Add two our MLLM papers

[sccbhxc]

We have submit pull request as the template of README.
BradyFU/Awesome-Multimodal-Large-Language-Models#249

{
"title": Learning Compact Vision Tokens for Efficient Large Multimodal Models,
"url": paper URL,
"venue": arXiv,
"category": Visual Understanding,
"code": https://github.com/visresearch/LLaVA-STF,
"collections": https://huggingface.co/visresearch/LLaVA-STF/tree/main
}

{
"title": Diversity-Guided MLP Reduction for Efficient Large Vision Transformers,
"url": https://arxiv.org/abs/2506.08591,
"venue": arXiv,
"category": Visual Understanding,
"code": https://github.com/visresearch/DGMR,
"collections": https://huggingface.co/visresearch/DGMR/tree/main
}

[friedrichor]

Received and updated.