Visual Tokenizers

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, down 40% on the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 62

Sep 30, 2026cs.CV

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation

Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene tokenizer is paramount for the optimal performance of each of these, both in terms of fidelity and semantics. Flexible-length, coarse-to-fine tokenizers yield exactly that: the first coarse tokens carry the clip's global semantics while later tokens further specify details. Existing flexible tokenizers only apply a representation-alignment (REPA) loss on early decoder hidden states, a target the decoder can partly meet from its noised input instead. We introduce SemanTok, a flexible video tokenizer that feeds frozen DINO features into its encoder and adds lightweight heads that reconstruct them from each retained token prefix alone. SemanTok achieves high semantic alignment and video fidelity at every AR model size: a 201M SemanTok AR model matches or beats a VideoFlexTok AR model

3.4\times

its size, and larger SemanTok AR models further improve fidelity. It keeps semantic alignment on out-of-distribution classes and gives the decoder higher semantic alignment at every noise level, including pure noise. It performs well in both reconstruction and generation, and its short token prefixes are cheaper to predict and give better generation fidelity, with pixel detail deferred to later tokens.

Mikhail Dereviannykh, Vikram Voleti, Simon Donne +3

Stability AI · Karlsruhe Institut für Technologie

Visual Tokenizers Autoregressive Video Generation Video Generation Diffusion Models Encoders

Sep 29, 2026cs.CV

NesTok: Nested Self-Aligned 1D Tokenizer for Autoregressive Image Generation

One-dimensional (1D) variable-length visual tokenizers enable adaptive compression by varying the number of tokens, allowing downstream autoregressive (AR) models to flexibly trade off generation quality against computational cost using a single tokenizer. However, existing approaches based on nested dropout often fail to fully exploit the representational capacity of the tokenizer, resulting in suboptimal performance in both image reconstruction and generation. In this work, we introduce NesTok, a nested self-alignment framework tailored to dynamic visual tokenizers. NesTok introduces cross-length training, which jointly optimizes reconstruction across token lengths while using the full-length sequence to guide shorter counterparts, enabling shorter token sequences to approach the reconstruction quality of full-length sequences. On ImageNet, NesTok improves substantially over standard training and achieves an rFID score of 0.98. On downstream image generation, it achieves the state-of-the-art gFID score of 1.46 on ImageNet 256

\times

256 among existing variable-length autoregressive image generation methods. Code will be available at https://github.com/Jiawei804/NesTok.

Jiawei Zhang, Shuhao Liu, Rong Huang +4

North China Electric Power University · University of Science and Technology of China · Stanford University

Autoregressive Image Generation Visual Tokenizers Autoregressive Token Prediction Tokenizer

Sep 21, 2026cs.CV

What Makes a Good Medical Image Tokenizer? Rethinking Reconstruction and Generation in Medical Image Tokenization

Latent diffusion models now dominate medical image generation, and every such pipeline rests on a \emph{tokenizer} that compresses images into the latent codes for image generation to operate on. Thereby, the tokenizer choice bounds every downstream task from reconstruction fidelity and generation quality to the representations available for downstream analysis. Yet, medical imaging pipelines routinely utilize tokenizers from natural imaging on the hypothesis that their behavior carries over. However, this is an assumption never tested in the medical imaging regime, where datasets are orders of magnitude smaller and images exhibit far lower inter-sample variance. We present a systematic evaluation of medical image tokenizers evaluating thirty configurations across ten model families on twelve datasets at three compression factors, spanning reconstruction, generation, latent geometry, downstream classification, and memorization. We find that (1) performance on image reconstruction and generation strongly correlate, unlike prior reports on natural images; (2) modern tokenizers use nearly all of their codebook entries, but still leave most of the latent space unused; (3) training-set memorization is mild and is further suppressed by stronger latent space compression; and (4) discrete quantization can largely preserve downstream classification, with lookup-free schemes being the main exception.

Niklas Bubeck, Yundi Zhang, Vasiliki Sideri-Lampretsa +4

School of Computation, Information and Technology, Technical University of Munich, Germany · Munich Center for Machine Learning, Technical University of Munich, Germany · School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Germany +3

Medical Image Generation Visual Tokenizers Latent Space Quantizer

Sep 14, 2026cs.CV

VideoTok4D: A 4D-Aware Video Tokenizer for Compact World Representation

Video tokenizers have emerged as a cornerstone of modern video modeling, underpinning progress in compression, reconstruction and generation by mapping high-dimensional visual signals into compact latent spaces. However, despite this progress, current tokenization paradigms largely remain within the 2D visual domain, treating videos as image sequences rather than observations of an underlying dynamic 3D world. Consequently, the learned tokens inherit this observation-centric bias, limiting their capacity to compactly represent real-world 4D scenes. To mitigate this issue, we propose VideoTok4D, a novel 4D-aware video tokenizer for compact world representation. Specifically, our approach comprises three key designs: 1) a spatiotemporal disentanglement strategy that factorizes videos into static and dynamic tokens for holistic world modeling; 2) a track-aware dynamic attention mechanism that aggregates trajectory-aligned cues to promote cross-view motion consistency; and 3) Co4DGen, a diffusion prior learned over the resulting VideoTok4D token space for efficient 4D scene generation. Extensive experiments have demonstrated that our proposed method achieves state-of-the-art performance while requiring up to 4 orders of magnitude less storage than dense 4D representations. Moreover, the compact token space substantially shortens diffusion sequences, enabling efficient generation.

Xinyi Chen, Hanxin Zhu, Xijun Wang +4

University of Science and Technology of China

Visual Tokenizers Video Diffusion Models World Models

Sep 11, 2026cs.CV

LoopVAE: Recurrent Depth Across Scales for Visual Tokenization

Hierarchical visual tokenizers typically allocate different processing blocks to different spatial scales. We ask how much of this computation can use the same parameters. LoopVAE reuses a scale- and loop-conditioned core within and across scales, while keeping resolution-changing transitions independent. A four-block core executes 28 block applications per encoder or decoder. On ImageNet-256, the 29M-parameter convolutional model reaches 0.28 rFID and 32.54 dB PSNR under an approximately 30-epoch two-stage training budget, using approximately 65% fewer parameters than the 84M reference VAEs. A non-adversarial Transformer ablation with the same execution graph finds competitive PSNR and SSIM under global sharing, although unshared blocks improve LPIPS. Targeted loop interventions show that completing the trained recurrence improves reconstruction and that even small feature updates can have substantial downstream effects. Truncation also exposes output-range errors, distinguishing useful recurrent computation from reliable early exit. Runtime profiling reveals the execution tradeoff: fewer stored weights require more arithmetic and longer runtime in the tested configurations. With convolutional and Transformer operators and single- or multi-resolution latent interfaces, LoopVAE establishes recurrent depth across scales as a parameter-sharing design axis for visual tokenization.

Zhiying Lu

University of Science and Technology of China

Visual Tokenizers Imagenet

Aug 13, 2026cs.CV

V-RAE: Rethinking Video Latent Spaces for Generation

Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures have evolved substantially, their latent spaces are still optimized primarily for pixel-level reconstruction and provide limited high-level semantic organization. A reconstruction-optimal latent space, however, need not be well suited to generative modeling. We propose V-RAE, a video representation autoencoder that builds compact generative latents on top of frozen vision foundation model representations. A lightweight temporal pooling module removes temporal redundancy while preserving semantic structure, and a video decoder reconstructs continuous motion from the compressed features. We evaluate V-RAE with four representative frozen encoders on video reconstruction, semantic probing, and class-conditional generation. V-RAE achieves 2.13 rFVD on K600, outperforming all evaluated large-scale pretrained video VAEs. Its latents retain substantially more semantic information than conventional video tokenizer latents. Under matched generation settings, our best variant achieves gFVD scores of 117.86 and 19.16 on UCF101 and K600, respectively, while converging up to 6x faster}. We further show that reconstruction quality alone is insufficient to characterize generative utility and introduce tFVD, a temporal-coherence diagnostic that correlates more reliably with downstream generation quality. Beyond video generation, V-RAE also improves future video prediction on Cityscapes over the Wan 2.2 VAE latent space under matched prediction settings. Taken together, the experiments show that frozen semantic representations can support video reconstruction, generation, and predictive modeling. The project page: https://v-rae.github.io/.

