# dNaViT: Discrete Codes are General-Purpose Visual Representations

**Authors:** Xiaotong Li, Zhengrong Yue, Xu Huang, Jialv Zou, Minhao Jing, Wenhao Yan, Haodong Li, Hai Huang, Bo Zhao, Yan Feng, Peng Pei, Xunliang Cai  
**Lab:** Meituan · **Published:** 9 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.12426) · [PDF](https://arxiv.org/pdf/2611.12426) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.12426.html)

## Key numbers

- **12**: Extensive evaluations show that dNaViT matches or exceeds task-specific baselines across 12 visual understanding benchmarks

## Abstract

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 reconstruction-aware cues into semantic features. By leveraging grouped product quantization, it scales discrete capacity without inflating spatial sequence lengths, while a balanced training recipe maintains both semantic and pixel-level information. Consequently, dNaViT functions as a versatile discrete visual tokenizer, enabling unified encoding across downstream tasks alongside high-fidelity image decoding. Extensive evaluations show that dNaViT matches or exceeds task-specific baselines across 12 visual understanding benchmarks, 4 generation benchmarks, and an image editing benchmark. These findings demonstrate that a compact discrete vocabulary can serve as a universal visual currency and unlock the full potential of fully unified, native multimodal methodology.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.