8 papers
AutoPSO: A Meta-framework for Automated Particle Swarm Optimization
Xinmeng Yu, Jiaxin Gao, Jianguo Zhang +2
Particle swarm optimization (PSO) is a widely used metaheuristic, prized for its simplicity and small parameter set. Although decades of research have produced numerous PSO variant…
EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization
Tao Jiang, Xinmeng Yu, Chenhao Yi +5
Evolutionary model merging provides a powerful framework for the automated, training-free composition of LLMs through parameter-space search. However, existing methods predominantl…
Enabling Population-Level Parallelism in Tree-Based Genetic Programming for GPU Acceleration
Zhihong Wu, Lishuang Wang, Kebin Sun +2
Tree-based Genetic Programming (TGP) is a widely used evolutionary algorithm for tasks such as symbolic regression, classification, and robotic control. Due to the intensive comput…
A Multi-objective Evolutionary Algorithm Based on Bi-population with Uniform Sampling for Neural Architecture Search
Yu Xue, Pengcheng Jiang, Chenchen Zhu +4
Neural architecture search (NAS) automates neural network design, improving efficiency over manual approaches. However, efficiently discovering high-performance neural network arch…
Unleashing the Potential of Differential Evolution through Individual-Level Strategy Diversity
Chenchen Feng, Minyang Chen, Zhuozhao Li +1
Since Differential Evolution (DE) is sensitive to strategy choice, most existing variants pursue performance through adaptive mechanisms or intricate designs. While these approache…
Bridging Evolutionary Multiobjective Optimization and GPU Acceleration via Tensorization
Zhenyu Liang, Hao Li, Naiwei Yu +2
Evolutionary multiobjective optimization (EMO) has made significant strides over the past two decades. However, as problem scales and complexities increase, traditional EMO algorit…