Projects
Study of Packing Problems in Different Models Jul 2025 - Present
Related fields: Online Algorithms, Competitive Analysis
This individual research project investigates online algorithms for packing problems under various computational models. The study will explore competitive analysis techniques across different online models, aiming to characterize trade-offs between information, randomness, and optimality in these problem domains. Supervised by Professor Allan Borodin at the University of Toronto.
Advanced Search and RL Algorithms for Othello May 2025 - Present
Related fields: Reinforcement Learning, Artificial Intelligence
In the second phase of the project, I focused on advanced AI techniques for strategic gameplay in Othello. I implemented multiple Monte Carlo Tree Search (MCTS) agents, exploring various configurations including random and heuristic-based rollout policies, partial and full expansion strategies, and tuning of exploration constants. I conducted large-scale performance evaluations to study how these design choices impact win rates and efficiency. Currently, I am developing a reinforcement learning-based agent using Temporal-Difference (TD) Learning, allowing the agent to improve through self-play by learning value estimates from game outcomes. Supervised by Professor Alice Gao at the University of Toronto.
This project was also presented in a research poster showcase. [View Poster]
Designing and Implementing AI Agents for Othello Jan 2025 - Apr 2025
Related fields: Artificial Intelligence, Game AI
Under the supervision of Professor Alice Gao at the University of Toronto, I designed and implemented a fully functional Othello (Reversi) game engine in Python, supporting human input, random agents, and AI agents. This included developing the full game logic—legal move generation, disc flipping, and end-game detection—within a modular architecture. I built several game-playing agents, including a minimax search agent enhanced with alpha-beta pruning and various heuristic functions such as coin parity, mobility, stability, and corner control. The system was equipped with a flexible command-line interface and supported automated batch evaluations between agents for performance testing under different settings.
This project was also presented in a research poster showcase. [View Poster]
VR Backend Framework for Cilindir Jan 2025 - Present
Related fields: Computer Vision, Artificial Intelligence, Real-Time Systems
As part of a collaborative project with the startup Cilindir, I am working with a team to develop a backend framework that supports lifelike avatar generation and real-time manipulation for their virtual reality (VR) pod. This framework processes input from a network of cameras to generate and continuously update 3D avatars based on user movement. Leveraging machine learning techniques and real-time rendering technologies, the project aims to create an immersive, wearables-free virtual communication experience.
Weather Weavers Sep 2023 - Dec 2023
Related fields: Software Design
In a team of four, I developed a Java-based weather application that integrated real-time data using external APIs. By applying Clean Architecture and adhering to SOLID principles, I ensured the project maintained modularity and scalability. Additionally, I conducted comprehensive testing and debugging, which significantly improved the application’s reliability and overall user experience.