Novel method makes tools like Stable Diffusion and DALL-E-3 faster by simplifying the image-generating process to a single step while maintaining or enhancing image quality.

FeatUp, developed by MIT CSAIL researchers, boosts the resolution of any deep network or visual foundation for computer vision systems.

Joining three teams backed by a total of $75 million, MIT researchers will tackle some of cancer’s toughest challenges.

A new algorithm reduces travel time by identifying shortcuts a robot could take on the way to its destination.

By enabling models to see the world more like humans do, the work could help improve driver safety and shed light on human behavior.

Faster and more accurate than some alternatives, this approach could be useful for robots that interact with humans or work in tight spaces.

Electric vehicles are catching on across the US, but they’re also catching on fire in colder regions like the Northeast and Midwest.

MIT spinout DataCebo helps companies bolster their datasets by creating synthetic data that mimic the real thing.

The work will help researchers tune surface properties of perovskites, a promising alternative and supplement to silicon, for more efficient photovoltaics.