9 papers
Akashic: A Low-Overhead LLM Inference Service with MemAttention
Yang Liu, Zhaokai Luo, Huayi Jin +7
Recent LLM-based agent systems continuously accumulate context across multi-turn interactions, tool invocations, and cross-session workflows. Replaying the full history for every r…
Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization
Hefeng Zhou, Xuan Liu, Sicheng Chen +7
Federated cross-modal retrieval faces severe challenges from heterogeneous client data, particularly non-IID semantic distributions and missing modalities. Under such heterogeneity…
IEMAS: An Incentive-Efficiency Routing Framework for Open Agentic Web Ecosystems
Hongze Liu, Chang Guo, Yingzeng Li +6
The transition to open, distributed Multi-Agent Systems (MAS) promises scalable intelligence but introduces a non-trivial tension: maximizing global efficiency requires cooperative…
AgentTutor: Empowering Personalized Learning with Multi-Turn Interactive Teaching in Intelligent Education Systems
Yuxin Liu, Zeqing Song, Jiong Lou +2
The rapid advancement of large-scale language models (LLMs) has shown their potential to transform intelligent education systems (IESs) through automated teaching and learning supp…
BAPFL: Exploring Backdoor Attacks Against Prototype-based Federated Learning
Honghong Zeng, Jiong Lou, Zhe Wang +4
Prototype-based federated learning (PFL) has emerged as a promising paradigm to address data heterogeneity problems in federated learning, as it leverages mean feature vectors as p…
PS-WL: A Probability-Sensitive Wear Leveling scheme for SSD array scaling
Shuhang Xu, Yunfei Gu, Linhui Liu +1
As flash-based Solid State Drive (SSD) arrays become essential to modern data centers, scaling these arrays to meet explosive data growth is a frequent and critical operation. Howe…
BLOCKS: Blockchain-supported Cross-Silo Knowledge Sharing for Efficient LLM Services
Zhaojiacheng Zhou, Hongze Liu, Shijing Yuan +4
The hallucination problem of Large Language Models (LLMs) has increasingly drawn attention. Augmenting LLMs with external knowledge is a promising solution to address this issue. H…
STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support
Chenqi Zhang, Yu Feng, Jieru Zhao +4
3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 fram…
Gaze into the Pattern: Characterizing Spatial Patterns with Internal Temporal Correlations for Hardware Prefetching
Zixiao Chen, Chentao Wu, Yunfei Gu +3
Hardware prefetching is one of the most widely-used techniques for hiding long data access latency. To address the challenges faced by hardware prefetching, architects have propose…