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, Shenzhen.
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.
I study how machine learning models work, how to make them more reliable, and how to use them to solve interesting real-world problems. My recent work spans:
- Model mechanisms, interpretability, and control: studying and manipulating the representations that shape language-model behavior [xLLM] [MoD] [SKOP] [Persistent SAE].
- Applied ML and agentic systems: building scalable methods for document intelligence, automated systems, and domain-facing LLM applications [OpenFE] [ActiveAD] [TIDE] [PageIndex].
Research
Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models PDF
Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik
arXiv 2026
Don't Lose Focus: Activation Steering via Key-Orthogonal Projections PDF Code
Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik
ICML 2026 Workshop on Mechanistic Interpretability
Tuning Language Models by Mixture-of-Depths Ensemble PDF Poster Code
Haoyan Luo, Lucia Specia
COLM 2026 Workshop on Actionable 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 2024
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.
I served as president of TEDxCUHKSZ during my undergraduate years (check out our annual events), 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💙