Yilun Du – MIT EECS

New research could allow a person to correct a robot’s actions in real-time, using the kind of feedback they’d give another human.

A new method can train a neural network to sort corrupted data while anticipating next steps. It can make flexible plans for robots, generate high-quality video, and help AI agents navigate digital environments.

In this conceptual painting, a computer responds with several different images in response to the prompt "A horse in a yellow flower field".

Yilun Du, a PhD student and MIT CSAIL affiliate, discusses the potential applications of generative art beyond the explosion of images that put the web into creative hysterics.

Robotic helper making mistakes? Just nudge it in the right direction

Combining next-token prediction and video diffusion in computer vision and robotics

3 Questions: How AI image generators could help robots