# Forward Prediction for Physical Reasoning

arXiv: https://arxiv.org/abs/2006.10734 · HTML: https://mlsanity.com/paper/2006.10734/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2020.

## Built on by (most cited first, 18 of 18)

- [How Far is Video Generation from World Model: A Physical Law Perspective](https://mlsanity.com/paper/2411.02385/) (2024)
- [Physion: Evaluating Physical Prediction from Vision in Humans and Machines](https://mlsanity.com/paper/2106.08261/) (2021)
- [SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models](https://mlsanity.com/paper/2210.05861/) (2022)
- [Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos](https://mlsanity.com/paper/2204.01696/) (2022)
- [I-PHYRE: Interactive Physical Reasoning](https://mlsanity.com/paper/2312.03009/) (2023)
- [3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes](https://mlsanity.com/paper/2304.11470/) (2023)
- [On the Learning Mechanisms in Physical Reasoning](https://mlsanity.com/paper/2210.02075/) (2022)
- [Phy-Q as a measure for physical reasoning intelligence](https://mlsanity.com/paper/2108.13696/) (2021)
- [VLMgineer: Vision Language Models as Robotic Toolsmiths](https://mlsanity.com/paper/2507.12644/) (2025)
- [Benchmarks for Physical Reasoning AI](https://mlsanity.com/paper/2312.10728/) (2023)
- [Learning to Design and Use Tools for Robotic Manipulation](https://mlsanity.com/paper/2311.00754/) (2023)
- [Physical Reasoning Using Dynamics-Aware Models](https://mlsanity.com/paper/2102.10336/) (2021)
- [DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Rendering](https://mlsanity.com/paper/2410.08983/) (2024)
- [Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel](https://mlsanity.com/paper/2505.22861/) (2025)
- [Learning to reason about and to act on physical cascading events](https://mlsanity.com/paper/2202.01108/) (2022)
- [RoboGolf: Mastering Real-World Minigolf with a Reflective Multi-Modality Vision-Language Model](https://mlsanity.com/paper/2406.10157/) (2024)
- [Object-centric Denoising Diffusion Models for Physical Reasoning](https://mlsanity.com/paper/2507.04920/) (2025)
- [Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment](https://mlsanity.com/paper/2607.06522/) (2026)

## Abstract (arXiv)

Physical reasoning requires forward prediction: the ability to forecast what will happen next given some initial world state. We study the performance of state-of-the-art forward-prediction models in the complex physical-reasoning tasks of the PHYRE benchmark. We do so by incorporating models that operate on object or pixel-based representations of the world into simple physical-reasoning agents. We find that forward-prediction models can improve physical-reasoning performance, particularly on complex tasks that involve many objects. However, we also find that these improvements are contingent on the test tasks being small variations of train tasks, and that generalization to completely new task templates is challenging. Surprisingly, we observe that forward predictors with better pixel accuracy do not necessarily lead to better physical-reasoning performance.Nevertheless, our best models set a new state-of-the-art on the PHYRE benchmark.