Minghui Guo, Shengqiong Wu, Hao Fei

National University of Singapore · University of Oxford

Autoregressive Video Generation Star-Vae Conditional Variational Autoencoder Video Latents Autoencoder Architectures Frozen Vision-Language Models+3

Aug 7, 2026cs.CV

Tokenizer-Generator Coupling in Medical Image Generation

Latent medical image generators usually treat the tokenizer as fixed preprocessing. We test whether this separation holds in a controlled ChestMNIST study at

64\times64

that crosses discrete tokenizers, generator families, and sampler settings under a shared latent grid, with continuous-latent reference cells. The rankings depend jointly on the tokenizer, generator, and sampler. The best quantizer changes with the generator, and validation-based sampler selection changes the apparent generator ranking. We interpret this through a rate-distortion-modelability framing in which modelability is conditional on the generator, sampler, and inference budget. The interaction persists when the vocabulary-1024 block is retrained at three seeds, with 4 of 9 pairwise quantizer comparisons exceeding three seed standard deviations, including a reversal between LFQ and FSQ from MaskGIT to D3PM; the rest of the grid was trained at a single seed and is correspondingly less certain. Reconstruction PSNR alone is not a reliable selection criterion. On LFQ-1024, retuning the D3PM and SEDD samplers on a held-out validation split reduces FID-192 from 0.44/0.41 at the default budget to 0.09/0.10 at lower NFE, replicated across seeds, although the continuous references were not given an equivalent sampler sweep. FID-192, our internal ranking metric, ranks consistently with standard FID-2048 (Spearman 0.89) and with a label-free classifier two-sample test (0.86). All experiments are unconditional, use low-resolution

64\times64

medical-style images and are evaluated with non-clinical FID-based metrics, and our claims are limited to that setting. Implementations are released at https://github.com/liamchalcroft/medtokenizers and https://github.com/liamchalcroft/medlatents.

Liam Chalcroft

University College London London, United Kingdom

Medical Image Generation Visual Tokenizers Generators Tokenizer Token-Level Entropy

Aug 6, 2026cs.CV

KVAE: Family of Tokenizers for Multimodal Generative Models

Latent diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral part of generation process itself, since it affects learning speed, quality of synthesized samples and lay foundation for later applications. This report presents series of KVAE tokenizers for audio, image and video, all designed for subsequent text-conditioned generation: KVAE-Audio, a continuous full-band 48 kHz tokenizer with a 50 Hz latent of 64 channels; KVAE-3D -- two causal video tokenizers for 4x16x16 and 4x8x8 compression; KVAE-2D, an image model, compressing input by factor of 8 with 32 channels. We demonstrate that reconstruction (PSNR, LPIPS, PESQ, etc.) and generation results on objective (Frechet Distance, CLIP score, CLAP score, etc.) and subjective (side-by-side evaluation) metrics matches or surpasses frontier opensource tokenizers, such as VAEs from Wan-2.2, HunyuanVideo-1.5, FLUX.2, MovieGen, StableAudio and MMAudio. Considering difficulty of development, we share with community training details, model selection method and ablation on design choices. The code is publicly available at https://github.com/kandinskylab/kvae and https://github.com/kandinskylab/kvae-audio.

Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov +11

Kandinsky Lab

Visual Tokenizers Star-Vae Tokenizer Generative Models Latent Variable Data Compression Methods

Aug 5, 2026cs.CV

MOSAIK: Multi-Patch Content-Aware Spatial Allocation of Image Tokens for Efficient Generation

Pixel-space diffusion models avoid the reconstruction ceiling of latent diffusion models by generating directly in image space. However, their substantially higher token count makes generation expensive due to the quadratic complexity of self-attention. Several existing efficiency methods reduce this cost by using larger patches at selected denoising steps, thereby representing the image with fewer tokens. Yet, each step still uses a single patch size uniformly across the entire image, overlooking that different regions suffer different fidelity losses when coarsened. We introduce MOSAIK, a damage-guided framework that varies patch size across regions and denoising steps. MOSAIK adapts the PixelDiT backbone to generate arbitrary heterogeneous patch layouts, and a lightweight predictor uses intermediate denoising features to estimate the fidelity loss caused by coarsening each region. Given a token budget, our damage-guided layout predictor assigns fine patches to sensitive regions and coarse patches elsewhere. Remarkably, while reducing FLOPs by 70% and token count by 83%, MOSAIK matches the full-compute PixelDiT on GenEval and its DPG-Bench score drops by only 1.0 point. Compared to diverse efficiency paradigms, including temporal patch scheduling and feature caching, our approach delivers highly competitive performance at moderate budgets and consistently outperforms these baselines in highly constrained compute regimes.

Mohammadreza Hami, Mohammadreza Samadi, Chao Gao +1

Huawei Technologies Canada

Visual Tokenizers Iterative Denoising Methods Mosaic Structural Damage

Aug 3, 2026cs.CV

Token Radius Attention for Efficient Video Generation

Video Diffusion Transformers (VDiTs) enable high-fidelity generation but incur quadratic cost from dense 3D self-attention. Existing head- and block-level sparse methods share computation budgets across queries, overlooking token-specific attention demand. We observe that retained density varies across queries yet correlates log-linearly with attention entropy, while dominant interactions form query-centered neighborhoods with token-dependent radii. Based on these findings, we propose Token Radius Attention (TRA), a training-free framework that maps query entropy to an analytic token budget and converts it into a temporally decayed radius without explicit key ranking. Fused entropy extraction, warm-up reuse, and block-sparse mask construction further reduce overhead. Across seven Wan2.1, Wan2.2, and HunyuanVideo T2V/I2V configurations, TRA retains only 9-19% of attention interactions and achieves 1.56x-2.05x speedup with competitive generation quality. Code is available at https://github.com/IF-LAB-PKU/Token-Radius-Attention.

Jiayu Chen, Zhikun Jiang, Maoliang Li +6

School of Computer Science, Peking University · School of Electronics Engineering and Computer Science, Peking University · School of Computer Science and Engineering, Beihang University +2

Spatio-Temporal Attention Visual Tokenizers Neighbors

Jul 21, 2026cs.CV

VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers

Vector Quantization (VQ) underpins modern discrete visual tokenization. However, training quantization modules for state-of-the-art VQ-based models requires significant computational resources which, in practice, all but prevents the development of novel, cutting-edge VQ techniques under resource constraints. To address this limitation, we propose {\bf VQ-Transplant}, a simple framework that enables plug-and-play integration of new VQ modules into frozen, pre-trained tokenizers by replacing their native VQ modules. Crucially, the proposed transplantation process preserves all encoder-decoder parameters, obviating the need for costly end-to-end retraining when modifying the quantization method. To mitigate decoder-quantization mismatch, we introduce a lightweight decoder adaptation strategy (trained for only 5 epochs on ImageNet-1k) to align feature priors with the new quantization space. In our empirical evaluation, we find that VQ-Transplant allows obtaining near state-of-the-art reconstruction fidelity for industry-level models like VAR while reducing the training cost by 95%. VQ-Transplant democratizes quantization research by enabling resource-efficient integration of novel VQ techniques while matching industry-level reconstruction performance.

Xianghong Fang, Yuan Yuan, Dehan Kong +1

University of Toronto · 2Boston College · 3Vijil

Residual Vector Quantization Visual Tokenizers Retraining Chronic Kidney Disease

Jul 20, 2026cs.CV

Pixel-Space Diffusion Transformers

Latent diffusion models (LDMs) enable efficient high-resolution image synthesis by denoising in a VAE-compressed latent space. However, fixed visual tokenizers can discard fine textures and structural details, while separate representation and diffusion training creates a mismatch between reconstruction and generation objectives. These limitations have renewed interest in pixel-space diffusion, which models raw pixels directly, removes the VAE bottleneck, and supports end-to-end optimization. This formulation better matches the demands of high-fidelity generation but introduces challenges in high-dimensional modeling, including noise scheduling, loss weighting, token efficiency, and scalable architecture design. Pixel-space modeling also offers a promising basis for unified multimodal systems: raw pixels, text, and task conditions can be represented in a shared token space and jointly processed by a single Transformer, narrowing the gap between visual understanding and generation. This paper reviews Pixel-Space Diffusion Transformers (pDiTs) from the perspectives of model architecture, continuous generative mechanisms, and unified multimodal modeling. We summarize representative methods, identify key technical challenges, and discuss future directions toward high-fidelity, end-to-end vision foundation models that integrate generation and understanding.

Renye Yan, Jikang Cheng, You Wu +8

Peking University, China · Nanjing University, China · Stanford University, USA +3

Diffusion Transformers Visual Tokenizers Transformer Architectures

Jul 18, 2026cs.CV

Test-Time Registers as Global Priors for Tokenized Image Generation

Attention-based models often develop attention sinks, where a small number of tokens repeatedly attract attention and accumulate unusually large activations. In vision transformers, these outliers are closely related to registers, which have been diagnostically linked to global, low-frequency image structure. Existing work has largely studied registers through interpretability analyses and linear probes, leaving open whether they can be operationalized as plug-and-play signals for generation without retraining. We revisit this question in tokenized image generation. Using OpenCLIP and DINOv2 on ImageNet, we find that test-time register features exhibit stronger low-frequency concentration than both [CLS] readouts and patch-mean features, and show a consistent (albeit moderate) correlation with pixel-space DCT low-frequency energy. Motivated by these diagnostics, we introduce RegToken, a training-free procedure that converts register structure into a small set of global prior tokens by (i) NFN-based layer localization, (ii) TokenRank-guided subspace extraction, and (iii) a projection-and-conservation update on the register subspace. Inserted into a frozen compact 1D token generation pipeline, RegToken improves ImageNet generation and alignment metrics (e.g., FID-5k 20.5 to 20.1, SigLIP 3.6 to 3.9) without modifying pretrained weights, and accelerates test-time optimization (Steps@

τ

74 to 52). Overall, our results suggest that structures often viewed as attention artifacts can be repurposed as lightweight global priors for tokenized generation.

