Guisong Liu

EMWQ: An Efficient Mixed Precision Weight Quantization Method for Large Language Models

2025 · IEEE Transactions on Neural Networks and Learning Systems

Large language models (LLMs) have gained a lot of attention and achievements recently because of their significant comprehension and generative abilities. However, the large-scale parameters of LLMs require considerable computational resources in the training and …

Transferable Graph Condensation from the Causal Perspective

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

The increasing scale of graph datasets has significantly improved the performance of graph representation learning methods, but it has also introduced substantial training challenges. Graph dataset condensation techniques have emerged to compress large datasets into …