Can I read V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation on EtoBox?

V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation by Zhang, Guiwei; Zhang, Tianyu; Zhou, Mohan; Bai, Yalong; Li, Biye is a scholarly article available to read on EtoBox.

What is V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation about?

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 reco

Author

Zhang, Guiwei; Zhang, Tianyu; Zhou, Mohan; Bai, Yalong; Li, Biye

Published

2025

Language

EN