activity
20242026
collaborators
Showing cs.NEShow all

7 papers · 1 filter

cs.NE2026

Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems

Chao Wang, Lingling Li, Fang Liu +1

Artificial intelligence (AI) is shifting scientific discovery from task-specific workflows towards autonomous systems that organize exploration with experimental and human feedback…

cs.NE2026

Model Merging to Evolution: Parameter Space Exploration for Expert Models

Chao Wang, Yuchen Guo, Zheng Tan +4

Model merging integrates the capabilities of multiple expert models to create strong models for multiple tasks without additional training, thereby reducing computational resource…

cs.NE2026

Task-free Adaptive Meta Black-box Optimization

Chao Wang, Licheng Jiao, Lingling Li +4

Handcrafted optimizers become prohibitively inefficient for complex black-box optimization (BBO) tasks. MetaBBO addresses this challenge by meta-learning to automatically configure…

cs.NE2025

Learning Evolution via Optimization Knowledge Adaptation

Chao Wang, Lingling Li, Licheng Jiao +3

The iterative search process of evolutionary algorithms (EAs) encapsulates optimization knowledge within historical populations and fitness evaluations. Effective utilization of th…

cs.NE2024

Knowledge-aware Evolutionary Graph Neural Architecture Search

Chao Wang, Jiaxuan Zhao, Lingling Li +4

Graph neural architecture search (GNAS) can customize high-performance graph neural network architectures for specific graph tasks or datasets. However, existing GNAS methods begin…

cs.NE2024

Automatic Graph Topology-Aware Transformer

Chao Wang, Jiaxuan Zhao, Lingling Li +3

Existing efforts are dedicated to designing many topologies and graph-aware strategies for the graph Transformer, which greatly improve the model's representation capabilities. How…