{
  "id": 19099045,
  "title": "A single AI model simulates the behavior of many substances, from sliding sand to folding proteins",
  "url": "https://urgent.news/2026/11/09/a-single-ai-model-simulates-the-behavior-of-many-substances-from-19099045",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-09T05:00:00.000Z",
  "source": {
    "name": "MIT News AI",
    "slug": "mit-news-ai",
    "url": "https://news.mit.edu/2026/single-ai-model-simulates-many-substances-behavior-1109"
  },
  "original_language": "en",
  "account": "A single deep-learning system called WorldParticle has been created by researchers at MIT, the University of British Columbia (UBC), and other institutions. This AI architecture can simulate various physical phenomena, such as sliding sand and folding proteins, using one unified model. WorldParticle represents each material as tiny particles and predicts their movement step by step based on the underlying dynamics. This unified model could offer faster and more accurate simulations compared to separate simulators for different processes, such as modeling the impact of sloshing oil on an elastic valve in a storage tank or studying the movement of granular materials when touched by a soft robot. The system could help scientists discover new materials and explore physical processes that are challenging to study with existing simulation methods. The researchers, including Peter Yichen Chen, Minghao Guo, Caoliwen Wang, Siyuan Chen, and Wojciech Matusik, aim to create a \"GPT moment for simulation,\" where a foundation model works out of the box for any scenario one wants to simulate.",
  "summary": "By learning how matter moves, the WorldParticle system could assist with developing soft robots, medicines, and more.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}