Cheng-Yao Hong, Yifan Wang, Yuewei Lin +1

Stony Brook University · Brookhaven National Laboratory

Visual Tokenizers Single-Cell Foundation Models Text-To-Image Prior Knowledge Integration Graph-Coherent Low-Frequency Ones Test Time

Jul 10, 2026cs.CV

SVF-CR: Synchronized Visual-Facial Cross-Refinement for Multimodal Ambivalence and Hesitancy Recognition

Ambivalence and hesitancy are subtle behavioral states that are expressed through a combination of verbal content, facial behavior, visual context, and acoustic cues. Effective recognition therefore requires not only extracting informative unimodal representations, but also modeling how temporally aligned behavioral evidence interacts across modalities. In this paper, we propose a synchronized visual-facial cross-refinement framework (SVF-CR) with pairwise multimodal evidence fusion for ambivalence and hesitancy recognition. The proposed method first extracts whole-video segment tokens and cropped-face segment tokens using the same temporal partition. The synchronized visual and facial tokens are refined through intra-modal self-attention and bidirectional visual-facial cross-attention, allowing whole-video context and local facial behavior to mutually refine each other before evidence construction. We then construct segment-level visual-facial evidence using consistency and discrepancy modeling, followed by temporal self-attention and attention pooling. Textual and acoustic features are lightly refined through context self-attention and are fused with the enhanced visual-facial evidence at the final decision stage using pairwise evidence fusion. Experiments on the BAH (Behavioral Ambivalence/Hesitancy) public evaluation split show that the proposed synchronized visual-facial cross-refinement improves public macro-F1 over both global visual-face token fusion and synchronized evidence baselines, achieving a public macro-F1 of 0.7156. Code is available at : https://github.com/hiinnnii/BAH-Challenge-ECCV2026\_SVF-CR.

Hyein Park, Namho Kim, Junhwa Kim

Dept. of AI Software Convergence, Konyang University · Korean Broadcasting System (KBS)

Facial Expression Recognition Attitude Visual Tokenizers

Jul 10, 2026cs.CV

Subtoken Vision Transformer for Fine-grained Recognition

We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transformers compress each fixed-size patch into a single token, although fine-grained distinctions often depend on localized variations within only a few patches. SubViT addresses this mismatch by representing discriminative patches with multiple subtokens while retaining the original token sequence for global context, thereby allocating additional capacity where it is most needed. Since attention heads encode complementary semantics and extracting attention maps at inference requires an extra backbone forward, we adopt a two-stage training strategy. Stage 1 fine-tunes the ViT using subdivision regions sampled from random attention heads, exposing the model to diverse subdivision patterns. Stage 2 identifies informative attention maps through feature-degradation distances and distills them into a lightweight single-map router, which directly predicts deterministic token-importance scores without a separate attention forward. We evaluate SubViT on Generalized Category Discovery (GCD), a challenging task requiring both fine-grained discrimination and generalization to unlabeled novel categories. Across CUB, FGVC-Aircraft, and Stanford-Cars, SubViT improves the average novel-category accuracy of DINOv2 from

81.3\%

to

84.7\%

, with only

0.50

ms additional latency and

3.4\%

more FLOPs, while reducing latency by

73.8\%

relative to Retina Patch. Code: \href{https://github.com/jiezhu23/SubViT_ACCV26}{SubViT}.

Jie Zhu, Ivy Zhang, Minchul Kim +1

Michigan State University · Cranbrook Kingswood School · University of North Carolina at Chapel Hill

Self-Supervised Vision Transformers Visual Tokenizers Fine-Grained Perception Transformer Architectures

Jul 9, 2026cs.CV

VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval

Open-vocabulary object detection and segmentation aim to recognize arbitrary objects beyond predefined categories. Although recent vision-language and reference-based approaches have significantly advanced this field, they often rely on text prompts, limited visual examples, or expensive feature matching procedures, making them difficult to scale to large and continuously expanding object repositories. In this work, we propose VocaDet, a sample-driven open-vocabulary object detection and segmentation framework that learns object concepts directly from user-provided positive and negative sample collections without model retraining. The key idea is to transform continuous visual representations into discrete visual vocabularies and perform efficient retrieval-based recognition through a scalable vector database. Specifically, we employ DINOv3 as the visual feature extractor and apply agglomerative clustering with adaptive clustering sensitivity to generate multi-granularity visual tokens. These visual tokens, together with position-debiased representations and spatial topology information, are stored as expandable object memories in a vector database. During inference, query images are converted into visual tokens and efficiently matched against the stored object memories for object localization and segmentation. Furthermore, a background filtering mechanism is introduced to remove frequently occurring background patterns and reduce redundant retrieval operations in practical fixed-camera scenarios. Experiments on the UA-DETRAC dataset demonstrate that VocaDet achieves effective open-vocabulary detection performance without conventional detector training, while supporting continuously expandable recognition capability as additional positive and negative samples are accumulated.

ZhiXin Sun

PowerChina Zhongnan Engineering Corporation Limited

Open-Vocabulary Object Detection Semantic Segmentation Visual Tokenizers Vector Database Semantic Memory

Jul 1, 2026cs.CV

SpiralFovea: Input-Adaptive Foveated Tokenization as a Third Lever of Resource-Adaptive Inference

Most adaptive-inference techniques for foundation models change what the model does - early exit, MoE routing, KV-cache compression, dynamic attention sparsity. The input that hits the backbone, however, remains a fixed-grid tokenisation indifferent to image content. We argue that this is a missed lever. We present SpiralFovea, a parameter-free, input-adaptive tokeniser in which token identity, location, scale, and count are all functions of local visual entropy and selection completes before any backbone parameter is queried. Around content-driven hotspot anchors, multi-scale spiral rings produce <= 78 patches that replace the standard 196-patch ViT grid at the input stage. Across four canonical fine-grained benchmarks, SpiralFovea yields +1.7-2.1 pp accuracy with a 60% reduction in input tokens, an 84% reduction in self-attention FLOPs at every transformer layer, and 18-29% throughput gains over the matched static tokenisation baseline. A controlled ablation on CUB-200-2011 Genus across four backbones reveals a clean diagnostic: the gain magnitude tracks inversely with the strength of the backbone's whole-image positional prior, isolating self-supervised foundation models as the regime where input-adaptive tokenisation is most valuable.

Kyan Mahajan, Mohammad Saqlain

Indian Institute of Information Technology, Allahabad, Uttar Pradesh, India.

Parameter-Efficient Fine-Tuning Methods Wireless Foundation Models Visual Tokenizers

Jun 30, 2026cs.CV

Steal the Patch Size: Adversarially Manipulate Vision-Language Models

We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and input preprocessing pipeline. The key idea is a task-level side channel induced by ViT-style patchification: when a synthetic grid image is aligned with the hidden patch grid, boundary cues are erased at tokenization, causing periodic accuracy drop. By sweeping the grid cell size and measuring these collapses, we infer the patch size; by introducing padding and a consistency-check test, we further identify whether preprocessing is dynamic- or fixed-resolution and recover the target resize resolution. Across open-source Qwen-VL variants and proprietary models including GPT and Claude, we reliably recover tokenizer-related parameters. Finally, we show that such leakage enables preprocessing-aware transfer attacks and model-targeted adversarial manipulation.

Kai Hu, Akash Bharadwaj, Weichen Yu +1

Carnegie Mellon University, Pittsburgh, USA.

Visual Tokenizers Preprocessing

Jun 29, 2026cs.CV

Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis

We propose Nemotron-Labs-Diffusion-Image, a state-of-the-art masked discrete diffusion model (MDM) for high-resolution text-to-image synthesis. Compared with prior work on masked image generation, Nemotron-Labs-Diffusion-Image addresses two key challenges. First, unlike continuous diffusion models which progressively refine latent representations across the entire image, standard MDMs lack self-correcting capability because discrete tokens cannot be modified once they are unmasked. Second, although increasing the vocabulary size of discrete image tokenizers improves reconstruction fidelity, it introduces optimization difficulties for generative modeling as the per-token training signal becomes increasingly sparse. To address the first challenge, Nemotron-Labs-Diffusion-Image incorporates a token-editing mechanism that enables the model to dynamically revise already-unmasked tokens during inference, similar to how a sculptor iteratively refines their work. To tackle the second challenge, we propose a Grouped Cross-Entropy (GCE) objective that assigns positive learning signals to tokens neighboring the ground truth in embedding space, thereby alleviating signal sparsity. To further improve training efficiency, we implement a custom fused operator for GCE that significantly reduces VRAM usage in large-vocabulary settings. Experimental results demonstrate that these innovations substantially improve both training efficiency and image fidelity of masked discrete image generators, achieving a score of 0.90 on GenEval, 86.9 on DPG and 10.76 of HPSv3.

