11 papers
AquaSentinel: Next-Generation AI System Integrating Sensor Networks for Urban Underground Water Pipeline Anomaly Detection via Collaborative MoE-LLM Agent Architecture
Qiming Guo, Bishal Khatri, Wenbo Sun +3
Underground pipeline leaks and infiltrations pose significant threats to water security and environmental safety. Traditional manual inspection methods provide limited coverage and…
Spatio-Temporal Graph Unlearning
Qiming Guo, Wenbo Sun, Wenlu Wang
Spatio-temporal graphs are widely used in modeling complex dynamic processes such as traffic forecasting, molecular dynamics, and healthcare monitoring. Recently, stringent privacy…
AI-Driven Forecasting and Monitoring of Urban Water System
Qiming Guo, Bishal Khatri, Hua Zhang +1
Underground water and wastewater pipelines are vital for city operations but plagued by anomalies like leaks and infiltrations, causing substantial water loss, environmental damage…
TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardware
Wenbo Sun, Qiming Guo, Wenlu Wang +1
Deploying Large Language Models (LLMs) on resource-constrained devices remains challenging due to limited memory, lack of GPUs, and the complexity of existing runtimes. In this pap…
CEBench: A Benchmarking Toolkit for the Cost-Effectiveness of LLM Pipelines
Wenbo Sun, Jiaqi Wang, Qiming Guo +3
Online Large Language Model (LLM) services such as ChatGPT and Claude 3 have transformed business operations and academic research by effortlessly enabling new opportunities. Howev…
A Layered Multi-Expert Framework for Long-Context Mental Health Assessments
Jinwen Tang, Qiming Guo, Wenbo Sun +1
Long-form mental health assessments pose unique challenges for large language models (LLMs), which often exhibit hallucinations or inconsistent reasoning when handling extended, do…