CAREER: Self-Supervised Video Representation Learning for Machine Perception — NSF Award to Massachusetts Institute of Technology
Artificial intelligence systems can now generate realistic video, but they still struggle to learn the world knowledge needed to understand how environments change over time, anticipate the consequences of actions, and support decision- making in the physical world. This limitation is a major barrier to building machin
| Award title | CAREER: Self-Supervised Video Representation Learning for Machine Perception |
|---|---|
| Award ID | 2543631 |
| Awardee | Massachusetts Institute of Technology |
| City | CAMBRIDGE |
| State | MA |
| Amount obligated | $360,000 |
| Principal investigator | Vincent Sitzmann |
| Program | Robust Intelligence |
| Start date | 07/01/2026 |
| Abstract | Artificial intelligence systems can now generate realistic video, but they still struggle to learn the world knowledge needed to understand how environments change over time, anticipate the consequences of actions, and support decision- making in the physical world. This limitation is a major barrier to building machines that can safely and effectively assist people in homes, workplaces, and scientific settings. By developing learning methods that extract action-relevant structure directly from |
| Source | NSF Awards |
$799/mo
Try NSFGrants →