In conventional camera sensors collect photons like buckets collecting raindrops. When a “bucket” gets filled up, any additional “water drops” (i.e. photons) will be discarded, and that information is lost. In the resulting photo, that pixel will show up as pure white.
With the modulo camera, each bucket is emptied whenever it fills up during an exposure. This means that when the exposure ends, all the buckets have some kind of useful information in them. By taking into account the number of resets for each bucket, the camera can figure out the relative brightness for each pixel.
See the full story here: http://petapixel.com/2015/08/18/mit-created-a-camera-that-will-never-overexpose-a-photograph/