Shufan Li, Greg Heinrich, Hanrong Ye +4

NVIDIA

Text-To-Image Diffusion Models Diffusion Models Visual Tokenizers Synthesis

Jun 25, 2026cs.CV

TaskTok: Delving into Task Tokens for Task-driven Image Restoration

While traditional image restoration focuses on perceptual quality, Task-Driven Image Restoration (TDIR) aims to maximize the performance of downstream high-level vision tasks. Recent approaches leveraging generative priors have shown promise for TDIR; however, they typically suffer from computational inefficiency and potential semantic alteration by indiscriminately updating all latent tokens. In this paper, we posit that not all visual information is equally important for machine perception. Through an analysis of the latent token space, we observe that task-relevant cues are unevenly distributed across the token sequence, exhibiting index-wise specialization. This suggests that selectively refining a subset of tokens can be sufficient for task-driven objectives. Leveraging this insight, we propose TaskTok, a novel framework that selectively restores only task-relevant tokens via a learnable token switch and a lightweight token refinement module. Extensive experiments across image classification, semantic segmentation, and object detection demonstrate that TaskTok significantly enhances task performance with high computational efficiency. The source code is available at https://github.com/jimmy9704/TaskTok

Hongjae Lee, Sojung Kang, Jaeseong Yu +1

Korea University

Image Restoration Visual Tokenizers Self-Supervised Vision Transformers Compact Latent Sensor Tokens Task-Relevant Information

Jun 19, 2026cs.CV

Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space

Dataset distillation (DD) has proven to reduce training cost while preserving accuracy. While promising, the factors that make one distilled dataset more effective than another remain poorly understood. In this work, we investigate this question through the lens of discrete visual tokenizers. Whereas many prior DD efforts emphasize matching global data distributions, we suggest that the effectiveness depends on which semantic concepts are captured and how they are composed. Discrete visual tokenizers provide a finite vocabulary that enables direct statistical analysis of such compositional structure. Through quantitative analysis of token-level statistics, we introduce the structural score to measure the adequacy of token compositions. We observe that distilled datasets with balanced token composition yield higher validation performance. On the other hand, divergence from the original data does not necessarily harm performance. We further show that samples with high structural scores in the discrete token space can effectively guide diffusion-based DD. Our findings highlight the importance of token composition in dataset effectiveness, offering a principled complement to distributional similarity considerations in DD.

Yue Cao, Jianyang Gu, Vyacheslav Kungurtsev +4

The University of British Columbia · The Ohio State University · Czech Technical University in Prague +1

Diffusion-Based Dataset Distillation Dataset Distillation Visual Tokenizers Token-Level Uncertainty

Jun 18, 2026cs.CV

Variable-Length Tokenization via Learnable Global Merging for Diffusion Transformers

Latent Diffusion Models (LDMs) have become dominant in visual synthesis, but their quality-compute trade-off is largely constrained by the tokenizer's fixed compression ratio. Variable-length tokenizers (VLTs) promise adaptive compression by varying token counts, allowing diffusion models to flexibly balance quality and compute. However, conventional VLTs modulate length by truncating ordered token sequences, which makes token semantics depend on token position and breaks representational alignment across lengths. This leads to a cross-length shift in the latent distribution that hinders a single variable-length diffusion model from operating effectively. To address this, we propose a novel variable-length tokenizer that modulates length by merging tokens. We show that encouraging similar tokens to merge enables direct cross-length representation alignment when the diffusion transformer operates according to the merging pattern. Since conventional merging methods are data-dependent, making the merging pattern inaccessible during generation, we introduce learnable global merging, which is data-independent, to ensure compatibility with diffusion transformers. On ImageNet 256

\times

256 generation, our merging-based variable-length tokenizer integrated with a diffusion transformer achieves a superior gFID-compute trade-off compared to prior VLT methods. Code is available at this https URL

Dong Hoon Lee, Seunghoon Hong

Kim Jaechul Graduate School of AI, KAIST, Daejeon, South Korea · School of Computing, KAIST, Daejeon, South Korea

Diffusion Transformers Visual Tokenizers Diffusion Models Tokenizer Hierarchical Semantic Alignment

Jun 16, 2026cs.CV

Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification

Unified Multimodal Modeling aims to integrate visual understanding and generation within a single system. However, existing approaches typically rely on two disparate visual tokenizers, which splits the representation space and hinders truly unified modeling. We propose UniAR, a unified autoregressive framework where a single discrete visual tokenizer serves as the key bridge between understanding and generation, enabling a shared context in which the model can directly interpret its own generated visual tokens without additional re-encoding. UniAR adapts a pretrained vision encoder with multi-level feature fusion and a lookup-free bitwise quantization scheme, preserving both high-level semantics and low-level details while scaling the effective visual vocabulary at minimal cost. Building on this, the unified autoregressive model adopts parallel-bitwise-prediction to jointly predict spatially grouped, multi-level visual codes, substantially reducing visual sequence length and accelerating generation. Finally, a diffusion-based visual decoder operates on discrete visual tokens to decode high-fidelity images. Through large-scale pre-training, followed by supervised fine-tuning and reinforcement learning, UniAR achieves state-of-the-art performance on image generation and image editing while remaining competitive on multimodal understanding benchmarks. The project page is available at https://sharelab-sii.github.io/uniar-web.

Wujian Peng, Lingchen Meng, Yuxuan Cai +7

Institute of Trustworthy Embodied AI, Fudan University · Shanghai Innovation Institute · Qwen Team, Alibaba Inc.

Visual Tokenizers Autoregressive Language Models Autoregressive Model

Jun 16, 2026cs.CV

TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization

Video tokenization is fundamental to scalable video generation, as the number of tokens directly determines the computational cost and the length of videos that can be modeled. Existing tokenizers mainly improve scalability by compressing videos into fewer tokens, but they often continue to represent persistent content, such as static backgrounds and consistent object appearances, repeatedly across frames and chunks. In this paper, we propose \textbf{TivTok} (\textit{Time-Invariant Tokenizer}), a reuse-aware video tokenizer that makes persistent information reusable across time. TivTok represents a clip with Time-Invariant (TIV) tokens that encode information shared across frames and Time-Variant (TV) tokens that encode frame-specific residuals. To obtain this factorization, we introduce Scope-Induced Factorization (SIF), which assigns different attention scopes to the two token groups: TIV tokens attend to the full clip, whereas each TV token only accesses its corresponding frame together with the TIV tokens. In the decoder, Invariant Broadcasting (IB) reuses the same TIV tokens across frames and chunks for parallel reconstruction and long-video tokenization. Experiments show that TivTok achieves an rFVD of 12.65 on the standard

16{\times}256{\times}256

benchmark and improves compression efficiency by 2.91

\times

for 128-frame videos compared with the evaluated baselines, while using only 1.1% of the tokens required by downsample-based tokenizers in our evaluation.

Weiliang Chen, Yuanhui Huang, Xuebo Wang +1

Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China · Department of Automation, Tsinghua University, Beijing, 100084, China · Kuaishou Technology, Beijing, China

Visual Tokenizers Video Compression

Jun 11, 2026cs.CV

RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

This work presents RepWAM, a representation-centric world action model (WAM) built on representation visual-action tokenizers. Existing WAMs typically inherit reconstruction-oriented video tokenizers from pretrained video generation models. Although these tokenizers preserve visual fidelity, pixel reconstruction alone provides limited guidance for learning instruction-following dynamics that connect future prediction with robot control. To address this, we explore a semantic visual-action latent space for representation-centric world action modeling. Specifically, we train a representation visual-action tokenizer that maps visual inputs into aligned visual and latent action tokens. We then pretrain our WAM to jointly model future visual states and the latent actions that connect them under language instructions, followed by adaptation to real robot trajectories for closed-loop manipulation. Experiments on real-world manipulation tasks and simulation benchmarks show that RepWAM delivers strong performance across diverse manipulation settings, while ablations highlight the value of semantic visual-action tokenization over reconstruction-oriented alternatives. These results establish representation visual-action tokenization as a promising foundation for world action models and a step toward generalist robot policies. Code and weights will be available at https://github.com/wdrink/RepWAM.

Junke Wang, Qihang Zhang, Shuai Yang +5

Institute of Trustworthy Embodied AI, Fudan University · 2Robbyant, Ant Group · 3Hongkong University of Science and Technology

Efficient World-Action Model Discrete Action Tokenizers World Models Visual Tokenizers

Jun 11, 2026cs.CV

HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space. In this paper, we present HYDRA-X, the first UMM that unifies image and video tokenization within a single Vision Transformer (ViT). Our design is driven by two core challenges: efficiently injecting spatiotemporal reconstruction capability into a native ViT, and embedding image- and video-level semantic awareness into the latent space. To address the first, comprehensive ablations reveal two key findings: (1) frame-level causal temporal attention suffices for visual reconstruction, whereas full spatiotemporal attention degrades it; and (2) hierarchical temporal compression substantially outperforms single-step alternatives. To tackle the second, we propose a lightweight decompressor that upsamples temporally compressed features under joint image-video teacher supervision, thereby enforcing complementary semantic structures within the compact latent space. Building on this holistic tokenizer, we further propose a principled improvement of the editing pipeline: source-target interaction should occur at the latent level inside the tokenizer rather than at the semantic level inside the LLM, substantially improving editing consistency and accelerating convergence. Instantiated at the 7B dense model, HYDRA-X achieves strong performance across image and video understanding and generation tasks, paving the way for future unified-tokenizer UMMs.

