Haoyan (Ryan) Luo
PhD, Machine Learning, University of Cambridge
hl678 [AT] cam.ac.uk
Bio
I am a PhD student in Machine Learning at the University of Cambridge, where I am affiliated with Darwin College and the department of Computer Science. 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 & Data Science Associate at J.P. Morgan, designing and implementing LLM-based solutions for real-world financial applications. I previously interned at Microsoft Research Asia and Shanghai AI Lab, and held engineering roles at Tencent and Seasun Entertainment.
My research interests lie primarily in machine learning and natural language processing, with a focus on:
- Scaling concept-based models: developing scalable and efficient concept-based architectures with inherent interpretability and control.
- Interpretability and explainability in large language models (LLMs): advancing theoretical and empirical understanding of how LLMs represent and manipulate knowledge and concepts. [xLLM] [MoD] [LoPE]
- Applied machine learning systems: designing efficient, automated ML pipelines for real-world deployment at scale. [OpenFE] [TIDE] [ActiveAD]
Recent News
September 2024: Joined J.P. Morgan as an AI Associate. September 2024: Completed MRes (Master of Research) in AI & Machine Learning at Imperial College with Distinction. August 2024: Completed MRes thesis titled: "Explainable and Controllable Language Models: Interpretability and Its Applications", awarded with Distinction. August 2024: MoD paper, a new PEFT framework using mixture-of-depths ensembles, available on arXiv. June 2024: Survey paper on explainability and its applications for large language models is available on arXiv.Research
Localized Projectional Editing for Debiasing Language Models PDF Code
Haoyan Luo, Lucia Specia
arXiv
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
Localized Projectional Editing for Debiasing Language Models PDF Code
Haoyan Luo, Lucia Specia
arXiv
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
PDF
Code
Tianping Zhang, Zheyu Zhang, Haoyan Luo, Fengyuan Liu, Wei Cao, Jian Li
Fortieth International Conference on Machine Learning (ICML 2023)
ActiveAD: Enhancing Anomaly Detection in Tabular Data through Active Learning Strategies PDF Code
Haoyan Luo, Xiaofan Gui, Wei Cao, Jiang Bian
arXiv
🗺️ Steering the Networked Temporal Point Processes via Controlling the Network Graph PDF Code
Haoyan Luo, Shuang Li
Open-source Project
🛠️ Deep-Learning-Lookup: Deep Learning Algorithms and Utils in Python Code
Haoyan Luo
Open-source Project
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💙