UniTok: A Unified Tokenizer for Visual Generation and Understanding

• URL: http://arxiv.org/abs/2502.20321v2
• Date: Mon, 19 May 2025 12:45:03 GMT
• Title: UniTok: A Unified Tokenizer for Visual Generation and Understanding
• Authors: Chuofan Ma, Yi Jiang, Junfeng Wu, Jihan Yang, Xin Yu, Zehuan Yuan, Bingyue Peng, Xiaojuan Qi,
• Abstract summary: Visual generative and understanding models typically rely on distinct tokenizers to process images.<n>We introduce UniTok, a unified tokenizer featuring a novel multi-codebook quantization mechanism.<n>In terms of final performance, UniTok sets a new record of 0.38 rFID and 78.6% zero-shot accuracy on ImageNet.
• Score: 69.09699034036124
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Visual generative and understanding models typically rely on distinct tokenizers to process images, presenting a key challenge for unifying them within a single framework. Recent studies attempt to address this by connecting the training of VQVAE (for autoregressive generation) and CLIP (for understanding) to build a unified tokenizer. However, directly combining these training objectives has been observed to cause severe loss conflicts. In this paper, we show that reconstruction and semantic supervision do not inherently conflict. Instead, the underlying bottleneck stems from limited representational capacity of discrete token space. Building on these insights, we introduce UniTok, a unified tokenizer featuring a novel multi-codebook quantization mechanism that effectively scales up the vocabulary size and bottleneck dimension. In terms of final performance, UniTok sets a new record of 0.38 rFID and 78.6% zero-shot accuracy on ImageNet. Besides, UniTok can be seamlessly integrated into MLLMs to unlock native visual generation capability, without compromising the understanding performance. Additionally, we show that UniTok favors cfg-free generation, reducing gFID from 14.6 to 2.5 on ImageNet 256$\times$256 benchmark. GitHub: https://github.com/FoundationVision/UniTok.