Guozhen Zhang, Xuerui Qiu, Yutao Cui +11

Nanjing University · Work done during internship at Tencent Hunyuan. · CASIA +3

Visual Tokenizers Fine-Grained Video Understanding Self-Supervised Vision Transformers

Jun 5, 2026cs.CV

AdaTok: Self-Budgeting Image Tokenization with Quality-Preserving Dynamic Tokens

Image tokenizers, from 2D grids to recent 1D sequences, typically encode every image with the same fixed number of tokens. Yet visual complexity is highly heterogeneous, so a uniform budget overspends on simple inputs and underserves complex ones. Existing elastic tokenizers expose variable-length reconstructions, but often leave token length as a deployment-time operating point, a search target, or an external prediction rather than an output of the tokenizer itself. In this work, we ask whether a discrete visual tokenizer can budget itself in one pass. Our central finding is that actionable elasticity requires a representation--allocation co-design: prefixes must remain decodable across budgets, and the tokenizer must learn which prefix each image needs. We propose AdaTok, a self-budgeting discrete 1D tokenizer. AdaTok combines Prioritized Representation Learning, which orders tokens with nested tail masking and resolves budget-dependent semantic shift through Multi-Head LoRA decoder heads, with Adaptive Token Allocation, which trains a lightweight deterministic-group GRPO policy over candidate budgets. Dynamic Pareto Weighting balances fidelity and efficiency during policy training without manual trade-off sweeps. On ImageNet-1K, AdaTok-Full reaches rFID 1.31 at 256 tokens, while AdaTok-Adaptive attains rFID 1.50 using only ~118 tokens on average, outperforming discrete 1D baselines at comparable budgets. In autoregressive image generation, the shorter adaptive representation yields ~2.1x throughput over a fixed 256-token decode, suggesting that visual token count can be learned as a content-conditioned output rather than set as a fixed hyperparameter.

Xiaocheng Lu, Yuxi Chen, Jie Zhang +5

The Hong Kong University of Science and Technology · The Hong Kong Polytechnic University

Visual Tokenizers Long Visual-Token Sequences Tokenizer Autoregressive Image Generation

Jun 4, 2026cs.CV

Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting

Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence. Current continuous-regime approaches achieve this via iterative binarised searches or trained neural regressors, while discrete methods often require a full-rate decoder pass to estimate information content. We demonstrate that such computational overheads are not strictly necessary. We show that the latent space of a frozen continuous video tokeniser inherently encodes temporal redundancy that can be exploited directly: spatial positions whose latent representations change minimally between consecutive frames carry near-zero additional information. We introduce a parameter-free adaptive token allocation mechanism that applies a fixed threshold to per-position temporal-L1 differences, identifying and dropping redundant latent positions. Consequently, the compression rate emerges naturally from the input content rather than being enforced top-down: static scenes get compressed aggressively, while highly dynamic sequences retain more tokens. To reconstruct the dropped positions, we propose the Latent Inpainting Transformer (LIT), a lightweight factorised spatial-temporal attention architecture. The resulting inference pipeline is highly efficient, requiring only a single encoder pass and one LIT forward pass, eliminating the need for auxiliary routing networks. Evaluations across TokenBench and DAVIS, which are the standard benchmarks used by recent tokenisers~\cite{infotok, agarwal2025cosmos}, indicate that our framework yields meaningful, content-driven token allocation while maintaining competitive reconstruction fidelity, and delivers a

31\times

inference-time speedup over the continuous adaptive baseline (ElasticTok-CV) and an

\approx2\times

speedup over the discrete information-theoretic baseline (InfoTok)

Kevin Dave, Sai Aditya Patkuri, Chhaya Kumar Das +3

Phronetic AI · IISc Bangalore · IIT Bombay

Visual Tokenizers Spatio-Temporal Attention Redundancy

Jun 4, 2026cs.LG

Balancing Image Compression and Generation with Bootstrapped Tokenization

Despite progress in image tokenization, standard methods encode redundant information by mixing all granularities within each token, thus redundancy persists between tokens. The mix of information of different granularity also complicates the training of generators. This paper introduces SelfBootTok, a method that resolves this by cleanly decomposing information into global and local token groups. Through self-bootstrapped learning, the model predicts local details exclusively from global tokens, shifting the burden of visual details from the generator to the tokenizer. Consequently, our generator is far more efficient, requiring only global tokens and reducing computation by approximately 40%, while delivering superior reconstruction and generation. Moreover, this paradigm scales elegantly: by leveraging more data or parameters to self-supervise local representation learning, SelfBootTok achieves a new state-of-the-art gFID score of 1.56 using only 64 tokens.

Haozhe Chi, Jinghan Li, Hao Jiang +4

1Peking University · 2Central Media Technology Institute, Huawei

Visual Tokenizers Autoregressive Image Generation Single-Cell Foundation Models Tokenizer Generators Representation Learning+1

Jun 3, 2026cs.CV

ChannelTok: Efficient Flexible-Length Vision Tokenization

Leading flexible vision tokenizers achieve SOTA quality at an extreme cost, relying on parameter-heavy backbones and slow, multi-step generative decoders. We depart from this complex, spatial-token paradigm and introduce a simple, lightweight, and fast channel-wise flexible-length tokenizer. Our method treats each latent channel as a visual token, enabling a parameter-efficient CNN-Transformer hybrid backbone. Furthermore, employing a stochastic tail-dropping paradigm during training naturally forces channels to organize by semantic importance. This allows for flexible compression at inference by simply retaining the first

k

channels, and naturally enables variable-length autoregressive image generation. We validate our approach through extensive experiments on ImageNet, demonstrating consistent quality across diverse token budgets. The results establish a new quality-efficiency frontier: our model achieves state-of-the-art perceptual quality (rFID 2.92) while being

8.6\times

faster in decoding and

2.1\times

smaller (159M params) than the next-best alternative. Our work establishes channel-wise tokenization as a powerful and practical paradigm for efficient visual representation. Project page: https://channeltok.github.io

Sukriti Paul, Arpit Bansal, Tom Goldstein

University of Maryland, College Park

Visual Tokenizers Cnn-Transformer Tradeoff Imagenet

Jun 2, 2026cs.CV

Diffusing in the Right Space: A Systematic Study of Latent Diffusability

Latent diffusion models leverage visual tokenizers to compress images into latent spaces for efficient generative modeling. However, better reconstruction quality of a tokenizer does not necessarily translate into better generation quality, suggesting that latent representations should be evaluated not only by fidelity but also by their diffusability. Recent studies have proposed diverse explanations for diffusion-friendly latent spaces, including semantic separability, affine equivariance, distribution uniformity, spatial structure, spectral smoothness, and manifold continuity. Yet these properties are often validated on a limited set of tokenizers, leaving it unclear which factors are most predictive of downstream generation quality and whether such conclusions hold beyond the specific settings in which they are introduced. In this work, we conduct a systematic study of latent diffusability by training a large collection of tokenizers with diverse regularization strategies, architectures, and latent configurations, and evaluating them with multiple downstream diffusion backbones. Our analysis identifies several latent properties that consistently correlate with generation quality and exhibit strong generalization across experimental settings. Beyond existing metrics, we introduce Velocity Irreducible Variance (VIV), a measure of velocity ambiguity induced by trajectory crossings. Extensive experiments show that VIV is one of the most stable predictors of generation quality.

Tianxiong Zhong, Xingye Tian, Xuebo Wang +2

Kling Team, Kuaishou Technology

Visual Tokenizers Diffusion Dynamics Generative Models Systematic Study

Jun 1, 2026cs.CV

FocusDiT: Masking Queries in Diffusion Transformers for Fine-grained Image Generation

Diffusion transformer (DiT) has been widely adopted in the generative diffusion field, advancing the denoising of query tokens through attention and Feed-Forward (\text{FFN}) layers. FFN actually acts as the key-value vocabulary for decoding visual contents where the value embeds the visual semantical knowledge. We present that focusing on critical query tokens corresponding to more complex details and encouraging the model to improve these tokens is essential for fine-grained visual generation. To this end, we propose FocusDiT, which applies a Masking scheme to focus on critical query tokens that are exclusively fed into FFN. The masked queries can retrieve visual tokens from the FFN vocabularies, and use them to decode their visual details. Extensive text-to-image experiments validate the effectiveness of token masking in enhancing generative performance.

