dNaViT: Discrete Codes are General-Purpose Visual Representations
Discrete autoregressive modeling, notably through next-token prediction, has become a cornerstone of modern language models. Extending this paradigm to vision allows visual and language models to converge on a unified framework, thereby fostering shared methodology and infrastructure. This work investigates a central question: how far can a finite discrete vocabulary go in representing the…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
