Request to add new paper

[ZZZHANG-jx]

Hello! Thanks for compiling so many great methods into this very helpful resource. Our new paper (accepted by AAAI 2025) is a multimodal method for document image understanding. Would you mind adding it to your resource? Thanks!

Title: DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming Paper: https://arxiv.org/abs/2406.19101 Code: https://github.com/ZZZHANG-jx/DocKylin

We will cite your work in our camera-ready version.