Can I update some new features?

[maxwZJU]

Hello! I read the paper and want to implement the code, and I want to add some KA features on vit for image classification. My ideas are as below:
Provide a comprehensive and robust pipeline and a data preprocessing method that allows training with own datasets.
Implement KA on vision transformers to accomplish image classification tasks.(finetuned on several datasets such as Stanford Dogs)
Provide a multimodal transfer method to apply KA for audio classification.

[MArSha1147]

Thanks for your update! We'll accept it after the code review.