A lot of recent works can be added to the paper list.

[zhangyuygss]

Rencently, many MLLM works on both image and video understanding achieve great results on video benchmarks. e.g. LLaVA-Next, InternLM, Vila, etc
I think these works should also be added to the paper list for readers to have a comprehensive understanding on this feild.

[yunlong10]

Rencently, many MLLM works on both image and video understanding achieve great results on video benchmarks. e.g. LLaVA-Next, InternLM, Vila, etc I think these works should also be added to the paper list for readers to have a comprehensive understanding on this feild.

Thank you for your suggestions! We've updated these recent works in the latest version of our survey paper, but they haven't been added to the GitHub repository yet. We'll be working on that soon.