About Me
I'm Chengyu Fan (go by "Cathy"), a senior undergraduate student at Colby College majoring in Computer Science (AI concentration) and Mathematical Sciences, with a minor in Statistics. My research lies at the intersection of artificial intelligence, multimodal interaction, and large language models.
I've conducted research across a range of topics including multimodal coordination, LLM-based agent simulation, and pose estimation. My work has been published at ACM ICMI and ACM UMAP, and has involved close interdisciplinary collaboration between computer science and psychology.
I'm especially passionate about building intelligent systems that engage with human behavior in socially responsible and interpretable ways. I enjoy working with multi-agent simulations, generative models, and applied machine learning pipelines — always with an eye toward ethical deployment.
I'm currently seeking a PhD position starting in Fall 2026, where I hope to deepen my research in responsible AI, agent modeling, and multimodal interaction. If you are a faculty member, or know of an open position in a lab, I would love to connect.
Research
- Multimodal Human Coordination: I co-authored a study on quantifying human movement coordination through multimodal alignment techniques. This research, combining computer science and psychology, was published at ACM ICMI 2024.
- LLM-Based Agent Simulation: At Colby's Davis Institute for AI, I helped build a persistent multi-agent simulation platform (Comp-HuSim) using large language models to simulate digital personalities. This work was published at ACM UMAP 2024.
- Pose Estimation and Responsible AI: I'm currently working on integrating pose estimation techniques with ethical AI principles as part of an ongoing research project in Colby's HUMANE Lab.
- AI for Environmental Sustainability: I helped develop a drone image dataset (containing around 1k images) and trained a computer vision model to detect coastal litter in Maine, achieving ~92% accuracy and supporting local recycling efforts.