dNaViT: Discrete Codes are General-Purpose Visual Representations
dNaViT tests whether one discrete visual vocabulary can support image understanding, reconstruction, generation, and editing without sacrificing semantic or fine-grained detail.
ls ./papers | grep "#dNaViT"
Trending AI research papers from Hugging Face, summarized in plain language: what each paper does, why it matters and where to read more.
1 paper · #dNaViT
dNaViT tests whether one discrete visual vocabulary can support image understanding, reconstruction, generation, and editing without sacrificing semantic or fine-grained detail.