Great work!
After reading your paper SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs , I'm very interested in the implementation, especially how the image is reconstructed from the word pyramid.
But I haven’t seen the release of the code yet.
Looking forward to SPAE code release!
Great work! After reading your paper SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs , I'm very interested in the implementation, especially how the image is reconstructed from the word pyramid. But I haven’t seen the release of the code yet. Looking forward to SPAE code release!