Weiyu Chen

PhD Student, Department of Computer Science and Engineering, HKUST

Welcome to my personal webpage! I am currently a fourth-year PhD student at The Hong Kong University of Science and Technology (HKUST), supervised by Prof. James Kwok. My research interests include multi-objective deep learning, efficient LLM (such as low-rank adaptation and model merging), and discrete diffusion models. I am actively seeking collaborations in these areas. If you are interested in working together, please feel free to contact me.

Google Scholar GitHub
Honors & Awards
  • IEEE (HK) CI Chapter Graduate Student Paper Competition First Runner-Up 2024
  • Hong Kong PhD Fellowship Scheme (HKPFS) 2021
  • National Scholarship 2020
  • PPSN Best Paper Nomination 2020
Academic Service
  • Journal Reviewer: IEEE TNNLS, IEEE TAI, Artificial Intelligence, TMLR
  • Conference Reviewer: ICML, NeurIPS, ICLR, AAAI, IJCAI
News
2025
Two papers have been accepted to ICML 2025, including one as the first author!
May 02
We will be hosting a tutorial on gradient-based multi-objective optimization at IJCAI 2025 (Montreal and Guangzhou)!
Apr 29
2024
I received the First Runner-Up Prize in the IEEE (HK) Computational Intelligence Chapter Graduate Student Competition!
Aug 25
Our paper has been accepted at ICML 2024!
May 03
Selected Publications (view all)
Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging
Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging

Weiyu Chen, James Kwok

International Conference on Machine Learning (ICML) 2025

[Paper]

Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging
Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging

Weiyu Chen, James Kwok

International Conference on Machine Learning (ICML) 2025

[Paper]

Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond
Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond

Weiyu Chen*, Xiaoyuan Zhang*, Baijiong Lin*, Xi Lin, Han Zhao, Qingfu Zhang, James Kwok (* equal contribution)

arXiv 2025 Survey

[Paper]

Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond
Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond

Weiyu Chen*, Xiaoyuan Zhang*, Baijiong Lin*, Xi Lin, Han Zhao, Qingfu Zhang, James Kwok (* equal contribution)

arXiv 2025 Survey

[Paper]

Efficient Pareto Manifold Learning with Low-Rank Structure
Efficient Pareto Manifold Learning with Low-Rank Structure

Weiyu Chen, James Kwok

International Conference on Machine Learning (ICML) 2024 Spotlight (3.5%)

[Paper]

Efficient Pareto Manifold Learning with Low-Rank Structure
Efficient Pareto Manifold Learning with Low-Rank Structure

Weiyu Chen, James Kwok

International Conference on Machine Learning (ICML) 2024 Spotlight (3.5%)

[Paper]

Multi-Resolution Diffusion Models for Time Series Forecasting
Multi-Resolution Diffusion Models for Time Series Forecasting

Lifeng Shen, Weiyu Chen, James Kwok

International Conference on Learning Representations (ICLR) 2024

[Paper]

Multi-Resolution Diffusion Models for Time Series Forecasting
Multi-Resolution Diffusion Models for Time Series Forecasting

Lifeng Shen, Weiyu Chen, James Kwok

International Conference on Learning Representations (ICLR) 2024

[Paper]

Enhancing Meta Learning via Multi-Objective Soft Improvement Functions
Enhancing Meta Learning via Multi-Objective Soft Improvement Functions

Runsheng Yu, Weiyu Chen, Xinrun Wang, James Kwok

International Conference on Learning Representations (ICLR) 2023

[Paper]

Enhancing Meta Learning via Multi-Objective Soft Improvement Functions
Enhancing Meta Learning via Multi-Objective Soft Improvement Functions

Runsheng Yu, Weiyu Chen, Xinrun Wang, James Kwok

International Conference on Learning Representations (ICLR) 2023

[Paper]

HV-Net: Hypervolume Approximation based on DeepSets
HV-Net: Hypervolume Approximation based on DeepSets

Ke Shang*, Weiyu Chen*, Weiduo Liao, Hisao Ishibuchi (* equal contribution)

IEEE Transactions on Evolutionary Computation 2022

[Paper]

HV-Net: Hypervolume Approximation based on DeepSets
HV-Net: Hypervolume Approximation based on DeepSets

Ke Shang*, Weiyu Chen*, Weiduo Liao, Hisao Ishibuchi (* equal contribution)

IEEE Transactions on Evolutionary Computation 2022

[Paper]

Multi-Objective Deep Learning with Adaptive Reference Vectors
Multi-Objective Deep Learning with Adaptive Reference Vectors

Weiyu Chen, James Kwok

Conference on Neural Information Processing Systems (NeurIPS) 2022

[Paper]

Multi-Objective Deep Learning with Adaptive Reference Vectors
Multi-Objective Deep Learning with Adaptive Reference Vectors

Weiyu Chen, James Kwok

Conference on Neural Information Processing Systems (NeurIPS) 2022

[Paper]

Fast Greedy Subset Selection from Large Candidate Solution Sets in Evolutionary Multi-objective Optimization
Fast Greedy Subset Selection from Large Candidate Solution Sets in Evolutionary Multi-objective Optimization

Weiyu Chen, Hisao Ishibuchi, Ke Shang

IEEE Transactions on Evolutionary Computation 2021

[Paper]

Fast Greedy Subset Selection from Large Candidate Solution Sets in Evolutionary Multi-objective Optimization
Fast Greedy Subset Selection from Large Candidate Solution Sets in Evolutionary Multi-objective Optimization

Weiyu Chen, Hisao Ishibuchi, Ke Shang

IEEE Transactions on Evolutionary Computation 2021

[Paper]

All publications