Metraipolis › archive › dc_c33c600d26b4
dNaViT: Discrete Codes are General-Purpose Visual Representations — arXiv:2611.12426
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12426
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:44:06.779Z
- SHA-256 of the archived text
fd17b9a899b62ac39e8abaab57b39617409066bb3f8d8cb620c241b617d763fd- Stable URL of this page
https://metraipolis.com/documento/dc_c33c600d26b4
How to cite
dNaViT: Discrete Codes are General-Purpose Visual Representations — arXiv:2611.12426 — arXiv (en), https://arxiv.org/abs/2611.12426 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c33c600d26b4 (Metraipolis archive dc_c33c600d26b4, sha256 fd17b9a899b62ac39e8abaab57b39617409066bb3f8d8cb620c241b617d763fd)
BibTeX
@misc{dcc33c600d26b4,
title = {dNaViT: Discrete Codes are General-Purpose Visual Representations — arXiv:2611.12426},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12426},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c33c600d26b4; sha256 fd17b9a899b62ac39e8abaab57b39617409066bb3f8d8cb620c241b617d763fd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12426. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.12426 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:37.693Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).