4 papers
BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation
Xuan Li, Yining Wang, Haocai Luo +6
Retrieval-Augmented Generation (RAG) has become a pivotal paradigm for Large Language Models (LLMs), yet current approaches struggle with visually rich documents by treating text a…
CATS-Linear: Classification Auxiliary Linear Model for Time Series Forecasting
Zipo Jibao, Yingyi Fu, Xinyang Chen +1
Recent research demonstrates that linear models achieve forecasting performance competitive with complex architectures, yet methodologies for enhancing linear models remain underex…
Inner-Instance Normalization for Time Series Forecasting
Zipo Jibao, Yingyi Fu, Xinyang Chen +1
Real-world time series are influenced by numerous factors and exhibit complex non-stationary characteristics. Non-stationarity can lead to distribution shifts, where the statistica…
General LLMs as Instructors for Domain-Specific LLMs: A Sequential Fusion Method to Integrate Extraction and Editing
Xin Zhang, Tianjie Ju, Huijia Liang +2
The substantial interest in updating Large Language Models (LLMs) without retraining from scratch is accompanied by several challenges. This is particularly true when updating LLMs…