SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs Supplementary Materials Appendix Overview

Appendix B provides additional implementation details, including a video SP AE variant. Appendix C includes more quantitative evaluation results. Appendix D shows more qualitative examples of model generations. Figure 1 shows an example of the dilation subsampler defined by Eq. (1). We select evenly distributed positions in each layer to form the token pyramid with monotonically increasing layer sizes.