Factorized Vector Quantization Advances Discrete Visual Tokens
A new arXiv paper proposes Factorized Vector Quantization for discrete visual representations, using complementary fixed-dimensional views and symmetric parallel codebooks to reduce saturation as bit budgets increase. Its authors report that the resulting model matches continuous visual representations on multimodal understanding and outperforms UniAR and Emu3-Chat by 22.8% and 59.2%, respectively, on a nine-metric average. The paper also claims competitiveness with continuous-representation models such as Qwen3-VL, including on fine-grained OCR tasks.
The work presents a concrete method for preserving semantic information in discrete visual tokens, a central issue for multimodal models that use shared next-token prediction.
Computer Science > Computer Vision and Pattern Recognition
arXiv:2610.37662 (cs)
[Submitted on 27 Oct 2026]
Title:Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?
Authors:Jialv Zou, Xiaotong Li, Zhengrong Yue, Xu Huang, Yaxin Luo, Wenhao Yan, Haodong Li, Wenyu Liu, Xinggang Wang
View a PDF of the paper titled Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?, by Jialv Zou and 8 other authors