Related papers

• WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction [15.687542914511488]
  We introduce a powerful and concise WeTok tokenizer, which surpasses the previous leading tokenizers.<n>We partition the latent features into groups, and perform lookup-free quantization for each group.<n>Generative Decoding (GD) can probabilistically model the distribution of visual data conditioned on discrete tokens.
  arXiv  Detail & Related papers  (2025-08-07T17:41:26Z)
• VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning [95.89543460132413]
  Vision-language models (VLMs) have improved performance by increasing the number of visual tokens.<n>However, most real-world scenarios do not require such an extensive number of visual tokens.<n>We present a new paradigm for visual token compression, namely, VisionThink.
  arXiv  Detail & Related papers  (2025-07-17T17:59:55Z)
• Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models [92.18057318458528]
  Token-Shuffle is a novel method that reduces the number of image tokens in Transformer.<n>Our strategy requires no additional pretrained text-encoder and enables MLLMs to support extremely high-resolution image synthesis.<n>In GenAI-benchmark, our 2.7B model achieves 0.77 overall score on hard prompts, outperforming AR models LlamaGen by 0.18 and diffusion models LDM by 0.15.
  arXiv  Detail & Related papers  (2025-04-24T17:59:56Z)
• UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding [84.87802580670579]
  We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations. Our unified visual encoding framework captures both high-level semantics and low-level details, delivering multidimensional information.
  arXiv  Detail & Related papers  (2025-04-06T09:20:49Z)
• CODA: Repurposing Continuous VAEs for Discrete Tokenization [52.58960429582813]
  textbfCODA(textbfCOntinuous-to-textbfDiscrete textbfAdaptation) is a framework that decouples compression and discretization. Our approach achieves a remarkable codebook utilization of 100% and notable reconstruction FID (rFID) of $mathbf0.43$ and $mathbf1.34$ for $8 times$ and $16 times$ compression on ImageNet 256$times$ 256 benchmark.
  arXiv  Detail & Related papers  (2025-03-22T12:59:00Z)
• GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting [64.84383010238908]
  We propose an effective image tokenizer with 2D Gaussian Splatting as a solution.<n>In general, our framework integrates the local influence of 2D Gaussian distribution into the discrete space.<n> Competitive reconstruction performances on CIFAR, Mini-Net, and ImageNet-1K demonstrate the effectiveness of our framework.
  arXiv  Detail & Related papers  (2025-01-26T17:56:11Z)
• SweetTokenizer: Semantic-Aware Spatial-Temporal Tokenizer for Compact Visual Discretization [20.109136454526233]
  SweetTokenizer (SweetTokenizer) is a compact yet effective discretization approach for vision data.<n>Our goal is to boost tokenizers' compression ratio while maintaining reconstruction fidelity in the VQ-VAE paradigm.
  arXiv  Detail & Related papers  (2024-12-11T13:48:06Z)
• TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation [26.29803524047736]
  TokenFlow is a novel unified image tokenizer that bridges the gap between multimodal understanding and generation.<n>We demonstrate for the first time that discrete visual input can surpass LLaVA-1.5 13B in understanding performance.<n>We also establish state-of-the-art performance in autoregressive image generation with a GenEval score of 0.55 at 256*256 resolution.
  arXiv  Detail & Related papers  (2024-12-04T06:46:55Z)
• Taming Scalable Visual Tokenizer for Autoregressive Image Generation [74.15447383432262]
  Index Backpropagation Quantization (IBQ) is a new VQ method for the joint optimization of all codebook embeddings and the visual encoder.<n>IBQ enables scalable training of visual tokenizers and, for the first time, achieves a large-scale codebook with high dimension ($256$) and high utilization.
  arXiv  Detail & Related papers  (2024-12-03T18:59:10Z)
• Factorized Visual Tokenization and Generation [37.56136469262736]
  We introduce Factorized Quantization (FQ), a novel approach that revitalizes VQ-based tokenizers by decomposing a large codebook into multiple independent sub-codebooks.<n>This factorization reduces the lookup complexity of large codebooks, enabling more efficient and scalable visual tokenization.<n> Experiments show that the proposed FQGAN model substantially improves the reconstruction quality of visual tokenizers, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-11-25T18:59:53Z)
• Image Understanding Makes for A Good Tokenizer for Image Generation [62.875788091204626]
  We introduce a token-based IG framework, which relies on effective tokenizers to project images into token sequences. We show that tokenizers with strong IU capabilities achieve superior IG performance across a variety of metrics, datasets, tasks, and proposal networks.
  arXiv  Detail & Related papers  (2024-11-07T03:55:23Z)
• Token Fusion: Bridging the Gap between Token Pruning and Token Merging [71.84591084401458]
  Vision Transformers (ViTs) have emerged as powerful backbones in computer vision, outperforming many traditional CNNs. computational overhead, largely attributed to the self-attention mechanism, makes deployment on resource-constrained edge devices challenging. We introduce "Token Fusion" (ToFu), a method that amalgamates the benefits of both token pruning and token merging.
  arXiv  Detail & Related papers  (2023-12-02T04:29:19Z)
• AiluRus: A Scalable ViT Framework for Dense Prediction [95.1313839257891]
  Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. We propose to apply adaptive resolution for different regions in the image according to their importance. We evaluate our proposed method on three different datasets and observe promising performance.
  arXiv  Detail & Related papers  (2023-11-02T12:48:43Z)
• UniFormer: Unifying Convolution and Self-attention for Visual Recognition [69.68907941116127]
  Convolution neural networks (CNNs) and vision transformers (ViTs) have been two dominant frameworks in the past few years. We propose a novel Unified transFormer (UniFormer) which seamlessly integrates the merits of convolution and self-attention in a concise transformer format. Our UniFormer achieves 86.3 top-1 accuracy on ImageNet-1K classification.
  arXiv  Detail & Related papers  (2022-01-24T04:39:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.