2 papers
cs.LG2025
Fre-CW: Targeted Attack on Time Series Forecasting using Frequency Domain Loss
Naifu Feng, Lixing Chen, Junhua Tang +3
Transformer-based models have made significant progress in time series forecasting. However, a key limitation of deep learning models is their susceptibility to adversarial attacks…
cs.CL2024
Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph
Yutong Zhang, Lixing Chen, Shenghong Li +6
Large language models (LLMs) have demonstrated exceptional performance across a wide variety of domains. Nonetheless, generalist LLMs continue to fall short in reasoning tasks nece…