papers

Publications (12)

cs.LG2026

MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with 0.1K Parameters

Aitian Ma, Dongsheng Luo, Mo Sha

Recently, there has been a growing interest in Long-term Time Series Forecasting (LTSF), which involves predicting long-term future values by analyzing a large amount of historical…

cs.NI2016

An Internet of Things Framework for Smart Energy in Buildings: Designs, Prototype, and Experiments

Jianli Pan, Raj Jain, Subharthi Paul +3

Smart energy in buildings is an important research area of Internet of Things (IoT). Buildings as important parts of the smart grids, their energy efficiency is vital for the envir…

physics.chem-ph2025

Exponential convergence of the local diabatic representation for nonadiabatic models

Mo Sha, Bing Gu

The discrete variable local diabatic representation (LDR) provides a divergence-free framework for exact conical intersection dynamics simulation. In this work, we investigate the…

cs.AI2026

DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL

Esteban Schafir, Xu Zheng, Hojat Allah Salehi +4

Large Language Models (LLMs) have demonstrated remarkable capabilities in translating natural language to SQL, yet existing methods still falter on complex queries requiring multi-…

cs.DB2026

Why Database Manuals Are Not Enough: Efficient and Reliable Configuration Tuning for DBMSs via Code-Driven LLM Agents

Xinyi Zhang, Tiantian Chen, Zhentao Han +9

Modern database management systems (DBMSs) expose hundreds of configuration knobs that critically influence performance. Existing automated tuning methods either adopt a data-drive…

cs.LG2024

Parametric Augmentation for Time Series Contrastive Learning

Xu Zheng, Tianchun Wang, Wei Cheng +4

Modern techniques like contrastive learning have been effectively used in many areas, including computer vision, natural language processing, and graph-structured data. Creating po…

cs.CR2025

Femur: A Flexible Framework for Fast and Secure Querying from Public Key-Value Store

Jiaoyi Zhang, Liqiang Peng, Mo Sha +6

With increasing demands for privacy, it becomes necessary to protect sensitive user query data when accessing public key-value databases. Existing Private Information Retrieval (PI…

cs.DS2018

Technical Report: Accelerating Dynamic Graph Analytics on GPUs

Mo Sha, Yuchen Li, Bingsheng He +1

As graph analytics often involves compute-intensive operations, GPUs have been extensively used to accelerate the processing. However, in many applications such as social networks,…

cs.LG2026

Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

Xu Zheng, Wei Cheng, Zhuomin Chen +3

The paper presents IB-Forecast, an interpretable multivariate time-series forecasting model that uses an information bottleneck to generate sparse, faithful explanations of predict…

#time series forecasting#interpretability#information bottleneck#explainable AI
physics.chem-ph2026

Coarse-Grained Geometric Quantum Dynamics in the Tensor Network Representation

Mo Sha, Bing Gu

Quantum geometrical molecular dynamics provides a quantum geometric picture for understanding reactive dynamics, especially excited-state conical intersection dynamics, and also a…

cs.CL2025

Towards Structurally Explainable Machine-Generated Text Detection: A Graph-Perspective Framework

Xu Zheng, Zhuomin Chen, Esteban Schafir +7

Despite the success of machine-generated text detectors, the black-box nature remains a critical limitation. Traditional explainability methods rely on token-level saliency, insuff…

cs.LG2024

MMFNet: Multi-Scale Frequency Masking Neural Network for Multivariate Time Series Forecasting

Aitian Ma, Dongsheng Luo, Mo Sha

Long-term Time Series Forecasting (LTSF) is critical for numerous real-world applications, such as electricity consumption planning, financial forecasting, and disease propagation…