Zhengyang Jin

Zhengyang Jin

Ph.D. Student in Computer Science

Boston College, Expected Start: Aug 2026

About Me

I am an incoming Ph.D. student in the Department of Computer Science at Boston College, advised by Prof. Momchil Tomov.

My research area of interest focuses on the computational modelling of human cognition and behaviour. Specifically, I study how individuals learn and adapt to new software environments by utilizing statistical modeling and mathematical frameworks. The primary goal of my work is to understand general human learning patterns to inform the design of user interfaces and improve the reliability of digital software experiences.

My background bridges computer science, statistical data analysis, and human factors, aiming to build computational paradigms that minimize cognitive friction in human-computer interactions.

Education

Ph.D. in Computer Science

Aug 2026 – Present

Boston College | Chestnut Hill, MA, USA

  • Advisor: Prof. Momchil Tomov
  • Focus: Computational modelling of human cognition & behaviour.

MSc in Computer Science (Adaptive Systems)

Sep 2021 – Oct 2022

University of Sussex | Brighton, UK

  • Graduated with Distinction
  • Dissertation: Extending Computational Visual Models for Colour Image Processing
  • Evaluated standard computational vision structures using basic spatial filters to enhance shape feature recognition over textures.

BSc in Computer Science

Sep 2019 – Jun 2021

University of Sussex | Brighton, UK

  • Graduated with First-Class Honours
  • Dissertation: Parameter Tuning for Synchronization in Mathematical Networks
  • Conducted mathematical fitting for network dynamics, simulating network structures incorporating time delays and coupling strengths.

Academic & Research Experience

Academic Research Collaborator

Sep 2025 – Jan 2026

Rogers Research Group, University of Northwestern | Remote

  • Supervised by Prof. John A. Rogers.
  • Conducted time-series data analysis on standard physiological signals to build computational models for prediction tasks.
  • Applied statistical distributions and foundational modeling techniques to understand and classify behavioral patterns in small-scale feature data.
  • Performed algorithm evaluation and interpretability studies to ensure the reliability of the computational models.

Independent Research Collaborator

Jul 2024 – Present

HLP Lab, University of Rochester | Remote

  • Supervised by Prof. Florian Jeager & Prof. Yuhao Zhu.
  • Engaged in independent research collaboration focusing on cross-talker generalization in computational speech perception.
  • Utilized statistical modelling concepts to create data structures capable of capturing speech variations.
  • Analysed large-scale interaction data using Generalized Linear Mixed Models (GLMMs) to map learning distances to behavioural outcomes.

Research Engineer

Aug 2023 – Mar 2024

A*STAR (Agency for Science, Technology and Research) | Singapore / Remote

  • Conducted literature reviews, developed mathematical and computational models, optimized algorithms, and performed data annotation for research projects.
  • Constructed standard virtual 3D scenes to serve as simulation training sets for evaluating algorithms.

Algorithm Engineer Intern

Jan 2023 – Jul 2023

hyperTunnel | London / Remote

  • Conducted literature reviews and implemented cutting-edge algorithms from academic papers.
  • Developed computational models for autonomous systems and performed simulations to evaluate and optimize system performance.
  • Designed a task scheduling and motion control framework in a simulated environment, optimizing operational efficiency.

Mentee of EMBRACE Mentoring Program

Oct 2021 – Jun 2022

Microsoft | London / Remote

  • Studied fairness-aware algorithms to understand how to mitigate statistical bias in software systems and ensure equitable user exposure.
  • Explored statistical modeling and data-driven concepts to model dynamic user preferences, assisting in the optimization of user interface layouts.

Publications

2025

Latent speech representations learned through self-supervised learning predict listeners' generalization of adaptation across talkers

Jin, Z., Zhu, Y. and Jaeger, T.F.

Cognitive Science, 2025.

2024

A dynamic fitting method for hybrid time-delayed and uncertain internally-coupled networks: from Kuramoto model to Macroscopic Mass Model

Jin, Z.

Networks & Their Applications XII. Cham: Springer Nature Switzerland, pp. 27–38, 2024.