Xudong Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xudong Wang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Guoming Tang
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
3 shared publications - Junyu Xue
Southern University of Science and Technology, Shenzhen, Guangdong, China
3 shared publications - Shicheng Liu
Tsinghua University, Beijing, China
2 shared publications - Tongxin Li
The Chinese University of Hong Kong, Shenzhen, Shenzhen, Guangdong, China
2 shared publications - Yi Wang
Southern University of Science and Technology
2 shared publications - Chris Ding
The Chinese University of Hong Kong
1 shared publication
Latest Publications
- Open Access
- 5 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
Capability and Explanation Boundaries of Large Language Models for Non-Intrusive Load Monitoring
Non-intrusive load monitoring (NILM) aims to disaggregate total electricity consumption into individual appliance usage. Although deep learning has advanced NILM, it remains limited by its dependence on labeled data, restricted generalization, and lack of explainability. This paper introduces a prompt-based NILM framework that uses large language models (LLMs) with in-context learning. We integrate appliance features, contextual history, and one-shot examples into a unified prompting strategy and evaluate it on the REDD and UK-DALE datasets. Prompt-only LLMs deliver basic NILM capability but lag behind specialized deep learning models in accuracy, while achieving zero-shot generalization across houses and regions by adapting the injected appliance features. To characterize the unique value of LLMs for NILM, we propose a three-layer faithfulness framework that evaluates LLM-generated explanations along factual validity, internal coherence, and external correctness. The framework reveals a traceable-but-misaligned pattern in which LLMs often cite numerical values supported by the input but fail to align the cited events with true appliance activity. Rather than replacing specialized models, LLMs are better positioned as a semantic interface for energy disaggregation. We release our framework to support follow-up research.
- 5 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
Open AccessCapability and Explanation Boundaries of Large Language Models for Non-Intrusive Load Monitoring
Non-intrusive load monitoring (NILM) aims to disaggregate total electricity consumption into individual appliance usage. Although deep learning has advanced NILM, it remains limited by its dependence on labeled data, restricted generalization, and lack of explainability. This paper introduces a prompt-based NILM framework that uses large language models (LLMs) with in-context learning. We integrate appliance features, contextual history, and one-shot examples into a unified prompting strategy and evaluate it on the REDD and UK-DALE datasets. Prompt-only LLMs deliver basic NILM capability but lag behind specialized deep learning models in accuracy, while achieving zero-shot generalization across houses and regions by adapting the injected appliance features. To characterize the unique value of LLMs for NILM, we propose a three-layer faithfulness framework that evaluates LLM-generated explanations along factual validity, internal coherence, and external correctness. The framework reveals a traceable-but-misaligned pattern in which LLMs often cite numerical values supported by the input but fail to align the cited events with true appliance activity. Rather than replacing specialized models, LLMs are better positioned as a semantic interface for energy disaggregation. We release our framework to support follow-up research.
- Open Access
- 22 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 89-119
Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning
- 22 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 89-119
Open AccessEnergy Injection Identification enabled Disaggregation with Deep Multi-Task Learning
- Open Access
- 11 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 34-44
Prompting Large Language Models for Training-Free Non-Intrusive Load Monitoring
- 11 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 34-44
Open AccessPrompting Large Language Models for Training-Free Non-Intrusive Load Monitoring
- Open Access
- 16 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 985-986
Open In-Context Energy Management Platform
- 16 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 985-986
Open AccessOpen In-Context Energy Management Platform