Trendoday

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 conv

  • Upvotes22
–Rank now
#4Peak rank
2Days on list
365Score · 7d
Nov 11, 2026First seen
Rank · 7 days

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.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 05:2812:2819:2802:2809:28 Nov 11, 05:28 UTC · #4Nov 11, 07:28 UTC · #4Nov 11, 09:28 UTC · #5Nov 11, 11:28 UTC · #4Nov 11, 13:28 UTC · #5Nov 11, 15:28 UTC · #5Nov 11, 17:28 UTC · #5Nov 11, 19:28 UTC · #5Nov 11, 21:28 UTC · #5Nov 11, 23:28 UTC · #6Nov 12, 01:28 UTC · #6Nov 12, 03:28 UTC · #6Nov 12, 05:28 UTC · #6Nov 12, 07:28 UTC · #6Nov 12, 09:28 UTC · #4

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

Platform metric as reported by Hugging Face.

0112233 05:2812:2819:2802:2809:28 Nov 11, 05:28 UTC · 22Nov 11, 07:28 UTC · 28Nov 11, 09:28 UTC · 29Nov 11, 11:28 UTC · 29Nov 11, 13:28 UTC · 31Nov 11, 15:28 UTC · 32Nov 11, 17:28 UTC · 32Nov 11, 19:28 UTC · 32Nov 11, 21:28 UTC · 32Nov 11, 23:28 UTC · 32Nov 12, 01:28 UTC · 32Nov 12, 03:28 UTC · 33Nov 12, 05:28 UTC · 33Nov 12, 07:28 UTC · 33Nov 12, 09:28 UTC · 33

Questions

Is dNaViT: Discrete Codes are General-Purpose Visual Representations trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 12, 09:28 UTC, after 2 days of trending.

What is the highest rank dNaViT: Discrete Codes are General-Purpose Visual Representations reached?

#4 on Hugging Face · Daily papers, on Nov 11, 05:28 UTC. Trendoday checks this list every 120 minutes.

How long has dNaViT: Discrete Codes are General-Purpose Visual Representations been trending?

It was first seen on Nov 11, 2026 and has been on the list on 2 days (15 checks) since.