About the release of VILA v1.5 technical report or blog

[Fr0zenCrane]

Hi,

Thank you for your outstanding work! Without a doubt, your recently published VILA v1.5 series pushes the boundaries of multimodal large language models. It is arguably the most powerful and user-friendly MLLM available today.

Many of us who are interested in the VILA v1.5 series are curious about the development of its video intelligence capabilities. A detailed technical report on this aspect would be incredibly beneficial. Could you let us know if the VILA development team is planning to release such a report?

Thank you!

[Lyken17]

Thanks for your interest! Sure, we will release soon by end of July. Please stay tuned

[jihuishan]

@Lyken17 Thank you for your amazing work! May I ask where to view the technical report or blog? Or, specifically, what LLMs are vila-1.5 3b, 7b and 13b using? I noticed there seems to be some changes? Thank you for your attention!