activity
20242026
collaborators

9 papers

cs.AI2026

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…

cs.CV2026

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…

cs.NI2026

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…

cs.CY2025

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…

cs.LG2025

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…

cs.DC2025

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…