SketchAgent, a drawing system developed by MIT CSAIL researchers, sketches up concepts stroke-by-stroke, teaching language models to visually express concepts on their own and collaborate with humans.

This new machine-learning model can match corresponding audio and visual data, which could someday help robots interact in the real world.

Researchers are developing algorithms to predict failures when automation meets the real world in areas like air traffic scheduling or autonomous vehicles.

The color-correcting tool, known as “SeaSplat,” reveals more realistic colors of underwater features.

What do Sudoku, AI, Rubik’s cubes, clocks and molecules have in common? They can all be reimagined as algebraic equations.

With a novel simulation method, robots can guess the weight, softness, and other physical properties of an object just by picking it up.

“IntersectionZoo,” a benchmarking tool, uses a real-world traffic problem to test progress in deep reinforcement learning algorithms.

New type of “state-space model” leverages principles of harmonic oscillators.

A brain-inspired algorithm could improve word recognition accuracy in noisy situations by up to 40 percentage points.

Using diagrams to represent interactions in multipart systems can provide a faster way to design software improvements.