Home

Awesome

Visual Table

Beyond Embeddings: The Promise of Visual Table in Multi-Modal Models [Paper] <br> Yiwu Zhong<sup>*1</sup>, Ziyuan Hu<sup>*1,2</sup>, Michael R. Lyu<sup>1</sup>, Liwei Wang<sup>#1</sup> <br> <sup>1</sup>The Chinese University of Hong Kong, <sup>2</sup>Shanghai AI Laboratory <br> (<sup>*</sup> equal contributions, <sup>#</sup> corresponding author) <br>

<p align="center"> <img src="teaser_figure.jpg" width=97% height=97% class="center"> </p>

Stay tuned!