Zhenyu Tang

MoE-LLaVA combines images and text using an efficient model structure.

2025-09-13T12:29:42+00:00 ― 6 min read

A new dataset and model enhance video captioning quality for machines.

2025-08-01T13:56:24+00:00 ― 5 min read

Easily generate high-quality videos with just a few words using Open-Sora Plan.

2025-05-03T06:46:40+00:00 ― 6 min read

Learn how NPP improves AI image generation efficiency and quality.

2025-02-14T02:51:54+00:00 ― 5 min read