Even networks long considered “untrainable” can learn effectively with a bit of a helping hand. Researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have shown that a brief period of alignment between neural networks, a method they call guidance, can dramatically improve the performance of architectures previously thought unsuitable for modern tasks. Their findings suggest that many so-called “ineffective” networks may simply start from less-than-ideal starting points, and that short-term guidance can place them in a spot that makes learning easier for the network.  The team’s guidance method works by encouraging a target network to match the internal […]

In August 2025, Wang Lei decided it was finally time to say goodbye to his electric vehicle. Wang, who is 39, had bought the car in 2016, when EVs still felt experimental in Beijing. It was a compact Chinese brand. The subsidies were good, and the salesman talked about “supporting domestic innovation.” At the time, only a few people around him were driving on batteries. He liked being early. But now, the car’s range had started to shrink as the battery’s health declined. He could have replaced the battery, but the warranty had expired; the cost and trouble no longer […]

Why did humans evolve the eyes we have today? While scientists can’t go back in time to study the environmental pressures that shaped the evolution of the diverse vision systems that exist in nature, a new computational framework developed by MIT researchers allows them to explore this evolution in artificial intelligence agents. The framework they developed, in which embodied AI agents evolve eyes and learn to see over many generations, is like a “scientific sandbox” that allows researchers to recreate different evolutionary trees. The user does this by changing the structure of the world and the tasks AI agents complete, […]