Chunyuan Li

Discover the latest advancements in large multimodal models combining visual and language data.

This article examines how generative images can improve visual recognition tasks.

Discover the evolution of AI handling multiple data types.

Study reveals how larger models improve understanding of text and images.

Analyzing the importance and difficulties of assessing multimodal AI models.

Examining the role of LMMs in transforming search capabilities with text and images.