V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Guiwei, Zhang, Tianyu, Zhou, Mohan, Bai, Yalong, Li, Biye
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913728199393280
author Zhang, Guiwei
Zhang, Tianyu
Zhou, Mohan
Bai, Yalong
Li, Biye
author_facet Zhang, Guiwei
Zhang, Tianyu
Zhou, Mohan
Bai, Yalong
Li, Biye
contents We propose V2Flow, a novel tokenizer that produces discrete visual tokens capable of high-fidelity reconstruction, while ensuring structural and latent distribution alignment with the vocabulary space of large language models (LLMs). Leveraging this tight visual-vocabulary coupling, V2Flow enables autoregressive visual generation on top of existing LLMs. Our approach formulates visual tokenization as a flow-matching problem, aiming to learn a mapping from a standard normal prior to the continuous image distribution, conditioned on token sequences embedded within the LLMs vocabulary space. The effectiveness of V2Flow stems from two core designs. First, we propose a Visual Vocabulary resampler, which compresses visual data into compact token sequences, with each represented as a soft categorical distribution over LLM's vocabulary. This allows seamless integration of visual tokens into existing LLMs for autoregressive visual generation. Second, we present a masked autoregressive Rectified-Flow decoder, employing a masked transformer encoder-decoder to refine visual tokens into contextually enriched embeddings. These embeddings then condition a dedicated velocity field for precise reconstruction. Additionally, an autoregressive rectified-flow sampling strategy is incorporated, ensuring flexible sequence lengths while preserving competitive reconstruction quality. Extensive experiments show that V2Flow outperforms mainstream VQ-based tokenizers and facilitates autoregressive visual generation on top of existing. https://github.com/zhangguiwei610/V2Flow
format Preprint
id arxiv_https___arxiv_org_abs_2503_07493
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation
Zhang, Guiwei
Zhang, Tianyu
Zhou, Mohan
Bai, Yalong
Li, Biye
Computer Vision and Pattern Recognition
Artificial Intelligence
We propose V2Flow, a novel tokenizer that produces discrete visual tokens capable of high-fidelity reconstruction, while ensuring structural and latent distribution alignment with the vocabulary space of large language models (LLMs). Leveraging this tight visual-vocabulary coupling, V2Flow enables autoregressive visual generation on top of existing LLMs. Our approach formulates visual tokenization as a flow-matching problem, aiming to learn a mapping from a standard normal prior to the continuous image distribution, conditioned on token sequences embedded within the LLMs vocabulary space. The effectiveness of V2Flow stems from two core designs. First, we propose a Visual Vocabulary resampler, which compresses visual data into compact token sequences, with each represented as a soft categorical distribution over LLM's vocabulary. This allows seamless integration of visual tokens into existing LLMs for autoregressive visual generation. Second, we present a masked autoregressive Rectified-Flow decoder, employing a masked transformer encoder-decoder to refine visual tokens into contextually enriched embeddings. These embeddings then condition a dedicated velocity field for precise reconstruction. Additionally, an autoregressive rectified-flow sampling strategy is incorporated, ensuring flexible sequence lengths while preserving competitive reconstruction quality. Extensive experiments show that V2Flow outperforms mainstream VQ-based tokenizers and facilitates autoregressive visual generation on top of existing. https://github.com/zhangguiwei610/V2Flow
title V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.07493