Publications
A novel Tchebycheff set scalarization approach to find a small set of solutions to tackle a large number of optimization objectives.
Xi Lin, Yilu Liu, Xiaoyuan Zhang, Fei Liu, Zhenkun Wang, and Qingfu Zhang
EoH combines LLMs and EC to automate the design of heuristics. EoH co-evolves “thoughts” (natural language as ideas) and executable code using LLMs, outperforming heuristics designed by human experts on various combinatorial optimization problems.
Fei Liu, Xialiang Tong, Mingxuan Yuan, Xi Lin, Fu Luo, Zhenkun Wang, Zhichao Lu, and Qingfu Zhang
MOEA/D is a multiobjective evolutionary algorithm that uses decomposition to optimize subproblems simultaneously. MOEA/D is now one of the two most used frameworks for solving multiobjective optimization problems.
Qingfu Zhang and Hui Li
Improve practical utilities of neural architecture search through many-objective optimization, iterative surrogate modeling, and transfer learning.
Zhichao Lu , Gautam Sreekumar, Erik Goodman, Wolfgang Banzhaf, Kalyanmoy Deb, and Vishnu N. Boddeti
Tutorials
[1] Multi-objective Algorithm Design using Large Language Models
Fei Liu, Zhichao Lu, Xi Lin, Qingfu Zhang, and Zhenkun Wang
EMO 25, Proceedings of the International Conference on Evolutionary Multi-Criterion Optimization 2025
[2] Multi-Objective Machine Learning
Vishnu Naresh Boddeti, Zhichao Lu, Xi Lin, Qingfu Zhang, and Kalyanmoy Deb
WCCI 24, Proceedings of the IEEE World Congress on Computational Intelligence 2024
[3] Multi-Objective Deep Learning
Vishnu Naresh Boddeti, Zhichao Lu, Xi Lin, Qingfu Zhang, and Kalyanmoy Deb
CVPR 23, Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023
Surveys
[1] Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond
Weiyu Chen, Xiaoyuan Zhang, Baijiong Lin, Xi Lin, Han Zhao, Qingfu Zhang, James T. Kwok
arXiv, 2025
[2] A Systematic Survey on Large Language Models for Algorithm Design
Fei Liu, Yiming Yao, Ping Guo, Zhiyuan Yang, Zhe Zhao, Xi Lin, Xialiang Tong, Mingxuan Yuan, Zhichao Lu, Zhenkun Wang, and Qingfu Zhang
arXiv, 2024
[3] Heuristics for Vehicle Routing Problem: A Survey and Recent Advances
Fei Liu, Chengyu Lu, Lin Gui, Qingfu Zhang, Xialiang Tong, Mingxuan Yuan
arXiv, 2023
Software
[1] LLM4AD: A Platform for Algorithm Design with Large Language Model
Fei Liu, Rui Zhang, Zhuoliang Xie, Rui Sun, Kai Li, Xi Lin, Zhenkun Wang, Zhichao Lu, and Qingfu Zhang
[2] LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch
Xiaoyuan Zhang, Liang Zhao, Yingying Yu, Xi Lin, Yifan Chen, Han Zhao, Qingfu Zhang
Selected List of publications
Full list of papers are available on CityU Scholars.
