Baiyuan Chen | 陳柏源
Graduate student at University of Cambridge
Currently pursuing an MPhil in Data Intensive Science.
Graduate student at University of Cambridge
Currently pursuing an MPhil in Data Intensive Science.
I was a first-year graduate student at the University of Tokyo, advised by Yutaka Matsuo, and now I am taking a one-year leave of absence to pursue my studies at Cambridge.
I obtained my bachelor's degree in Mathematical Sciences with a minor in Cognitive Science from UTokyo, graduating as the Department Valedictorian.
I was fortunate to be advised by Masaaki Imaizumi had the pleasure of collaborating with Shinji Ito.
Previously, I worked on deep learning theory, focusing on the topological and dynamical properties of machine learning models.
Currently, my research centers on generative models—particularly video generation.
I am especially interested in long-time video generation and reconstructing visual content from brain activity.
You can't connect the dots looking forward; you can only connect them looking backward. So you have to trust that the dots will somehow connect in your future.
— Steve Jobs
My undergraduate thesis is now available: Link
Received the Dean's Award and was named Valedictorian of the Department of Integrated Sciences.
Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
Baiyuan Chen, Shinji Ito, Masaaki Imaizumi
Is Smoothness the Key to Robustness? A Comparison of Attention and Convolution Models Using a Novel Metric
Baiyuan Chen
Exploiting Topological Priors for Boosting Point Cloud Generation
Baiyuan Chen
2nd International Conference on Artificial Intelligence, Database and Machine Learning (AIDML 2024)
Link
Dynamical systems analysis
Advisor: Prof. Tetsuhiro S. Hatakeyama
• A highly selective, research-based course attended by only three students in the department.
• Phase 1: Analyzed various dynamical systems and statistical mechanics models, including chaos, Hodgkin-Huxley
equations, and the Ising model.
• Phase 2: Conducted independent research on traffic congestion and identified unusual patterns in flow-speed relationships.
Link
Software Development Engineer Intern @ Oin Auto
• Collaborated with the SDE team to build a job-search website.
• Built a database for the job-searching website.
Data Analyst Intern @ Accenture (Shanghai)
• Leveraged linear programming and machine learning methods to address optimization problems.
• Prepared and visualized data, collaborating with other teams to provide insight for decision-making.
Research Intern @ Forms Syntron
• Conducted comprehensive market research on image processing to identify emerging trends and market demands.
• Collaborated with the project assistant to facilitate software development and testing process.
Math and Physics Teacher @ AYANE Seminar (文音ゼミナール)
• Taught mathematics and physics to students in preparation for the Examination for Japanese University (EJU).