Xin Eric Wang

A new benchmark aims to assess MLLMs in video understanding across multiple topics.

2025-07-29T22:20:42+00:00 ― 6 min read

A new AI system enhances accessibility for users with visual impairments through better screen reading.

2025-07-23T10:27:06+00:00 ― 5 min read

Combining language understanding and vision enhances robot navigation capabilities.

2025-07-11T12:28:18+00:00 ― 6 min read

Discover how text descriptions become captivating videos with advanced technology.

2025-03-13T22:32:42+00:00 ― 7 min read