Journal
[1] A neighborhood-based momentum approach to accelerate convergence in multi-objective optimization
Longcan Chen, Lie Meng Pang, Qingfu Zhang, and Hisao Ishibuchi
Swarm and Evolutionary Computation (Swarm), 2026
[2] Uncertain Priors for Graphical Causal Models: A Multi-Objective Optimization Perspective
Zidong Wang, Xiaoguang Gao, and Qingfu Zhang
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2025
[3] Incorporating structural constraints into continuous optimization for causal discovery
Zidong Wang, Xiaoguang Gao, Xiaohan Liu, Xinxin Ru, and Qingfu Zhang
Neurocomputing, 2024
[4] Determining the direction of the local search in topological ordering space for Bayesian network structure learning
Zidong Wang, Xiaoguang Gao, Xiangyuan Tan, and Xiaohan Liu
Knowledge-Based Systems (KBS), 2021
[5] Learning Bayesian networks using A* search with ancestral constraints
Zidong Wang, Xiaoguang Gao, Xiangyuan Tan, and Xiaohan Liu
Neurocomputing, 2021
[6] Learning Bayesian networks based on order graph with ancestral constraints
Zidong Wang, Xiaoguang Gao, Yu Yang, Xiangyuan Tan, and Daqing Chen
Knowledge-Based Systems (KBS), 2021
[7] Adapting MOEA/D to CMA-ES for Dealing with Ill-conditioned Multiobjective Problems
Chengyu Lu, Zhenhua Li, and Qingfu Zhang
Evolutionary Computation, 2026
[8] EvolCAF: Automatic Cost-Aware Acquisition Function Design Using Large Language Models
Yiming Yao, Fei Liu, Ji Cheng, and Qingfu Zhang
Evolutionary Computation (EC), 2026
[9] Top‑K-Aware Set Optimization for Component-Sharing Multiobjective Optimization
Liang Zhao, Peng Wang, Jiangtao Shen, Luziwei Leng, Zhichao Lu, and Qingfu Zhang.
IEEE Transactions on Evolutionary Computation (TEVC), 2026
[10] Dyn-SSM: Towards the Efficient Long Sequence Learning via Bio-interpretable Dynamics in Spiking State Space Models
Yan Zhong, Ruoyu Zhao, Chao Wang, Jiaqi He, Qinghai Guo, Jianguo Zhang, Zhichao Lu, Luziwei Leng
IEEE Transactions on Cognitive and Developmental Systems (TCDS), 2026
[11] CAN: A Curvature-Aware Nesterov Optimizer for Fast Elastic Simulation With Topological Changes
Yuxiong Qin, Huamin Wang, Qingfu Zhang, Zhongkai Zhang
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2026
[12] Fast Nodal Hessian Computation for Peridynamic Fracture Simulation
Yuxiong Qin, Qingfu Zhang, Zhongkai Zhang
Computer Graphics Forum (CGF), 2026
[13] Few for Many: Towards Efficient and Flexible Many-Objective Optimization
Yilu Liu, Xi Lin, Liang Zhao, and Qingfu Zhang
IEEE Transactions on Evolutionary Computation (TEVC), 2026
[14] Lexicographic Lipschitz Bandits: New Algorithms and a Lower Bound
Bo Xue, Ji Cheng, Fei Liu, Yimu Wang, Lijun Zhang, and Qingfu Zhang
Journal of Machine Learning Research (JMLR), 2025
[15] Lexicographic Lipschitz Bandits: New Algorithms and a Lower Bound
Bo Xue, Ji Cheng, Fei Liu, Yimu Wang, Lijun Zhang and Qingfu Zhang
Journal of Machine Learning Research (JMLR), 2025
[16] Component-Sharing Preference in Expensive Multiobjective Optimization
Liang Zhao, Peng Wang, Jiangtao Shen, Baowei Song, and Qingfu Zhang.
IEEE Transactions on Evolutionary Computation (TEVC), 2025
[17] Parametric Pareto Set Learning: Amortizing Multi-Objective Optimization With Parameters
Ji Cheng, Xi Lin, Bo Xue, and Qingfu Zhang
IEEE Transactions on Evolutionary Computation (TEVC), 2025
[18] MOEA/D-CMA Made Better with (1+1)-CMA-ES
Chengyu Lu, Yilu Liu, and Qingfu Zhang
IEEE Congress on Evolutionary Computation (CEC), 2024
[19] DPP-HSS: Towards Fast and Scalable Hypervolume Subset Selection for Many-objective Optimization
Cheng Gong, Yang Nan, Ke Shang, Ping Guo, Hisao Ishibuchi, and Qingfu Zhang
IEEE Transactions on Evolutionary Computation (TEVC), 2024
