LLMs trained primarily on text can generate complex visual concepts through code with self-correction. Researchers used these illustrations to train an image-free computer vision system to recognize real photos.
The inventor, entrepreneur, and philanthropist encourages the Class of 2024 to “accept impossible missions” and “lead with imagination” in uncertain times.
“Alchemist” system adjusts the material attributes of specific objects within images to potentially modify video game models to fit different environments, fine-tune VFX, and diversify robotic training.
Graduate student Nolen Scruggs works with a local tenant association to address housing inequality as part of the MIT Initiative on Combatting Systemic Racism.