VTP-Small-f16d64

Papers using or citing this model 1

• Towards Scalable Pre-training of Visual Tokenizers for Generation 33 citations · 2025 · arXiv.org · arXiv

  The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level...