# Learning Transient Convective Heat Transfer with Geometry Aware World Models

arXiv: https://arxiv.org/abs/2601.22086 · HTML: https://mlsanity.com/paper/2601.22086/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 12 of 12)

- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [CFDBench: A Large-Scale Benchmark for Machine Learning Methods in Fluid Dynamics](https://mlsanity.com/paper/2310.05963/) (2023)
- [X-MeshGraphNet: Scalable Multi-Scale Graph Neural Networks for Physics Simulation](https://mlsanity.com/paper/2411.17164/) (2024)
- [TI-DeepONet: Learnable Time Integration for Stable Long-Term Extrapolation](https://mlsanity.com/paper/2505.17341/) (2025)
- [MeshMask: Physics-Based Simulations with Masked Graph Neural Networks](https://mlsanity.com/paper/2501.08738/) (2025)
- [A Curriculum-Training-Based Strategy for Distributing Collocation Points during Physics-Informed Neural Network Training](https://mlsanity.com/paper/2211.11396/) (2022)
- [Generalization capabilities of conditional GAN for turbulent flow under changes of geometry](https://mlsanity.com/paper/2302.09945/) (2023)
- [Generalization capabilities of MeshGraphNets to unseen geometries for fluid dynamics](https://mlsanity.com/paper/2408.06101/) (2024)
- [When do World Models Successfully Learn Dynamical Systems?](https://mlsanity.com/paper/2507.04898/) (2025)
- [Comparison of Generative Learning Methods for Turbulence Surrogates](https://mlsanity.com/paper/2411.16417/) (2024)
- [Multi-Stage Graph Neural Networks for Data-Driven Prediction of Natural Convection in Enclosed Cavities](https://mlsanity.com/paper/2509.06041/) (2025)

## Built on by (most cited first, 1 of 1)

- [Generative Adversarial Learning from Deterministic Processes](https://mlsanity.com/paper/2605.18425/) (2026)

## Abstract (arXiv)

Partial differential equation (PDE) simulations are fundamental to engineering and physics but are often computationally prohibitive for real-time applications. While generative AI offers a promising avenue for surrogate modeling, standard video generation architectures lack the specific control and data compatibility required for physical simulations. This paper introduces a geometry aware world model architecture, derived from a video generation architecture (LongVideoGAN), designed to learn transient physics. We introduce two key architecture elements: (1) a twofold conditioning mechanism incorporating global physical parameters and local geometric masks, and (2) an architectural adaptation to support arbitrary channel dimensions, moving beyond standard RGB constraints. We evaluate this approach on a 2D transient computational fluid dynamics (CFD) problem involving convective heat transfer from buoyancy-driven flow coupled to a heat flow in a solid structure. We demonstrate that the conditioned model successfully reproduces complex temporal dynamics and spatial correlations of the training data. Furthermore, we assess the model's generalization capabilities on unseen geometric configurations, highlighting both its potential for controlled simulation synthesis and current limitations in spatial precision for out-of-distribution samples.