Xueji Fang, Liyuan Ma, Jianhao Zeng +3

Zhejiang University · Westlake University · Hangzhou, China

Diffusion Transformers Visual Tokenizers Text-To-Image Queries

Jun 1, 2026cs.CV

Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning

Discrete visual tokens should provide a compact representation for both token-based world modeling and planning in autonomous driving. However, most tokenizers are inherited from image generation and are optimized mainly for pixel reconstruction, which may leave a gap between what is easy to generate and what is useful to decode for driving decisions. We present a representation-guided and geometry-enhanced tokenizer that learns discrete tokens under joint supervision. The tokenizer aligns its discrete bottleneck with a frozen DINO feature space through feature decoding, while preserving appearance via RGB reconstruction with perceptual and adversarial losses. To inject geometric state-related cues, we add adjacent-frame depth and relative-pose supervision during training and stabilize joint objectives with multi-codebook quantization. We evaluate the same learned tokens with a lightweight planning readout and a GPT-style next-token world model. Experiments on NAVSIM show improved reconstruction fidelity and representation consistency, competitive planning performance under a fixed decoder, and better generative quality under matched settings.

Ziyang Yao, Zeyu Zhu, YunCheng Jiang +2

Peking University · Xiaomi EV

Visual Tokenizers Autonomous Driving Long Visual-Token Sequences Geometric Cues World Models Planning

Jun 1, 2026cs.CV

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering

Visual Autoregressive (AR) models generate images by predicting discrete tokens that are decoded by a visual tokenizer. Despite demonstrating strong overall image generation ability, they still underperform on text rendering with blur strokes and disrupt letter shapes. In this work, we trace this limitation to the visual tokenizer, which struggles to reconstruct fine-grained detail. Improving the tokenizer is straightforward but expensive, as it necessitates retraining both the tokenizer and the AR model. Can we improve text rendering performance of AR models without retraining the existing tokenizer and AR model? To achieve this, we propose the Residual Decoder Adapter(RDA) that upgrades an existing tokenizer post-hoc without changing its token space. Specifically, it refines the decoder output of the visual tokenizer by introducing two novel components: (i) a paired codebook that shares the token distribution with the original one; (ii) a parallel branch to learn the tiny differences (residual) between the reconstructed image and the ground-truth images in the pixel space. This residual design allows us to enhance the tokenizer non-invasively while preserving compatibility with prior AR models. RDA substantially improves text rendering significantly by a large margin. For instance, we boost finetuned Janus-Pro OCR accuracy rises from 24.52% to 58.26% (TextVisionBlend), from 12.75% to 36.81% (StyledTextSynth) on competitive TextAtlas benchmark. The code is available at https://github.com/CSU-JPG/RDA

Dongxing Mao, Jinpeng Wang, Jiahao Tang +6

Central South University · University of Oxford · Microsoft Research

Autoregressive Image Generation Visual Tokenizers Visual Autoregressive Models Additive-Residual Selective Invariance Tokenizer Optical Character Recognition

May 31, 2026cs.CV

HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution

Vector-quantized (VQ) generative models have shown promising results in real-world image super-resolution (Real-ISR). However, existing methods typically rely on a monolithic latent space that entangles low-frequency structures with high-frequency textures. This entanglement forces a single codebook to capture a combinatorially complex set of structure-texture pairings, which constrains representational capacity and limits codebook utilization. To address this issue, we present HiTokSR, a hierarchical token prediction framework. Instead of using a single codebook, HiTokSR partitions the latent space along the channel dimension into frequency-aware groups, quantizing each with an independent sub-codebook. This coarse-to-fine design disentangles global structures from fine details, enhancing combinatorial expressiveness while circumventing the optimization instability of high-dimensional nearest-neighbor lookups. To further improve semantic consistency, our generator integrates priors from a vision foundation model via adaptive feature modulation, multi-scale class tokens, and a representation alignment loss. Additionally, we introduce an index-level perturbation strategy during decoder fine-tuning to bridge the train-test discrepancy in discrete token prediction. Extensive experiments on real-world benchmarks demonstrate that HiTokSR achieves state-of-the-art performance in both perceptual quality and reconstruction fidelity.

Mingxi Li

Real-World Image Super-Resolution Visual Tokenizers Autoregressive Image Generation Tokenizer Latent Space Representation-Alignment Loss+2

May 31, 2026cs.CV

Boundary-Protection W8A8 HiFloat8 Quantization for Large-Scale Text-to-Video Diffusion Transformers

We present a post-training quantization (PTQ) approach for Wan2.1-T2V-14B, a 14-billion-parameter text-to-video diffusion transformer, targeting the W8A8 HiFloat8 (HiF8) format on Ascend 910B NPUs. A central challenge in quantizing video DiT models is the heterogeneous activation distribution across transformer blocks: boundary blocks (the first and last few blocks) exhibit fundamentally different statistical properties from middle blocks, making uniform quantization ineffective. We conduct a systematic per-block activation analysis across all 40 WanAttentionBlocks and use the findings to motivate a boundary-protection strategy that retains the first two and last three blocks in BF16 while quantizing the remaining 35 blocks with W8A8 HiF8. The proposed PTQ method matches or marginally exceeds the BF16 baseline on all five VBench dimensions evaluated, indicating no measurable accuracy loss within the 5-prompt evaluation set. An ablation study over four protection configurations confirms that full boundary protection yields the highest average VBench score, validating the data-driven block selection. We additionally investigate quantization-aware training (QAT) as a complementary fine-tuning stage and analyze the conditions under which it fails to outperform plain PTQ on single-card hardware.

Yiming Zhao

University of Chinese Academy of Sciences Beijing, China

Text-To-Video Diffusion Models Video Diffusion Models Diffusion Transformers Post-Training Quantization Visual Tokenizers

May 29, 2026cs.CV

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging

Most visual tokenizers for image generation are bifurcated into two families with complementary limitations: continuous VAEs offer high-fidelity reconstruction but suffer from dense, entangled latents that are poorly suited for semantic control, whereas discrete VQ-based models enable autoregressive generation yet struggle with gradient sparsity, unstable training, and codebook collapse. In this work, we introduce MergeTok, a unified tokenizer that jointly optimizes continuous (VAE) and discrete (VQ) tokenizers within a encoder-decoder architecture, leveraging token merging techniques as a semantic bridge. By clustering similar tokens during encoding, MergeTok establishes a structural prior that provides dual supervision signals: (i) it imposes merged-token semantic alignment in the VAE branch, regularizing its latent space toward disentangled, semantic-aware representations; (ii) it derives group-wise constraints, promoting intra-group diversity and inter-group exclusivity that stabilize VQ training. MergeTok shows competitive reconstruction and generation performance on ImageNet-256, with substantially lower rFID than strong VAE and VQ models under matched token budgets, while producing semantically-organized token representations compatible with both autoregressive and diffusion generators. This shows that a single architecture can endow visual tokenizers with robust semantic organization and generator-friendly discreteness.

Luyuan Zhang, Siyuan Li, Zedong Wang +7

1Tsinghua University · 2Westlake University · 3Zhejiang University +3

Visual Tokenizers Visual Generation Conditional Variational Autoencoder Imagenet Merge

May 26, 2026cs.CV

Structure over Pixels: Learning Variable-Length Visual Programs

Discrete visual tokenizers map images to ordered sequences of tokens, providing a natural representation for structural scene descriptions. Most use a fixed sequence length, while adaptive methods often require post-hoc search or choose among a small set of rates that control the length. We propose STROP, a discrete tokenizer that learns both a visual program and its image-dependent active length. A length head is trained with a four-phase curriculum using local rate-distortion probes against frozen DINOv3 features, then predicts the active prefix in a single forward pass. At a matched rate of about

250

nominal bits per crop, the adaptive model improves segmentation over a separately trained fixed-length baseline on four benchmarks (by

1.6

-

3.1

mIoU), and it also beats a fixed

K{=}32

baseline that uses more bits. STROP programs also yield higher segmentation mIoU than FlexTok, One-D-Piece, and ALIT at similar or higher rates, under the same readout architecture and training protocol. STROP therefore learns useful per-image sequence lengths without post-hoc search or a predefined set of compression rates.

Piotr Wyrwiński, Kacper Dobek, Krzysztof Krawiec

Institute of Computing Science Poznan University of Technology, Poznan, Poland

Visual Tokenizers Semantic Scene Understanding Pixels Dense Prediction

May 25, 2026cs.CV

Channel-wise Vector Quantization

We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventional vector quantization, which assigns a discrete token to each patch feature vector, CVQ quantizes each channel of the feature map. This formulation represents an image as discrete levels of visual details, rather than as a grid of spatial patches. Based on CVQ, we introduce a new visual autoregressive framework with "next-channel prediction". Instead of rendering images patch by patch in raster order, our Channel-wise Autoregressive (CAR) model predicts image channels sequentially, producing progressively enriched visual details. Specifically, it first sketches global structure and then refines fine-grained attributes, akin to a human artist's workflow. Empirically, we show that: (1) CVQ achieves 100% codebook utilization with a 16K+ codebook size without any bells and whistles, and substantially improves reconstruction quality over conventional VQ; and (2) CAR attains a DPG score of 86.7 and a GenEval score of 0.79, demonstrating strong effectiveness for text-to-image generation.

