5 papers
MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents
Shuyue Wei, Chang Liu, Zimu Zhou +2
Recently, memory management has become a key infrastructure for LLM-based agents, as it directly affects long-horizon reasoning, personalized responses, and knowledge reuse. Howeve…
FedMosaic: Federated Retrieval-Augmented Generation via Parametric Adapters
Zhilin Liang, Yuxiang Wang, Zimu Zhou +3
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding generation in external knowledge to improve factuality and reduce hallucinations. Yet most d…
CAFEDistill: Learning Personalized and Dynamic Models through Federated Early-Exit Network Distillation
Boyi Liu, Zimu Zhou, Yongxin Tong
Personalized Federated Learning (PFL) enables collaboratively model training on decentralized, heterogeneous data while tailoring them to each client's unique distribution. However…
Accurate and Efficient Multivariate Time Series Forecasting via Offline Clustering
Yiming Niu, Jinliang Deng, Lulu Zhang +2
Accurate and efficient multivariate time series (MTS) forecasting is essential for applications such as traffic management and weather prediction, which depend on capturing long-ra…
Efficient Data Valuation Approximation in Federated Learning: A Sampling-based Approach
Shuyue Wei, Yongxin Tong, Zimu Zhou +2
Federated learning paradigm to utilize datasets across multiple data providers. In FL, cross-silo data providers often hesitate to share their high-quality dataset unless their dat…