As language models (LMs) improve at tasks like image generation, trivia questions, and simple math, you might think that human-like reasoning is around the corner. In reality, they still trail us by a wide margin on complex tasks. Try playing Sudoku with one, for instance, where you fill in numbers one through nine in such a way that each appears only once across the columns, rows, and sections of a nine-by-nine grid. Your AI opponent will either fail to fill in boxes on its own or do so inefficiently, though it can verify if you’ve filled yours out correctly.
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.
Imagine having a continuum soft robotic arm bend around a bunch of grapes or broccoli, adjusting its grip in real time as it lifts the object. Unlike traditional rigid robots that generally aim to avoid contact with the environment as much as possible and stay far away from humans for safety reasons, this arm senses subtle forces, stretching and flexing in ways that mimic more of the compliance of a human hand. Its every motion is calculated to avoid excessive force while achieving the task efficiently. In MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) and Laboratory for Information and Decisions Systems (LIDS) labs, these seemingly simple movements are the culmination of complex mathematics, careful engineering, and a vision for robots that can safely interact with humans and delicate objects.
