# Ask for Any Appliance: A Prompt-Programmable Foundation Model for Non-Intrusive Load Monitoring

arXiv: https://arxiv.org/abs/2609.23146 · HTML: https://mlsanity.com/paper/2609.23146/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 19 Sep 2026.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [Neural NILM: Deep Neural Networks Applied to Energy Disaggregation](https://mlsanity.com/paper/1507.06594/) (2015)
- [Subtask Gated Networks for Non-Intrusive Load Monitoring](https://mlsanity.com/paper/1811.06692/) (2018)
- [SoundBeam: Target sound extraction conditioned on sound-class labels and enrollment clues for increased performance and continuous learning](https://mlsanity.com/paper/2204.03895/) (2022)
- [TLINet: Differentiable Neural Network Temporal Logic Inference](https://mlsanity.com/paper/2405.06670/) (2024)
- [Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries](https://mlsanity.com/paper/2507.16343/) (2025)
- [MSDC: Exploiting Multi-State Power Consumption in Non-intrusive Load Monitoring based on A Dual-CNN Model](https://mlsanity.com/paper/2302.05565/) (2023)
- [Efficient Localness Transformer for Smart Sensor-Based Energy Disaggregation](https://mlsanity.com/paper/2203.16537/) (2022)
- [NILMFormer: Non-Intrusive Load Monitoring that Accounts for Non-Stationarity](https://mlsanity.com/paper/2506.05880/) (2025)
- [Prompting Large Language Models for Training-Free Non-Intrusive Load Monitoring](https://mlsanity.com/paper/2505.06330/) (2025)
- [Non-Intrusive Load Monitoring Based on Image Load Signatures and Continual Learning](https://mlsanity.com/paper/2506.06637/) (2025)
- [Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning](https://mlsanity.com/paper/2508.14600/) (2025)
- [Lightweight and Scalable Transfer Learning Framework for Load Disaggregation](https://mlsanity.com/paper/2603.04998/) (2026)

## Abstract (arXiv)

Non-intrusive load monitoring (NILM) estimates appliance-level consumption from a whole-home meter, but appliance-specific models and fixed output inventories make coverage costly to extend. We present FM4NILM (Foundation Model for NILM), a single prompt-programmable model that estimates a requested appliance's power trajectory from aggregate measurements, a natural-language description, and optional activation exemplars. A lightweight cadence-aware transformer is pretrained by masked reconstruction on 645k sequences from seven public corpora spanning 1-60 s sampling intervals, then aligned with appliance requests using observation-masked losses for partially labeled households. A Bernoulli-lognormal decoder separates activity detection from conditional power estimation. On held-out households and time periods from REDD, UK-DALE, and REFIT, one frozen text-prompted model serves twelve appliance-corpus requests, achieving 0.556 event F1, 0.625 AUPRC, and the lowest active-window MAE (251.8 W) among seven appliance-specific baselines. Streaming score aggregation raises event F1 to 0.582 with a 60 s aggregation delay. In a separate category-held-out evaluation, adding ten activation exemplars raises microwave AUPRC from 0.132 to 0.214 without parameter updates. Input-intervention ablations probe the model's dependence on appliance requests and aggregate measurements. These results demonstrate competitive disaggregation with one shared model and support extending appliance coverage through prompts and examples rather than additional specialist networks.