# Thermal-GEMs: Generalized Models for Building Thermal Dynamics

arXiv: https://arxiv.org/abs/2604.16443 · HTML: https://mlsanity.com/paper/2604.16443/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 50 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series](https://mlsanity.com/paper/2401.03955/) (2024)
- [Is Mamba Effective for Time Series Forecasting?](https://mlsanity.com/paper/2403.11144/) (2024)
- [This Time is Different: An Observability Perspective on Time Series Foundation Models](https://mlsanity.com/paper/2505.14766/) (2025)
- [GenTL: A General Transfer Learning Model for Building Thermal Dynamics](https://mlsanity.com/paper/2501.13703/) (2025)
- [Adapting to Change: A Comparison of Continual and Transfer Learning for Modeling Building Thermal Dynamics under Concept Drifts](https://mlsanity.com/paper/2508.21615/) (2025)
- [Transformer Training Strategies for Forecasting Multiple Load Time Series](https://mlsanity.com/paper/2306.10891/) (2023)
- [Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models](https://mlsanity.com/paper/2506.00630/) (2025)
- [A Highly Configurable Framework for Large-Scale Thermal Building Data Generation to drive Machine Learning Research](https://mlsanity.com/paper/2512.00483/) (2025)

## Built on by (most cited first, 3 of 3)

- [BuilDyn: Excitation-Driven Data Generation for Building Thermal Dynamics Modeling and Control](https://mlsanity.com/paper/2605.29849/) (2026)
- [Systematic Evaluation of TabPFN-TS and Chronos-2 for Zero-Shot Heat Load Forecasting in District Heating Networks](https://mlsanity.com/paper/2608.20024/) (2026)
- [Very Exciting: Zero-Shot Model Predictive Control of Buildings via Excitation-Based Generalized Transfer Learning Models](https://mlsanity.com/paper/2609.12853/) (2026)

## Abstract (arXiv)

Data-driven models for building thermal dynamics are a scalable approach for enabling energy-efficient operation through fault detection & diagnosis or advanced control. To obtain accurate models, measurement data from a target building spanning months to years are required. Transfer Learning (TL) mitigates this challenge by employing pretrained models based on single or multiple source buildings. General multi-source TL models promise to outperform single-source TL, but alternative multi-source modeling architectures remain to be explored, and evaluation on real-world data is missing. Moreover, time series foundation models (TSFM) have emerged as candidates for the best-performing general models. Hence, we conduct a first, comprehensive assessment of general modeling approaches for building thermal dynamics, including multi-source TL and TSFMs. Our assessment includes ablations using four state-of-the-art multi-source TL architectures and evaluations on synthetic as well as real-world data. We demonstrate that multi-source TL models are highly effective in accurately modeling buildings in real-world applications, yielding up to 63% lower forecasting errors compared to single-source TL. Moreover, our results suggest a trade-off between multi-source TL models exclusively pretrained with building data and TSFMs pretrained with a multitude of different time series, revealing that data from 16-32 source buildings must be available over 1 year for pretraining multi-source TL models to consistently outperform TSFMs as evaluated using the mean absolute error. These findings provide practical guidance for selecting modeling strategies based on the number of source buildings available for pretraining multi-source TL models.