Next-Token Prediction Meets Full-Sequence Diffusion

Watch this video to learn more about Rotograb, a robotic hand that merges the dexterity of human hands with the strength and efficiency of industrial grippers. It was developed by students during "Real World Robotics," a master course at ETH Zurich.

“With Diffusion Forcing, we are taking a step to bringing video generation and robotics closer together,” says senior author Vincent Sitzmann  , MIT assistant professor and member of CSAIL, where he leads the Scene Representation group.