Why not cite FastV?

[MiloQ]

In my opinion, the part of LLava-Mini where the model shallowly integrates image information has a lot in common with FastV. Has the author looked into this article?

An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models（https://arxiv.org/abs/2403.06764）