activity
20242026
most citedEvolutionary Neural Architecture Search with Dual Contrastive Learning

2 citations · 9 across the 30 of their papers we have counts for

collaborators

32 papers

cs.RO2026

Learning to Optimize UAV Path Planning for Data Sensing in Wireless Sensor Networks

Sijie Ma, Zeyuan Ma, Weijia Cao +4

UAVs have emerged as highly flexible platforms for data sensing in Wireless Sensor Networks (WSNs). Path planning for UAVs in such tasks plays a key role to assure remote sensing e…

cs.NE2026

GeM-EA: A Generative and Meta-learning Enhanced Evolutionary Algorithm for Streaming Data-Driven Optimization

Yue Wu, Yuan-Ting Zhong, Ze-Yuan Ma +1

Streaming Data-Driven Optimization (SDDO) problems arise in many applications where data arrive continuously and the optimization environment evolves over time. Concept drift produ…

cs.NE2026

A Learning-Based Cooperative Coevolution Framework for Heterogeneous Large-Scale Global Optimization

Wenjie Qiu, Zixin Wang, Hongyu Fang +2

Cooperative Coevolution (CC) effectively addresses Large-Scale Global Optimization (LSGO) via decomposition but struggles with the emerging class of Heterogeneous LSGO (H-LSGO) pro…

cs.NE2026

COBRA++: Enhanced COBRA Optimizer with Augmented Surrogate Pool and Reinforced Surrogate Selection

Zipei Yu, Zhiyang Huang, Hongshu Guo +2

The optimization problems in realistic world present significant challenges onto optimization algorithms, such as the expensive evaluation issue and complex constraint conditions.…

cs.NE2026

Surrogate Ensemble in Expensive Multi-Objective Optimization via Deep Q-Learning

Yuxin Wu, Hongshu Guo, Ting Huang +2

Surrogate-assisted Evolutionary Algorithms~(SAEAs) have shown promising robustness in solving expensive optimization problems. A key aspect that impacts SAEAs' effectiveness is sur…

cs.NE2026

Meta-Learning-Assisted Constraint Relaxation for Constrained Black-Box Optimization

Qianhao Zhu, Sijie Ma, Zeyuan Ma +3

Constraint handling is central to constrained black-box optimization (BBO), where objective improvement and feasibility restoration often provide conflicting search signals. Existi…