Is DALL-E 2 Just 'Gluing Things Together' Without Understanding Their Relationships? - Unite.AIA new research paper from Harvard University suggests that OpenAI's headline-grabbing text-to-image framework DALL-E 2 has notable difficulty in reproducing even infant-level relations between the elements that it composes into synthesized photos, despite the dazzling sophistication of much of its o
Face-specific brain area responds to faces even in people born blindMIT researchers have found the fusiform face area, which is specialized to recognize faces, lights up in people who have been blind since birth when they touch a 3D model of a face with their hands. The finding suggests this area does not require visual experience to develop a preference for faces.
The following links highlight the work that Artificio Researchers are pursuing at their current institutions and give a hint of what we are working on under stealth.