4 papers
Order Matters: Unveiling the Hidden Impact of Macro Placement Sequences via Proxy-Guided LLM Evolution
Shibing Mo, Jing Liu, Jianchu Xu +1
Macro placement is a fundamental step in modern chip physical design, playing a crucial role in determining the solution quality of high-dimensional combinatorial optimization prob…
High-order Knowledge Based Network Controllability Robustness Prediction: A Hypergraph Neural Network Approach
Shibing Mo, Jiarui Zhang, Jiayu Xie +2
In order to evaluate the invulnerability of networks against various types of attacks and provide guidance for potential performance enhancement as well as controllability maintena…
Textual Self-attention Network: Test-Time Preference Optimization through Textual Gradient-based Attention
Shibing Mo, Haoyang Ruan, Kai Wu +1
Large Language Models (LLMs) have demonstrated remarkable generalization capabilities, but aligning their outputs with human preferences typically requires expensive supervised fin…
AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks
Shibing Mo, Kai Wu, Qixuan Gao +2
In real-world applications, spectral Graph Neural Networks (GNNs) are powerful tools for processing diverse types of graphs. However, a single GNN often struggles to handle differe…