# Extracting Actionable Insights from Building Energy Data using Vision LLMs on Wavelet and 3D Recurrence Representations

arXiv: https://arxiv.org/abs/2509.21934 · HTML: https://mlsanity.com/paper/2509.21934/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 33 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks](https://mlsanity.com/paper/2007.01204/) (2020)
- [TnT-LLM: Text Mining at Scale with Large Language Models](https://mlsanity.com/paper/2403.12173/) (2024)
- [A-VL: Adaptive Attention for Large Vision-Language Models](https://mlsanity.com/paper/2409.14846/) (2024)
- [Advancing Building Energy Modeling with Large Language Models: Exploration and Case Studies](https://mlsanity.com/paper/2402.09579/) (2024)

## Built on by (most cited first, 2 of 2)

- [AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning](https://mlsanity.com/paper/2602.13807/) (2026)
- [An Agentic AI Pipeline for Appliance-Level Energy Anomaly Detection and LLM-Driven Recommendations](https://mlsanity.com/paper/2606.28467/) (2026)

## Abstract (arXiv)

The analysis of complex building time-series for actionable insights and recommendations remains challenging due to the nonlinear and multi-scale characteristics of energy data. To address this, we propose a framework that fine-tunes visual language large models (VLLMs) on 3D graphical representations of the data. The approach converts 1D time-series into 3D representations using continuous wavelet transforms (CWTs) and recurrence plots (RPs), which capture temporal dynamics and localize frequency anomalies. These 3D encodings enable VLLMs to visually interpret energy-consumption patterns, detect anomalies, and provide recommendations for energy efficiency. We demonstrate the framework on real-world building-energy datasets, where fine-tuned VLLMs successfully monitor building states, identify recurring anomalies, and generate optimization recommendations. Quantitatively, the Idefics-7B VLLM achieves validation losses of 0.0952 with CWTs and 0.1064 with RPs on the University of Sharjah energy dataset, outperforming direct fine-tuning on raw time-series data (0.1176) for anomaly detection. This work bridges time-series analysis and visualization, providing a scalable and interpretable framework for energy analytics.