Wei Song, Tianhang Wang, Yitong Chen +5

Shanghai Innovation Institute · Westlake University · Zhejiang University +2

Autoregressive Image Generation Visual Tokenizers Vector-Quantized Variational Autoencoder Residual Vector Quantization Autoregressive Model

May 20, 2026cs.CV

RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution

Discrete autoregressive (AR) text-to-image (T2I) models pair a VQ tokenizer with an AR policy, and current post-training pipelines optimize only the policy while keeping the VQ decoder frozen. Recent diffusion T2I work, exemplified by REPA-E, has shown that the VAE itself constitutes a key alignment bottleneck, yet no analogous investigation exists for discrete AR models. We show that policy-only optimization induces Latent Covariate Shift: as the policy evolves, the resulting token distribution diverges from the ground-truth distribution on which the decoder was trained, such that reward scores improve while decoded image quality degrades. To address this mismatch, we propose RankE, the first end-to-end post-training framework for discrete T2I generation. Rather than optimizing the policy against a fixed decoder, RankE co-evolves both components through alternating optimization: each module maximizes a ranking-based alignment objective while being regularized by a stability-preserving anchor suited to its parameter space. This co-evolution breaks the fidelity--alignment trade-off that plagues frozen-decoder approaches: on LlamaGen-XL (775M), standard RL improves CLIP but degrades FID, whereas RankE improves both simultaneously (FID 15.21, CLIP 33.76 on MS-COCO 30K). Consistent gains on Janus-Pro (1B) confirm that decoder co-evolution reliably converts reward optimization into pixel-space quality improvements.

Siyong Jian, Siyuan Li, Luyuan Zhang +5

1Westlake University · 2Zhejiang University · 3Tsinghua University +2

Text-To-Image Visual Tokenizers Co-Evolution Ranking

May 18, 2026cs.CV

Vision Foundation Models as Generalist Tokenizers for Image Generation

In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two key innovations: (1) a region-adaptive quantization framework to eliminate spatial redundancy in standard 2D grid features, and (2) a semantic reconstruction objective that aligns the decoded outputs with the VFM's representations to preserve semantic fidelity. Grounded in these designs, we propose VFMTok, a generalist visual tokenizer capable of operating seamlessly in both discrete and continuous latent spaces. VFMTok achieves substantial improvements in synthesis quality while drastically enhancing token efficiency. For discrete autoregressive (AR) generation, it accelerates model convergence by \textbf{3 times} and achieves a state-of-the-art gFID of \textbf{1.36} on ImageNet class-conditional synthesis. Similarly, for continuous-space generation, integrating VFMTok with a denoising model yields an exceptional gFID of \textbf{1.25}. Furthermore, because the latent space inherently captures rich spatial semantics, VFMTok enables high-fidelity class-conditional synthesis without classifier-free guidance (\textbf{w/o CFG}) across both generative paradigms, significantly accelerating inference speed. Beyond these remarkable empirical results, we systematically investigate the underlying mechanisms of our approach. We discover that the specific self-supervised learning objectives utilized during VFM pre-training dictate its effectiveness as a tokenizer. Specifically, a VFM jointly optimized with global contrastive learning and latent masked image modeling provides the optimal representations for image tokenization. These insights establish a strong foundation and offer valuable guidance for the design of future image tokenizers.

Anlin Zheng, Qi Han, Xin Wen +5

University of Hong Kong, Pokfulam, Hong Kong · StepFun

Visual Tokenizers Vision Foundation Models Image Generation Frozen Vision-Language Models Imagenet Data Generation

May 18, 2026cs.CV

WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens

Building a unified visual tokenizer is essential for bridging the gap between visual understanding and generation. Yet existing approaches struggle with the inherent conflict between these tasks, as a single token space is forced to support both high-level semantic abstraction and low-level pixel reconstruction. We propose WinTok, a concise hybrid tokenizer that achieves a win-win performance by explicitly decoupling the two objectives. WinTok supplements pixel tokens with a set of learnable semantic tokens, effectively mitigating cross-task interference without incurring the computational overhead of dual tokenizers. To further enhance understanding capability, we introduce an asymmetric token distillation mechanism: the semantic tokens are guided by pretrained semantic embeddings from any visual foundation model, enabling them to inherit strong discriminative power while maintaining flexibility. Across 10 challenging benchmarks, WinTok delivers consistent improvements in reconstruction, understanding, and generation. Trained on only 50M open-source data, WinTok surpasses the strong baseline UniTok by 11.2% in classification accuracy and achieves a competitive reconstruction rFID of 0.41, despite using substantially less training data. Code is released at https://github.com/markywg/WinTok.

Yiwei Guo, Shaobin Zhuang, Zhipeng Huang +4

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · WeChat Vision, Tencent Inc. · Shanghai Jiao Tong University

Visual Tokenizers

May 18, 2026cs.CV

A More Word-like Image Tokenization for MLLMs

Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the same form as text. However, the language model has been optimized to operate on discrete, semantically meaningful tokens, while prevailing visual projectors transform an image into a long stream of continuous and highly correlated embeddings. This causes the visual tokens to behave differently from the word-like units that LLMs are originally trained to understand. We propose a novel Disentangled Visual Tokenization (DiVT) that clusters patch embeddings into coherent semantic units, so each token corresponds to a distinct visual concept instead of a rigid grid cell. DiVT further adapts its token budget to image complexity, providing an explicit accuracy-compute trade-off modifying neither the vision encoder nor the language model. Across diverse multimodal benchmarks, DiVT matches or surpasses baselines with significantly fewer visual tokens, demonstrating robustness under limited token budgets, significantly reducing memory cost and latency while making visual inputs more compatible with LLMs. Our code is available at https://github.com/snuviplab/DiVT.

Hyun Lee, Hyemin Jeong, Yejin Kim +4

Seoul National University · Ewha Womans University

Long Visual-Token Sequences Visual Tokenizers Multimodal Large Language Models Vision Encoders Projection Heads

May 14, 2026cs.CV

Hierarchical Image Tokenization for Multi-Scale Image Super Resolution

We introduce a multi-scale Image Super Resolution (ISR) method building on recent advances in Visual Auto-Regressive (VAR) modeling. VAR models break image tokenization into additive, gradually increasing scales, using Residual Quantization (RQ), an approach that aligns perfectly with our target ISR task. Previous works taking advantage of this synergy suffer from two main shortcomings. First, due to the limitations in RQ, they only generate images at a predefined fixed scale, failing to map intermediate outputs to the corresponding image scales. They also rely on large backbones or a large corpus of annotated data to achieve better performance. To address both shortcomings, we introduce two novel components to the VAR training for ISR, aiming at increasing its flexibility and reducing its complexity. In particular, we introduce a) a \textbf{Hierarchical Image Tokenization (HIT)} approach that progressively represents images at different scales while enforcing token overlap across scales, and b) a \textbf{Direct Preference Optimization (DPO) regularization term} that, relying solely on the (LR,HR) pair, encourages the transformer to produce the latter over the former. Our proposed HIT acts as a strong inductive bias for the VAR training, resulting in a small model (300M params vs 1B params of VARSR), that achieves state-of-the-art results without external training data, and that delivers multi-scale outputs with a single forward pass.

Isma Hadji, Enrique Sanchez, Adrian Bulat +2

Samsung AI Center Cambridge, UK · Technical University of Iasi, Romania · Queen Mary University of London, UK

Generative Super-Resolution Visual Tokenizers Visual Autoregressive Models

May 12, 2026cs.CV

Spectral Vision Transformer for Efficient Tokenization with Limited Data

We propose a novel spectral vision transformer architecture for efficient tokenization in limited data, with an emphasis on medical imaging. We outline convenient theoretical properties arising from the choice of basis including spatial invariance and optimal signal-to-noise ratio. We show reduced complexity arising from the spectral projection compared to spatial vision transformers. We show equitable or superior performance with a reduced number of parameters as compared to a variety of models including compact and standard vision transformers, convolutional neural networks with attention, shifted window transformers, multi-layer perceptrons, and logistic regression. We include simulated, public, and clinical data in our analysis and release our code at: \verb+github.com/agr78/spectralViT+.

Alexandra G. Roberts, Maneesh John, Jinwei Zhang +10

Self-Supervised Vision Transformers Vision Transformer Visual Tokenizers Convolutional Neural Networks Medical Imaging Limited Data

May 11, 2026cs.CV

Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization

Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quality. However, existing methods universally extract features from only the last encoder layer, discarding the rich hierarchical information distributed across intermediate layers. We show that low-level visual details survive in the last layer merely as attenuated residuals after multiple layers of semantic abstraction, and that explicitly fusing multi-layer features can substantially recover this lost information. We propose DRoRAE (Depth-Routed Representation AutoEncoder), a lightweight fusion module that adaptively aggregates all encoder layers via energy-constrained routing and incremental correction, producing an enriched latent compatible with a frozen pretrained decoder. A three-phase decoupled training strategy first learns the fusion under the implicit distributional constraint of the frozen decoder, then fine-tunes the decoder to fully exploit the enriched representation. On ImageNet-256, DRoRAE reduces rFID from 0.57 to 0.29 and improves generation FID from 1.74 to 1.65 (with AutoGuidance), with gains also transferring to text-to-image synthesis. Furthermore, we uncover a log-linear scaling law (

R^2{=}0.86

) between fusion capacity and reconstruction quality, identifying \textit{representation richness} as a new, predictably scalable dimension for visual tokenizers analogous to vocabulary size in NLP.

