attached if available.

teaching image

Deep Learning

Gary Cottrell; Eric Yu, Martha Gahl, Rohin Garg, Shubham Kulkarni, Weitang Liu, Zirui Wang
evaluation / website

This course covers the fundamentals of neural networks. We introduce linear regression, logistic regression, perceptrons, multilayer networks and back-propagation, convolutional neural networks, recurrent networks, and deep networks trained by reinforcement learning.

teaching image

Introduction to Machine Learning

Jingbo Shang; Dheeraj Mekala, Weijian Xu, Xinghan Wang, Yilun Hao, Zhaoyi Hou, Zhenyu Bi, Zirui Wang
evaluation / website

The topics include some topics in supervised learning, such as k-nearest neighbor classifiers, decision trees, boosting, and perceptrons; and topics in unsupervised learning, such as k-means and hierarchical clustering. In addition to the actual algorithms, the course focuses on the principles behind the algorithms.

teaching image

Practical Data Science in R

Shannon Ellis; Sean Trott, Shubham Kulkarni, Zirui Wang
evaluation / website

Learn coding for data analysis using the R programming language. Course focus will be on practical and applied skills in asking data-informed questions, data wrangling, data visualization, building statistical learning models, and communication.

teaching image

The Practice and Application of Data Science

Justin Eldridge; Amy Nguyen, Jiaqi Feng, Murali Dandu, Nicole Brye, Ruojia Tao, Shubham Kaushal, Vineet Tallavajhala, Winston Yu, Zirui Wang

Students master the data science life-cycle and learn many of the fundamental principles and techniques of data science spanning algorithms, statistics, machine learning, visualization, and data systems.

teaching image

Data Structures and Algorithms for Data Science (x4)

Marina Langlois, Aaron Fraenkel, Soohyun Liao; Amy Nguyen, Brian Wang, Huaning Liu, Jeffrey Feng, Kevin Chin, Kunyang Sun, Madeline Tjoa, Sally Poon, Sharmi Mathur, Shasank Bonthala, Shubham Kaushal, Travis Tran, Trinity Pham, Viswesh Uppalapati, Yu-Chieh Chen, Yuanjia Yang, Yung-Chieh Chan, Yuri Bukhradze, Yuru Zhou, Yuxiao Ran, Yuxuan Fan, Zirui Wang
UCSD DSC 30 WI21/SP21/S221/FA21
evaluation / website

Programming techniques including encapsulation, abstract data types, interfaces, algorithms and complexity, and data structures such as stacks, queues, priority queues, heaps, linked lists, binary trees, binary search trees, and hash tables with Java.

teaching image

Programming and Basic Data Structures for Data Science (x2)

Marina Langlois; Aaron Chan, Amy Nguyen, Darren Liu, Haihao Sun, Huaning Liu, Huy Trinh, Jacqueline Lee, James Yu, Jeffrey Chu, Jianming Geng, Madeline Tjoa, Ruixuan Zhang, Sharmi Mathur, Shubham Kaushal, Siddharth Saha, Xiangyi Kong, Yijun Liu, Yu-Chieh Chen, Yung-Chieh Chan, Yuri Bukhradze, Yuru Zhou, Yuxiao Ran, Yuxuan Fan, Zirui Wang

Programming techniques including recursion, higher-order functions, function composition, object-oriented programming, interpreters, classes, and simple data structures such as arrays, lists, and linked lists.

teaching image

Principles of Data Science

Justin Eldridge; Anna Liu, Anqi Wang, Dylan Lee, Jeffrey Chu, Jessica Guzman, Meiwen Liu, Ruojia Tao, Shubham Kaushal, Teresa Lee, Xiaowang Huang, Xuzhe Zhi, Yuanjia Yang, Yi Li, Zirui Wang
UCSD DSC 10 S121

This introductory course develops computational thinking and tools necessary to answer questions that arise from large-scale datasets, emphasizing an end-to-end approach to data science, introducing programming techniques in Jupyter Notebook that cover data processing, modeling, and analysis.

Other Projects

These include courseworks, projects and other research-related work not for publishing. contents to be updated (10/11/2022). To remind myself what to put: DSC180 Capstone, DSC190 DataMining, COGS 108, MATH 189, DSC 102, DSC 106, COGS 189, DataHacks Adv, DataHacks Bus, Tencent, SS (CMU)

project image

On the Domain Robustness with Prompt & Prefix Tuning

Zirui Wang*, Lechuan Wang*, Yutong Luo
Data Science Undergraduate Capstone, 2022
paper / slides / code /

We analyze the robustness of Language Models using prompt tuning and prefix tuning toward a domain shift (i.e. learning a task from data in a specific domain and evaluating that model on the same task, but data is out-of-domain).

project image

EEG Transformer

Zirui Wang*, Xing Hong, Luning Yang, Annie Fan, Yunyi Huang, Zixin Ma
COGS 189: Brain Computer Interfaces, UCSD, 2022
slides / code /

We implement a naive EEG transformer that explores the possibility of using a ViT based transformer for inferring 3-class motor imagery based on multichannel time-series EEG data recorded at 1000 Hz for 8 seconds (in which 4 seconds are used). We propose future directions.

Design and source code from Jon Barron's website. Forked from the Jekyll varient by Leonid Keselman.