Federated Learning (FL) enables collaborative model training across mobile and edge devices without sharing raw data, but its deployment is hindered by <italic>system heterogeneity</italic> and <italic>non-IID</italic> data. Existing FL methods either require homogeneous architectures or suffer from accuracy loss and h...
Tong Liu, Feng Lyu, Shucheng Li et al.· IEEE Transactions on Mobile...· 0 citations
Deploying large language models (LLMs) on resource-constrained mobile devices remains a significant challenge due to memory limitations and high I/O overhead. While existing dynamic sparsity methods reduce computation costs, they often suffer from inefficient loading patterns that degrade I/O throughput. To address thi...
Wei-Ning Chen, Yong-Heng Deng, Xiang Wang et al.· IEEE Transactions on Mobile...· 0 citations
This work proposes Threader, a memory system that shifts the focus from memory construction to efficient, structure-aware access over raw interactions, and preserves them as first-class memory, organizes them into topic-coherent segments via lightweight incremental segmentation, and enables accurate retrieval through m...
Dong-Hua Cai, Yong-Heng Deng, Yi-Fei Wang et al.· 0 citations
This paper proposes Lever, a locality-aware collaborative retrieval framework that exploits query locality to accelerate graph-based RAG retrieval, and identifies and empirically validate a previously underexplored property of RAG workloads: strong per-user query locality.
Yong-Heng Deng, Tianyuan Jiang, Zhen-Ya Ma et al.· Proceedings of the 32nd ACM...· 0 citations
PersMem is proposed, a user profile memory framework for LLM personalization that addresses three key questions: what user information to store, how to organize it, and how to use it effectively during generation that consistently improves personalization effectiveness while reducing prompt length.
Yang-Xu Liao, Yong-Heng Deng, Tianyuan Jiang et al.· Proceedings of the 32nd ACM...· 0 citations
Retrieval-Augmented Generation (RAG) grounds large language models in external knowledge and has become a key technique for knowledge-intensive tasks. As knowledge bases continue to scale, however, the retrieval stage increasingly dominates end-to-end latency, limiting the responsiveness of RAG systems. In this paper,...
Yongheng Deng, Tianyuan Jiang, Zhenya Ma et al.· Proceedings of the 32nd ACM...· 0 citations
PersMem is proposed, a user profile memory framework for LLM personalization that addresses three key questions: what user information to store, how to organize it, and how to use it effectively during generation that consistently improves personalization effectiveness while reducing prompt length.
Yang-Xu Liao, Yongheng Deng, Tianyuan Jiang et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
