CAREER: Generative 4D Simulation with Physical Constraints — NSF Award to Regents of the University of Michigan - Ann Arbor (MI, $
This project aims to improve artificial intelligence (AI) systems that predict how three-dimensional environments change over time. Current AI models that generate videos or simulate future events often require massive computing power and routinely violate basic laws of physics, such as allowing solid objects to pass t
| Award title | CAREER: Generative 4D Simulation with Physical Constraints |
|---|---|
| Award ID | 2544116 |
| Awardee | Regents of the University of Michigan - Ann Arbor |
| City | ANN ARBOR |
| State | MI |
| Amount obligated | $367,296 |
| Principal investigator | Jeong Joon Park |
| Program | Robust Intelligence |
| Start date | 05/01/2026 |
| Abstract | This project aims to improve artificial intelligence (AI) systems that predict how three-dimensional environments change over time. Current AI models that generate videos or simulate future events often require massive computing power and routinely violate basic laws of physics, such as allowing solid objects to pass through one another. These flaws make them unsafe for critical real-world applications like medical surgery, robotics, or scientific simulation of future events. This award supports |
| Source | NSF Awards |
$799/mo
Try NSFGrants →