Ran Xu

Text2Data improves data generation using unlabeled and labeled sources effectively.

Introducing SQ-LLaVA, a method enhancing image questioning and understanding.

MINT-1T is the largest open-source dataset for training multimodal models.

Exploring the dynamics of fluid movement in porous materials and its implications.

xGen-MM enhances multimodal models for better image and text learning.

KALE combines images with rich captions for better understanding.