[20] Many-to-Few Decomposition: Linking R2-Based and Decomposition-Based Multiobjective Efficient Global Optimization Algorithms
Liang Zhao, Xiaobin Huang, Chao Qian, and Qingfu Zhang
IEEE Transactions on Evolutionary Computation (TEVC), 2024
[21] Machine Learning Assisted Multiobjective Evolutionary Algorithm for Routing and Packing
Fei Liu, Qingfu Zhang, Qingling Zhu, Tong Xialiang, and Mingxuan Yuan
IEEE Transactions on Evolutionary Computation (TEVC), 2024
[22] Hypervolume-Guided Decomposition for Parallel Expensive Multiobjective Optimization
Liang Zhao and Qingfu Zhang
IEEE Transactions on Evolutionary Computation (TEVC), 2023
Conference
[1] Robust Causal Discovery Under Imperfect Structural Constraints
Zidong Wang, Xi Lin, Chuchao He, and Xiaoguang Gao
AAAI Conference on Artificial Intelligence (AAAI), 2026
[2] LLM-enhanced Score Function Evolution for Causal Structure Learning
Zidong Wang, Fei Liu, Qi Feng, Qingfu Zhang, and Xiaoguang Gao
International Joint Conference on Artificial Intelligence (IJCAI), 2025
[3] Multimodal llm-assisted evolutionary search for programmatic control policies
Qinglong Hu, Tong Xialiang, Mingxuan Yuan, Fei Liu, Zhichao Lu, Qingfu Zhang
International Conference on Learning Representations (ICLR), 2026
[4] Evolving Interdependent Operators with Large Language Models for Multi-Objective Combinatorial Optimization
Junhao Qiu, Xin Chen, Liang Ge, Liyong Lin, Zhichao Lu, Qingfu Zhang
International Conference on Machine Learning (ICML), 2026
[5] Neural Evolution Strategy for Black-box Pareto Set Learning
Chengyu Lu, Zhenhua Li, Xi Lin, Ji Cheng, and Qingfu Zhang
Advances in Neural Information Processing Systems (NeurIPS), 2026
[6] Parametric Pareto Set Learning for Expensive Multi-Objective Optimization
Ji Cheng, Bo Xue, and Qingfu Zhang
AAAI Conference on Artificial Intelligence (AAAI), 2026
[7] Safe Multi-Objective Linear Bandits with Hierarchical Preferences
Bo Xue, Mengxia He, Yilu Liu, Ji Cheng, Zhe Zhao, and Qingfu Zhang
International Joint Conference on Artificial Intelligence (IJCAI), 2026
[8] Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits
Bo Xue, Yuanyu Wan, Zhichao Lu, and Qingfu Zhang
AAAI Conference on Artificial Intelligence (AAAI, Oral), 2026
[9] Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories
Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Bo Xue, Qingfu Zhang, Hau-San Wong, and Taiji Suzuki
ICML Workshop on Foundations of Deep Generative Models (FoGen), Spotlight, 2026
[10] Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Hau-San Wong, Qingfu Zhang, and Taiji Suzuki
International Conference on Machine Learning (ICML), 2026
[11] DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Discrete Diffusion Models
Dake Bu, Wei Huang, Andi Han, Si Wu, Hau-San Wong, Qingfu Zhang, Taiji Suzuki, and Atsushi Nitanda
ICML Workshop on Foundations of Deep Generative Models (FoGen), Oral, 2026
[12] How to Choose Solutions for Applying Momentum in Evolutionary Multi-Objective Optimization
Longcan Chen, Lie Meng Pang, Qingfu Zhang, and Hisao Ishibuchi
IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2025
[13] Using Momentum Moves as Training Data for Neural Network-Based Offspring Generation in Evolutionary Multi-Objective Optimization
Longcan Chen, Lie Meng Pang, Qingfu Zhang, and Hisao Ishibuchi
International Joint Conference on Neural Networks (IJCNN), 2025
[14] Multi-objective Evolution of Heuristic Using Large Language Model
Shunyu Yao, Fei Liu, Xi Lin, Zhichao Lu, Zhenkun Wang, Qingfu Zhang
Association for the Advancement of Artificial Intelligence (AAAI), 2025
[15] Partition to evolve: Niching-enhanced evolution with llms for automated algorithm discovery
Qinglong Hu, Qingfu Zhang
Advances in Neural Information Processing Systems 38 Main Conference (NeurIPS), 2025
