End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
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_ | 1866913084285648896 |
|---|---|
| author | Chu, Wenda Zhang, Bingliang Han, Jiaqi Li, Yizhuo Yang, Linjie Yue, Yisong Guo, Qiushan |
| author_facet | Chu, Wenda Zhang, Bingliang Han, Jiaqi Li, Yizhuo Yang, Linjie Yue, Yisong Guo, Qiushan |
| contents | Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision from generation results to the tokenizer. This contrasts with prior two-stage approaches that train tokenizers and generative models separately. We further investigate leveraging vision foundation models to improve 1D tokenizers for autoregressive modeling. Our autoregressive generative model achieves strong empirical results, including a state-of-the-art FID score of 1.48 without guidance on ImageNet 256x256 generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00503 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer Chu, Wenda Zhang, Bingliang Han, Jiaqi Li, Yizhuo Yang, Linjie Yue, Yisong Guo, Qiushan Computer Vision and Pattern Recognition Machine Learning Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision from generation results to the tokenizer. This contrasts with prior two-stage approaches that train tokenizers and generative models separately. We further investigate leveraging vision foundation models to improve 1D tokenizers for autoregressive modeling. Our autoregressive generative model achieves strong empirical results, including a state-of-the-art FID score of 1.48 without guidance on ImageNet 256x256 generation. |
| title | End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2605.00503 |