Haoyan (Ryan) Luo
PhD, Machine Learning, University of Cambridge
hl678 [AT] cam.ac.uk
About
I am a PhD student in Machine Learning at the University of Cambridge, advised by Prof. Mateja Jamnik. I am affiliated with Darwin College and the Department of Computer Science and Technology. Prior to this, I completed my MRes in Machine Learning at Imperial College London, supervised by Prof. Lucia Specia. I obtained my B.Eng. degree in Computer Science from The Chinese University of Hong Kong.
I have worked as an AI Associate at J.P. Morgan, designing and implementing LLM-based solutions for real-world financial applications. I previously interned at Microsoft Research Asia, Shanghai AI Lab, Tencent and Seasun Entertainment.
📢 2025 update: open to advise student projects on interp research. For Cambridge students, please see this link.
My research centers on making large language models more interpretable, controllable, and useful in real-world systems. I am especially interested in understanding the internal representations that drive model behavior, and in turning this understanding into reliable interventions, editing methods, and agentic workflows. Currently, my work spans two connected directions:
- Mechanistic interpretability and model control: developing methods to identify, characterize, and intervene on concepts and circuits inside language models. [xLLM] [MoD] [SKOP]
- Applied ML and agentic systems: building scalable systems for document intelligence, automated feature engineering, anomaly detection, and domain-facing LLM applications. [OpenFE] [ActiveAD] [TIDE] [PageIndex]
Research
Don't Lose Focus: Activation Steering via Key-Orthogonal Projections PDF
Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik
ICML 2026 Workshop on Mechanistic Interpretability
Industry-Aligned Granular Topic Modeling PDF
Sae Young Moon, Myeongjun Erik Jang, Haoyan Luo, Chunyang Xiao, Antonios Georgiadis, Fran Silavong
EMNLP 2025
Explainability in Large Language Models: Pathways to Refinement and Alignment PDF Poster
Haoyan Luo
MRes Thesis
🔎 From Understanding to Utilization: A Survey on Explainability for Large Language Models PDF
Haoyan Luo, Lucia Specia
arXiv
OpenFE: Automated Feature Generation With Expert-level Performance
PageIndex Code Chat Platform
VectifyAI
A document indexing and parsing system for building retrieval-ready representations from complex documents, designed to support downstream LLM and agentic workflows.
🎙️ Singer-adaptive Singing Voice Conversion PDF Code Demo
Haoyan Luo
A singing voice conversion project that adapts a source vocal performance to a target singer while preserving musical content and expression.
🗺️ Steering the Networked Temporal Point Processes via Controlling the Network Graph PDF Code
Haoyan Luo, Shuang Li
A reinforcement learning project for controlling networked temporal point processes by intervening on the underlying graph structure.
🛠️ Deep-Learning-Lookup: Deep Learning Algorithms and Utils in Python Code
Haoyan Luo
A personal Python toolkit collecting deep learning algorithms, reusable utilities, and implementation notes for experimentation.
Misc.
During my undergraduate studies, I served as a student coordinator at Shaw College and was a host in the Communication and Public Relations Office. I led TEDxCUHKSZ as president (check out our annual events!) during my undergraduate years, promoting our slogan: "ideas worth spreading" :p In my free time, I'm a passionate piano and cello enthusiast. I also enjoy playing football, basketball, and tennis. Go Warriors and KTBFFH💙