8 papers
FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment
Kewen Zhu, Liping Yi, Zhiming Zhao +3
Aligning large language models (LLMs) with human preferences in federated learning (FL) is challenging due to decentralized, privacy-sensitive, and highly non-IID preference data.…
Helix: A Dual-Helix Co-Evolutionary Multi-Agent System for Prompt Optimization and Question Reformulation
Kewen Zhu, Liping Yi, Zhiming Zhao +2
Automated prompt optimization (APO) aims to improve large language model performance by refining prompt instructions. However, existing methods are largely constrained by fixed pro…
Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Representation Alignment
Yanru Sun, Emadeldeen Eldele, Zongxia Xie +5
Recent advances have demonstrated that Large Language Models (LLMs) can be effectively adapted for time series forecasting, revealing strong potential beyond natural language tasks…
Lightweight Channel-wise Dynamic Fusion Model: Non-stationary Time Series Forecasting via Entropy Analysis
Tianyu Jia, Zongxia Xie, Yanru Sun +2
Non-stationarity is an intrinsic property of real-world time series and plays a crucial role in time series forecasting. Previous studies primarily adopt instance normalization to…
Patch-wise Structural Loss for Time Series Forecasting
Dilfira Kudrat, Zongxia Xie, Yanru Sun +2
Time-series forecasting has gained significant attention in machine learning due to its crucial role in various domains. However, most existing forecasting models rely heavily on p…
Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift
Yanru Sun, Zongxia Xie, Emadeldeen Eldele +3
Time series forecasting, which aims to predict future values based on historical data, has garnered significant attention due to its broad range of applications. However, real-worl…
Fine-Grained Domain Generalization with Feature Structuralization
Wenlong Yu, Dongyue Chen, Qilong Wang +1
Fine-grained domain generalization (FGDG) is a more challenging task than traditional DG tasks due to its small inter-class variations and relatively large intra-class disparities.…
Hierarchical Classification Auxiliary Network for Time Series Forecasting
Yanru Sun, Zongxia Xie, Dongyue Chen +2
Deep learning has significantly advanced time series forecasting through its powerful capacity to capture sequence relationships. However, training these models with the Mean Squar…