# Multimodal Transformers with signal inputs

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmultimodal-transformers-with-signal-inputs%2F85921%3E%5C
**Category:** Beginners\
**Created:** [May 9, 2024, 7:09am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmultimodal-transformers-with-signal-inputs%2F85921 "2024-05-09T07:09:40Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ashkan-zadeh](https://avatars.discourse-cdn.com/v4/letter/a/d2c977/32.png) [@ashkan-zadeh](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fashkan-zadeh)%5C
**Post date:** [May 9, 2024, 7:09am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmultimodal-transformers-with-signal-inputs%2F85921%2F1 "2024-05-09T07:09:40Z")

</div>

Hi all,

I’ve read papers that used multimodal models with both text and video/image together as inputs for VLMs but I’m not sure whether we can also have signals data (e.g., a sensor data) as an input along with text and image/video (as the third input) or not! I would like to hear your idea.