SJD-PV: Speculative Jacobi Decoding with Phrase Verification for Autoregressive Image Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912949027733504 |
|---|---|
| author | Yu, Zhehao Zhang, Baoquan Shan, Bingqi Liu, Xinhao Zhou, Dongliang Liang, Guotao Ye, Guangming Ye, Yunming |
| author_facet | Yu, Zhehao Zhang, Baoquan Shan, Bingqi Liu, Xinhao Zhou, Dongliang Liang, Guotao Ye, Guangming Ye, Yunming |
| contents | Autoregressive (AR) image models have recently demonstrated remarkable generative capability, but their sequential nature results in significant inference latency. Existing training-free acceleration methods typically verify tokens independently, overlooking the strong co-occurrence patterns between adjacent visual tokens. This independence assumption often leads to contextual inconsistency and limits decoding efficiency. In this work, we introduce a novel training-free acceleration framework that performs phrase-level speculative verification, enabling the model to jointly validate multiple correlated tokens within each decoding window. To construct such phrase units, we analyze token co-occurrence statistics from the training corpus and group frequently co-occurring tokens into semantically coherent visual phrases. During inference, the proposed phrase-level verification evaluates aggregated likelihood ratios over each phrase, allowing simultaneous acceptance of multiple tokens while preserving generation quality. Extensive experiments on autoregressive text-to-image generation show that our method significantly reduces the number of function evaluations (NFE) and achieves up to 30% faster decoding without compromising visual fidelity. Our findings reveal that modeling short-range token co-occurrence provides an effective and general principle for accelerating autoregressive inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06666 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SJD-PV: Speculative Jacobi Decoding with Phrase Verification for Autoregressive Image Generation Yu, Zhehao Zhang, Baoquan Shan, Bingqi Liu, Xinhao Zhou, Dongliang Liang, Guotao Ye, Guangming Ye, Yunming Computer Vision and Pattern Recognition Autoregressive (AR) image models have recently demonstrated remarkable generative capability, but their sequential nature results in significant inference latency. Existing training-free acceleration methods typically verify tokens independently, overlooking the strong co-occurrence patterns between adjacent visual tokens. This independence assumption often leads to contextual inconsistency and limits decoding efficiency. In this work, we introduce a novel training-free acceleration framework that performs phrase-level speculative verification, enabling the model to jointly validate multiple correlated tokens within each decoding window. To construct such phrase units, we analyze token co-occurrence statistics from the training corpus and group frequently co-occurring tokens into semantically coherent visual phrases. During inference, the proposed phrase-level verification evaluates aggregated likelihood ratios over each phrase, allowing simultaneous acceptance of multiple tokens while preserving generation quality. Extensive experiments on autoregressive text-to-image generation show that our method significantly reduces the number of function evaluations (NFE) and achieves up to 30% faster decoding without compromising visual fidelity. Our findings reveal that modeling short-range token co-occurrence provides an effective and general principle for accelerating autoregressive inference. |
| title | SJD-PV: Speculative Jacobi Decoding with Phrase Verification for Autoregressive Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.06666 |