# A single AI model simulates the behavior of many substances, from sliding sand to folding proteins

DevFeed: [A single AI model simulates the behavior of many substances, from sliding sand to folding proteins](<https://devfeed.tech/articles/a-single-ai-model-simulates-the-behavior-of-many-substances-from-sliding-sand-to-folding-proteins-124742.md>)

Original publisher: [Read original article](<https://news.mit.edu/2026/single-ai-model-simulates-many-substances-behavior-1109>)

Author: Adam Zewe | MIT News

Published: 2026-11-09T05:00:00Z

Content type: news

Language: en

Sources: [MIT AI News](<https://devfeed.tech/sources/mit-ai-news.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [model architecture](<https://devfeed.tech/topics/model-architecture.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-architecture](<https://devfeed.tech/tags/ai-architecture.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [computer-graphics](<https://devfeed.tech/tags/computer-graphics.md>), [computer-modeling](<https://devfeed.tech/tags/computer-modeling.md>), [computer-science-and-artificial-intelligence-laboratory-csail](<https://devfeed.tech/tags/computer-science-and-artificial-intelligence-laboratory-csail.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [design](<https://devfeed.tech/tags/design.md>), [electrical-engineering-and-computer-science-eecs](<https://devfeed.tech/tags/electrical-engineering-and-computer-science-eecs.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [faster](<https://devfeed.tech/tags/faster.md>), [fluid](<https://devfeed.tech/tags/fluid.md>), [folding](<https://devfeed.tech/tags/folding.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [framework](<https://devfeed.tech/tags/framework.md>), [human-computer-interaction](<https://devfeed.tech/tags/human-computer-interaction.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [matter](<https://devfeed.tech/tags/matter.md>), [minghao-guo](<https://devfeed.tech/tags/minghao-guo.md>), [mit-schwarzman-college-of-computing](<https://devfeed.tech/tags/mit-schwarzman-college-of-computing.md>), [model](<https://devfeed.tech/tags/model.md>), [peter-yichen-chen](<https://devfeed.tech/tags/peter-yichen-chen.md>), [proteins](<https://devfeed.tech/tags/proteins.md>), [research](<https://devfeed.tech/tags/research.md>), [robots](<https://devfeed.tech/tags/robots.md>), [school-of-engineering](<https://devfeed.tech/tags/school-of-engineering.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [system](<https://devfeed.tech/tags/system.md>), [wojciech-matusik](<https://devfeed.tech/tags/wojciech-matusik.md>), [world-models](<https://devfeed.tech/tags/world-models.md>), [worldparticle](<https://devfeed.tech/tags/worldparticle.md>)

## AI overview

WorldParticle is a deep-learning system that models varied physical phenomena by representing materials as particles and predicting their positions and properties one step at a time. Unlike separate hand-coded simulators built around equations for each process, its neural network learns dynamics across materials and integrates external forces into its predictions, aiming to handle unfamiliar materials and conditions. The researchers demonstrated it on six phenomena, including deformable objects, granular materials, and proteins; they report higher accuracy than numerical simulation methods and protein structure simulations about 100 times faster. Particle merging helps control the computational cost of large systems. The work is an early step toward a general simulation framework, with potential applications such as soft robot manipulation, RNA evolution, and galaxy mergers; those broader uses are future goals.

## Source excerpt

By learning how matter moves, the WorldParticle system could assist with developing soft robots, medicines, and more.