QuadTok introduces a quadtree-based visual tokenizer that replaces traditional 2D grids or 1D token sequences with a hierarchical structure, allowing dynamic allocation of tokens to visually complex regions while using coarser resolution for homogeneous areas. The tokenizer, trained on ImageNet, reduces token usage by about 10% compared to a fixed 256-token grid and retains comparable reconstruction fidelity. Leveraging the tree’s natural causality, a 947 M GPT-style model conditioned on a quadtree topology achieves a 2.08 gFID on ImageNet 256×256 and supports zero‑shot spatially controlled image generation.
By Yucheng Mao, Zeyuan Chen, Xiaojun Shan, Xiang Zhang, Divyansh Srivastava, Bingnan Li, Zhuowen Tu
The paper investigates whether keeping non‑spatial register tokens in vision transformer decoders improves image reconstruction and generation. Using representation autoencoders with frozen register‑equipped encoders, the authors show that joint self‑attention over both patch and register tokens yields better reconstruction quality on ImageNet‑1K, with lower FID scores and higher PSNRs compared to patch‑only baselines. For generation, a multi‑head attention pooling predictor recovers register features from sampled patches, further reducing FID by nearly 10% over the patch‑only approach.
By David Jacob Drexlin, Julius Hense, Jonas Dippel
ZipTok3D is a 3D tokenizer that achieves high‑fidelity reconstruction from extremely short token sequences by organizing object geometry into progressively informative global‑token prefixes. During training, nested dropout truncates the latent sequence, forcing each retained prefix to reconstruct the full object, which prioritizes essential geometric information in the leading tokens. The decoder uses a parameter‑shared Transformer block to iteratively recover fine‑grained geometry, enabling reconstruction quality comparable to a 32‑token baseline while using only one token on ShapeNet and four on TRELLIS.
By Mingda Lin, Weijie Wang, Zeyu Zhang, Bowen Cui, Yefei He, Haoyu Zhao, Yuanyu He, Donny Y. Chen, Feng Chen, Bohan Zhuang
VTBench is a new benchmark that evaluates visual tokenizers (VTs) used in autoregressive image generation. It assesses VTs on image reconstruction, detail preservation, and text preservation across diverse scenarios, revealing that continuous VAEs outperform discrete VTs in maintaining spatial structure and semantic detail. The study also explores GPT‑4o’s potential autoregressive behavior and releases the benchmark publicly to encourage development of robust, open‑source VTs.
By Huawei Lin, Tony Geng, Zhaozhuo Xu, Weijie Zhao
arXiv:2605. 26089v2 Announce Type: replace-cross Abstract: We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens.
By Wei Song, Tianhang Wang, Yitong Chen, Tong Zhang, Zuxuan Wu, Min Li, Jiaqi Wang, Kaicheng Yu
arXiv:2608.24293v1 Announce Type: new
Abstract: Latent diffusion models have emerged as a dominant framework for high-fidelity image and video synthesis, operating in compact latent spaces with varia...
By Yeonkyeong Lee, Hyunsung Go, Jongmin Kim, Sewoong Lim, Donghoon Lee
arXiv:2610.17412v1 Announce Type: cross
Abstract: Vision Transformers incur high computational costs when processing long visual token sequences. Existing reduction methods typically rank tokens inde...
By Xiaoya Tang, Shilong Liu, Daniel Smolyak, Xiwen Li, Quynh Nguyen, Tolga Tasdizen
arXiv:2610.33857v1 Announce Type: new
Abstract: We introduce TrackTok, an efficient video tokenization framework that produces object-centric tokens, i.e., tokens that consistently encode the same se...
By Nhi Pham, Christopher Wewer, Bernt Schiele, Jonas Fischer, Jan Eric Lenssen
The paper introduces Split Policy Learned Image Tokenization (SPLIT), a method that learns to allocate token resolution based on the model’s interpretation of task-relevant information rather than raw pixel statistics. SPLIT produces shorter token sequences while matching the accuracy of full-resolution Vision Transformers on classification tasks, and it also achieves competitive performance on dense prediction benchmarks such as COCO and ADE20K.
By Aditya Gupta, Jean Sebastien Dandurand, Kai Qiu, Rohan Choudhury, Laszlo A. Jeni
arXiv:2609.35232v2 Announce Type: replace-cross
Abstract: Visual-token compression is effective for improving the efficiency of vision-language models, but under extreme compression budgets, token pr...
By Rui Zhong, Yu Li, Zheyu Yan, Cheng Zhuo
arXiv:2609.36756v1 Announce Type: cross
Abstract: One-dimensional (1D) variable-length visual tokenizers enable adaptive compression by varying the number of tokens, allowing downstream autoregressiv...
By Jiawei Zhang, Shuhao Liu, Rong Huang, Yuancheng Li, Zhihui Li, Xiaojun Chang, Changlin Li
arXiv:2610.09242v1 Announce Type: new
Abstract: Representation Autoencoders (RAEs) generate images from pre-trained visual fea- tures, but their dense token grids make generative modeling expensive....
By Ram\'on Calvo-Gonz\'alez, Youssef Saied, Fran\c{c}ois Fleuret