Metraipolis › archive › dc_30da3867748e
SJD-SV: Speculative Jacobi Decoding with Semantics Verification for Autoregressive Image Generation — arXiv:2609.13245
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13245
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T01:52:32.667Z
- SHA-256 of the archived text
3e8850b82e58d50952ebf887b2d111d217dc18be44f47251d88705cd2482640e- Stable URL of this page
https://metraipolis.com/documento/dc_30da3867748e
How to cite
SJD-SV: Speculative Jacobi Decoding with Semantics Verification for Autoregressive Image Generation — arXiv:2609.13245 — arXiv (en), https://arxiv.org/abs/2609.13245 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_30da3867748e (Metraipolis archive dc_30da3867748e, sha256 3e8850b82e58d50952ebf887b2d111d217dc18be44f47251d88705cd2482640e)
BibTeX
@misc{dc30da3867748e,
title = {SJD-SV: Speculative Jacobi Decoding with Semantics Verification for Autoregressive Image Generation — arXiv:2609.13245},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13245},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_30da3867748e; sha256 3e8850b82e58d50952ebf887b2d111d217dc18be44f47251d88705cd2482640e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13245. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Speculative Jacobi Decoding (SJD) is an important approach for accelerating autoregressive image generation. Although SJD has shown superior performance, recent studies point out that it usually suffers from a token ambiguity issue during token verification but its reason can not be well explained. To figure out this reason, in this paper, we conduct a visualization analysis on vision token and find that different from text tokens, vision tokens generally corresponds to some local, small, and unclear vision details, which means only using single token is difficult to accurately express a certain semantic, thereby causing token ambiguity issue. To this end, we propose a novel Speculative Jacobi Decoding with Semantics Verification (called SJD-SV), for accelerating autoregressive image generation. The key idea is that leveraging the strong correction characters between tokens to recognize semantic-aware token subsequence and then instead of perform token-by-token verification, turning to perform verification on semantic-aware token subsequence level for accelerating image generation. In particular, our method is plug-in, which can be directly integrated into existing SJD and its variants. Extensive experiments on various datasets show that existing SJD methods achieve significant performance improvement after integrating our SJD-SV method. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.13245 — 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 2026-10-16T01:25:23.471Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).