3 citations · 6 across the 17 of their papers we have counts for
18 papers
GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs
Junjie Li, Jiong Lou, Jie Li
Hybrid language models interleave Gated DeltaNet (GDN) layers, whose recurrent memory has a fixed size, with full-attention layers, whose key-value (KV) cache grows with the contex…
HeraSys: Collaborative Serving of Multiple LLM Workflows via Fine-Grained End-to-End Optimization
Size Li, Zhiqing Tang, Hongrui Liang +4
The proliferation of Large Language Models (LLMs) has shifted serving systems from processing isolated requests to orchestrating high-concurrency, multi-tenant agentic workflows. H…
IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference
Junjie Li, Jiong Lou, Jie Li
Multi-turn LLM agents fan short queries into long trajectories of tool calls, search results, and intermediate reasoning. Both KV memory and KV read bandwidth grow by orders of mag…
OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
Kaixiang Wang, Jiong Lou, Zhaojiacheng Zhou +1
Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks. Existing agent…
ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference
Junjie Li, Jiong Lou, Jie Li
Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Value (KV) cache memory wall, yet existing pruning methods force a choice betwee…
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…
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…
Adaptive AI Agent Placement and Migration in Edge Intelligence Systems
Xingdan Wang, Jiayi He, Zhiqing Tang +5
The rise of LLMs such as ChatGPT and Claude fuels the need for AI agents capable of real-time task handling. However, migrating data-intensive, multi-modal edge workloads to cloud…
EAT: QoS-Aware Edge-Collaborative AIGC Task Scheduling via Attention-Guided Diffusion Reinforcement Learning
Zhifei Xu, Zhiqing Tang, Jiong Lou +5
The growth of Artificial Intelligence (AI) and large language models has enabled the use of Generative AI (GenAI) in cloud data centers for diverse AI-Generated Content (AIGC) task…
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…
LRScheduler: A Layer-aware and Resource-adaptive Container Scheduler in Edge Computing
Zhiqing Tang, Wentao Peng, Jianxiong Guo +5
Lightweight containers provide an efficient approach for deploying computation-intensive applications in network edge. The layered storage structure of container images can further…
Low-Latency Layer-Aware Proactive and Passive Container Migration in Meta Computing
Mengjie Liu, Yihua Li, Fangyi Mou +4
Meta computing is a new computing paradigm that aims to efficiently utilize all network computing resources to provide fault-tolerant, personalized services with strong security an…
VELO: A Vector Database-Assisted Cloud-Edge Collaborative LLM QoS Optimization Framework
Zhi Yao, Zhiqing Tang, Jiong Lou +2
The Large Language Model (LLM) has gained significant popularity and is extensively utilized across various domains. Most LLM deployments occur within cloud data centers, where the…
Robust and Communication-Efficient Federated Domain Adaptation via Random Features
Zhanbo Feng, Yuanjie Wang, Jie Li +5
Modern machine learning (ML) models have grown to a scale where training them on a single machine becomes impractical. As a result, there is a growing trend to leverage federated l…
Efficient Serverless Function Scheduling at the Network Edge
Jiong Lou, Zhiqing Tang, Shijing Yuan +3
Serverless computing is a promising approach for edge computing since its inherent features, e.g., lightweight virtualization, rapid scalability, and economic efficiency. However,…
Joint Task Scheduling and Container Image Caching in Edge Computing
Fangyi Mou, Zhiqing Tang, Jiong Lou +3
In Edge Computing (EC), containers have been increasingly used to deploy applications to provide mobile users services. Each container must run based on a container image file that…
Online Container Scheduling for Low-Latency IoT Services in Edge Cluster Upgrade: A Reinforcement Learning Approach
Hanshuai Cui, Zhiqing Tang, Jiong Lou +1
In Mobile Edge Computing (MEC), Internet of Things (IoT) devices offload computationally-intensive tasks to edge nodes, where they are executed within containers, reducing the reli…