# Video Prediction of Dynamic Physical Simulations With Pixel-Space Spatiotemporal Transformers

arXiv: https://arxiv.org/abs/2510.20807 · HTML: https://mlsanity.com/paper/2510.20807/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 55 of its 64 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 30 of 55)

- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [MAGVIT: Masked Generative Video Transformer](https://mlsanity.com/paper/2212.05199/) (2022)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Text-to-image Diffusion Models in Generative AI: A Survey](https://mlsanity.com/paper/2303.07909/) (2023)
- [Unsupervised Learning for Physical Interaction through Video Prediction](https://mlsanity.com/paper/1605.07157/) (2016)
- [N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion](https://mlsanity.com/paper/2111.12417/) (2021)
- [Large Scale Adversarial Representation Learning](https://mlsanity.com/paper/1907.02544/) (2019)
- [Generating Images with Perceptual Similarity Metrics based on Deep Networks](https://mlsanity.com/paper/1602.02644/) (2016)

## Abstract (arXiv)

Inspired by the performance and scalability of autoregressive large language models (LLMs), transformer-based models have seen recent success in the visual domain. This study investigates a transformer adaptation for video prediction with a simple end-to-end approach, comparing various spatiotemporal self-attention layouts. Focusing on causal modeling of physical simulations over time; a common shortcoming of existing video-generative approaches, we attempt to isolate spatiotemporal reasoning via physical object tracking metrics and unsupervised training on physical simulation datasets. We introduce a simple yet effective pure transformer model for autoregressive video prediction, utilizing continuous pixel-space representations for video prediction. Without the need for complex training strategies or latent feature-learning components, our approach significantly extends the time horizon for physically accurate predictions by up to 50% when compared with existing latent-space approaches, while maintaining comparable performance on common video quality metrics. In addition, we conduct interpretability experiments to identify network regions that encode information useful to perform accurate estimations of PDE simulation parameters via probing models, and find that this generalizes to the estimation of out-of-distribution simulation parameters. This work serves as a platform for further attention-based spatiotemporal modeling of videos via a simple, parameter efficient, and interpretable approach.