Enze Xie

A method for creating high-quality images from text descriptions with improved efficiency.

2025-08-31T13:45:42+00:00 ― 6 min read

DriveCoT improves self-driving car decision-making clarity and safety.

2025-08-26T00:15:06+00:00 ― 7 min read

Introducing a method to automate 3D labeling using 2D prompts.

2025-07-12T03:52:36+00:00 ― 6 min read

VILA-U integrates video, image, and language tasks into a single framework.

2025-06-16T03:07:06+00:00 ― 5 min read