This repository serves as a knowledge base with key insights, details from other research and implementations to serve as references and one place to document various possible paths to achieve something.
The survey paper does not go into much details around interpretability besides just leaving a few references to be studied:
Why and how Transformers perform so well in multimodal learning has been investigated [106], [299], [300], [301], [302], [303], [304], [305], [306]
This issue is around studying these references and extracting strategies and/or insights among these references, if any of them are useful towards Neko.
The survey paper does not go into much details around interpretability besides just leaving a few references to be studied:
This issue is around studying these references and extracting strategies and/or insights among these references, if any of them are useful towards Neko.