[16] Multi-objective Linear Reinforcement Learning with Lexicographic Rewards
Bo Xue, Dake Bu, Ji Cheng, Yuanyu Wan, and Qingfu Zhang
International Conference on Machine Learning (ICML), 2025
[17] Problem-dependent Regret for Lexicographic Multi-Armed Bandits with Adversarial Corruptions
Bo Xue, Xi Lin, Yuanyu Wan, and Qingfu Zhang
International Joint Conference on Artificial Intelligence (IJCAI), 2025
[18] Multiple Trade-offs: An Improved Approach for Lexicographic Linear Bandits
Bo Xue, Xi Lin, Xiaoyuan Zhang, and Qingfu Zhang
AAAI Conference on Artificial Intelligence (AAAI, Oral), 2025
[19] Provable In-Context Vector Arithmetic via Retrieving Task Concepts
Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Qingfu Zhang, Hau-San Wong, and Taiji Suzuki
International Conference on Machine Learning (ICML), 2025
[20] Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits
Bo Xue, Yuanyu Wan, Zhichao Lu and Qingfu Zhang
AAAI Conference on Artificial Intelligence (AAAI), 2026
[21] Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off
Song Lai, Zhe Zhao, Fei Zhu, Xi Lin, Qingfu Zhang, and Gaofeng Meng
AAAI Conference on Artificial Intelligence (AAAI), 2025
[22] Multi-Objective Neural Bandits with Random Scalarization
Ji Cheng, Bo Xue, Chengyu Lu, Ziqiang Cui, and Qingfu Zhang
International Joint Conference on Artificial Intelligence (IJCAI), 2025
[23] Gradient-Guided Epsilon Constraint Method for Online Continual Learning
Song Lai, Changyi Ma, Fei Zhu, Zhe Zhao, Xi Lin, Gaofeng Meng, and Qingfu Zhang
Advances in Neural Information Processing Systems (NeurIPS), 2025
[24] Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems
Fu Luo, Xi Lin, Yaoxin Wu, Zhenkun Wang, Tong Xialiang, Mingxuan Yuan, and Qingfu Zhang
International Conference on Learning Representations (ICLR), 2025
[25] Enhancing the convergence ability of evolutionary multi-objective optimization algorithms with momentum
Longcan Chen, Lie Meng Pang, Qingfu Zhang, and Hisao Ishibuchi
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), 2024
[26] Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
Dake Bu, Wei Huang, Taiji Suzuki, Ji Cheng, Qingfu Zhang, Zhiqiang Xu, and Hau-San Wong
International Conference on Machine Learning (ICML), 2024
[27] Hierarchize Pareto Dominance in Multi-Objective Stochastic Linear Bandits
Ji Cheng, Bo Xue, Jiaxiang Yi, and Qingfu Zhang
AAAI Conference on Artificial Intelligence (AAAI), 2024
[28] Evolve Cost-aware Acquisition Functions Using Large Language Models
Yiming Yao, Fei Liu, Ji Cheng, and Qingfu Zhang
Parallel Problem Solving from Nature (PPSN), 2024
[29] Smooth Tchebycheff Scalarization for Multi-Objective Optimization
Xi Lin, Xiaoyuan Zhang, Zhiyuan Yang, Fei Liu, Zhenkun Wang, and Qingfu Zhang
International Conference on Machine Learning (ICML), 2024
[30] Two Fists, One Heart: Multi-Objective Optimization Based Strategy Fusion for Long-tailed Learning
Zhe Zhao, Pengkun Wang, HaiBin Wen, Wei Xu, Song Lai, Qingfu Zhang, and Yang Wang
International Conference on Machine Learning (ICML), 2024
[31] Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Taiji Suzuki, Qingfu Zhang, and Hau-San Wong
Advances in Neural Information Processing Systems (NeurIPS), 2024
[32] Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
Dake Bu, Wei Huang, Taiji Suzuki, Ji Cheng, Qingfu Zhang, Zhiqiang Xu, and Hau-San Wong
International Conference on Machine Learning (ICML), 2024
[33] Multiobjective Lipschitz Bandits under Lexicographic Ordering
Bo Xue, Ji Cheng, Fei Liu, Yimu Wang, and Qingfu Zhang
AAAI Conference on Artificial Intelligence (AAAI), 2024
[34] Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization
Fu Luo, Xi Lin, Fei Liu, Qingfu Zhang, and Zhenkun Wang
Neural Information Processing Systems (NeurIPS), 2023