Hello, I'm

Hao Tan 谭浩

PhD Candidate in Computer Science

University of Leeds

scroll
01

About

Hao Tan

Currently, I am a Ph.D. candidate with the School of Computer Science at the University of Leeds, UK with expected graduation in July 2026, specializing in Deep Learning Model Fusion and Multi-Task Learning. I received the B.Eng. degree in Computer Science and Engineering from Southern University of Science and Technology (SUSTech), China in 2020. Prior to my doctoral studies, I researched in Neural Architecture Search and evolutionary computation at SUSTech. I am deep into AI applications and finance investment.

Thesis Fusion Strategies for Cascading, Merging, and Multi-Tasking Deep Models
Interests AI Applications · Finance Investment
02

Education

Oct 2021 — Jul 2026 (Expected)

University of Leeds

Doctor of Philosophy — Computer Science

PhD programme under the supervision of Dr. Nabi Omidvar and Prof. Netta Cohen.
Thesis: Fusion Strategies for Cascading, Merging, and Multi-Tasking Deep Models

Sep 2016 — Jun 2020

Southern University of Science and Technology

B.Eng. — Computer Science and Technology

Thesis: Neural Architecture Search Based on Differential Evolution

03

Experience

Jul 2020 — Jul 2021

Research Assistant

SUSTech — Dept. of Computer Science and Engineering

Key member responsible for developing neural architecture search algorithms. Collaborated with industry partners to design lightweight neural architectures tailored for microchip hardware constraints. Implemented evolutionary algorithms in PyTorch to automate network architecture optimization, achieving state-of-the-art performance.

04

Publications & Patents

Journal Articles

RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning

Hao Tan, Ran Cheng, Shihua Huang, Cheng He, Changxiao Qiu, Fan Yang, Ping Luo

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021

Efficient Evolutionary Neural Architecture Search by Modular Inheritable Crossover

Cheng He, Hao Tan, Shihua Huang, Ran Cheng

Swarm and Evolutionary Computation (SWEVO), 2021

Conference Papers

Efficient Evolutionary Neural Architecture Search by Modular Inheritable Crossover

Hao Tan, Cheng He, Dexuan Tang, Ran Cheng

International Conference on Bio-inspired Computing: Theories and Applications (BIC-TA), 2019

🏆 Best Paper Award

Patents

A Neural Architecture Search Method and System based on Evolutionary Learning

Ran Cheng, Hao Tan, Cheng He, Zhanglu Hou, Changxiao Qiu

International Patent, PCT/CN2020/136950, filed June 23, 2022

05

Honours & Awards

2021

SUSTech – University of Leeds Studentship

2019

Best Paper Award

BIC-TA 2019 — International Conference on Bio-inspired Computing: Theories and Applications

06

Get in Touch

I'm always open to discussing research, collaborations, or opportunities in AI and technology.