About this paper
A discrete native-resolution vision transformer with grouped product quantization and a dual-branch objective acts as a versatile visual tokenizer, matching or exceeding task-specific baselines across visual understanding, generation, and editing tasks.
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 richness of the visual world? We present dNaViT, a Discrete Native-resolution Vision Transformer that produces discrete visual primitives analogous to language tokens. Built upon a frozen pretrained encoder, dNaViT applies lightweight residual modulation with a dual-branch objective to inject…
discrete autoregressive modelingnext-token predictionvision transformerdiscrete visual primitiveslanguage tokensfrozen pretrained encoderresidual modulationdual-branch objectivereconstruction-aware cuesgrouped product quantization
- Upvotes
- 22
- Authors
- 12
- Published
- Nov 9, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
dNaViT: Discrete Codes are General-Purpose Visual Representations was first seen on Hugging Face · Daily papers on Nov 11, 2026. Since then it has appeared in 15 checks on 2 different days. Its best position was #4 of 30, reached on Nov 11, 05:28 UTC. It dropped off the list after Nov 12, 09:28 UTC.