Xuanyu Zhu, Yan Bai, Yang Shi +4

Peking University · Meituan Inc · Tsinghua University +1

Visual Tokenizers Vision Encoders Autoencoder Architectures Frozen Encoder

May 11, 2026cs.CV

Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice

Accurate and effective discrete image tokenization is crucial for long image sequence processing. However, current methods rigidly compress all content at a fixed rate, ignoring the variable information density of images and leading to either redundancy or information loss. Inspired by information entropy, we propose TaTok, a Theoretically grounded adaptive image Tokenization framework. We rigorously identify two key drawbacks in existing methods: information insufficiency when reconstructing images with patch tokens alone, and information redundancy among patch tokens. To address these, we introduce global tokens that model mutual information across patch tokens, and a Dynamic Token Filtering (DTF) algorithm based on cumulative conditional entropy to eliminate redundancy. Experiments confirm TaTok's state-of-the-art performance, delivering a 1.3x gFID improvement and 8.7x inference speedup. By allocating tokens according to information richness, TaTok enables more compressed yet accurate image tokenization, offering valuable insights for future research.

Xiusheng Huang, Xin Jiang, Jun Zhao +2

The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences · Beijing Academy of Artificial Intelligence

Visual Tokenizers Tokan Theory

May 8, 2026cs.CV

GEM: Generating LiDAR World Model via Deformable Mamba

World models, which simulate environmental dynamics and generate sensor observations, are gaining increasing attention in autonomous driving. However, progress in LiDAR-based world models has lagged behind those built on camera videos or occupancy data, primarily due to two core challenges: the inherent disorder of LiDAR point clouds and the difficulty of distinguishing dynamic objects from static structures. To address these issues, we propose GEM: a Generative LiDAR world model that leverages deformable mamba architecture, significantly improving fidelity and imaginative capability. Specifically, leveraging the structural similarity between sequential laser scanning and Mamba's processing mechanism, we first tokenize LiDAR sweeps into compact representations via a custom LiDAR scene tokenizer. After unsupervised disentanglement of tokenized features via a dynamic-static separator, a tri-path deformable Mamba is introduced to perform selective scanning and adaptive gating fusion over the disentangled features, leading to enhanced spatial-temporal understanding of the world evolution. Optionally, a planner and a BEV layout controller can be integrated to explore the model's capability for autonomous rollout and its potential to generate ``what-if" scenarios. Extensive experiments show that GEM achieves state-of-the-art performances across diverse benchmarks and evaluation settings, demonstrating its superiority and effectiveness. Project page: https://github.com/wuyang98/GEM.

Yang Wu, Zhaojiang Liu, Qiang Meng +5

SJTU · FDU · NTU +1

Lidar Latent World Models Autonomous Driving Mamba-Based Models Visual Tokenizers

May 7, 2026cs.CV

Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation

Most discrete visual tokenizers rely on a default design: every position in the sequence shares the same codebook. Researchers try to scale the codebook size

K

to get better reconstruction performance. Such a constant-codebook design hits a fundamental information-theoretic limit. We observe that the per-position conditional entropy of the training set decays so quickly along the sequence that, after a few positions, the conditional distribution becomes essentially deterministic. On ImageNet with

K=16384

, this happens within only 2 out of 256 positions, turning the remaining 254 into a memorization problem. We call this phenomenon the Entropy Cliff and formalize it with a simple expression:

t^{*} = \lceil \log_2 N / \log_2 K \rceil

. Interestingly, this phenomenon is not observed in language, as its natural structure keeps the effective entropy per position well below the codebook capacity. To address this, we propose Variable Codebook Size Quantization (VCQ), where the codebook size

K_t

grows monotonically along the sequence from

K_{\min}=2

to

K_{\max}

, leaving the loss function, parameter count, and AR training procedure unchanged. With a vanilla autoregressive Transformer and standard next-token prediction, a base version of VCQ reduces gFID w/o CFG from 27.98 to 14.80 on ImageNet

256\times256

over the baseline. Scaled up, it reaches gFID 1.71 with 684M autoregressive parameters, without any extra training techniques such as semantic regularization or causal alignment. The extreme information bottleneck at

K_{\min}=2

naturally induces a coarse-to-fine semantic hierarchy: a linear probe on only the first 10 tokens reaches 43.8% top-1 accuracy on ImageNet, compared to 27.1% for uniform codebooks. Ultimately, these results show that what matters is not only the total capacity of the codebook, but also how that capacity is distributed and organized.

Bowen Zheng, Weijian Luo, Guang Yang +2

The Chinese University of Hong Kong, Shenzhen · hi-Lab, Xiaohongshu Inc

Codebooks Autoregressive Image Generation Visual Tokenizers Imagenet Next-Token Prediction

May 7, 2026cs.CV

Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow

Discrete image tokenizers are commonly trained in two stages: first for reconstruction, and then with a prior model fitted to the frozen token sequences. This decoupling leaves the tokenizer unaware of the model that will later generate its tokens. As a result, the learned tokens may preserve image information well but still be difficult for an autoregressive (AR) prior to predict from left to right. We analyze this mismatch using Tripartite Variational Consistency (TVC), which decomposes latent-variable learning into three consistency conditions: conditional-likelihood consistency, prior consistency, and posterior consistency. TVC shows that two-stage training preserves the reconstruction side but leaves prior consistency outside the tokenizer objective: the overall token distribution is fixed before the AR prior participates in training. Motivated by this view, we add a distribution-level prior-matching signal during tokenizer training, while keeping the reconstruction objective unchanged. We optimize this signal with a Wasserstein-gradient-flow update. For hard categorical tokens, the update reduces to a token-level contrast between an auxiliary AR model that tracks the tokenizer's current token distribution and the target AR prior. It requires only forward passes through the two AR models and does not backpropagate through either of them. The resulting tokenizer, wAR-Tok, reduces AR loss and improves generation FID on CIFAR-10 and ImageNet at comparable reconstruction quality.

Bowen Zheng, Yihong Luo, Tianyang Hu

The Chinese University of Hong Kong, Shenzhen · Hong Kong University of Science and Technology

Visual Tokenizers Autoregressive Image Generation Wasserstein Gradient Flows Autoregressive Model Latent Variable Gradient

May 7, 2026cs.CV

MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality

Unified visual tokenization faces a fundamental trade-off between high-fidelity pixel reconstruction (spatial equivariance) and semantic abstraction (conceptual invariance). We attribute this conflict to Manifold Misalignment: naive joint optimization induces opposing gradients, creating a zero-sum game between reconstruction and perception. To address this, we propose MUSE, a framework based on Topological Orthogonality. By treating Structure as an orthogonal bridge, MUSE decouples optimization within Transformers: structural gradients refine attention topology, while semantic gradients update feature values. This turns destructive interference into Mutual Reinforcement. Experiments show that MUSE breaks the trade-off, achieving state-of-the-art generation quality (gFID 3.08) and surpassing its teacher InternViT-300M in linear probing (85.2% vs. 82.5%), demonstrating that structurally aligned reconstruction can enhance semantic perception. Code is available at https://github.com/PanqiYang1/MUSE.

Panqi Yang, Haodong Jing, Jiahao Chao +5

State Key Laboratory of Human-Machine Hybrid Augmented Intelligence,National Engineering Research Center of Visual Information and Applications,and Institute of Artificial Intelligence and Robotics, Xi’an Jiao Tong University · Xiaohongshu Inc.

Visual Tokenizers Self-Supervised Vision Transformers Dynamic Attention Orthogonality

May 6, 2026cs.CV

ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters

Vision Transformer (ViT) autoencoders have emerged as compelling tokenizers for images, offering improved reconstruction over convolutional tokenizers. However, existing ViT tokenizers cannot explore this landscape as performance degrades outside training resolutions, and reliance on adversarial losses prevents stable scaling. ViTok (Hansen-Estruch et al., 2025) found that the compression ratio r mediates a reconstruction-generation trade-off where lower r means better reconstructions but harder generations, so improving tokenizer reconstruction is key to more Pareto-optimal tokenizers. We introduce ViTok-v2, which addresses these limitations with native resolution support via NaFlex for generalization across resolutions and aspect ratios, and a novel DINOv3 perceptual loss that replaces both LPIPS and GAN objectives for stable training at any scale. ViTok-v2 is trained on about 2B images and scaled to 5B parameters, the largest image autoencoder to date. ViTok-v2 matches or exceeds state-of-the-art reconstruction at 256p and outperforms all baselines at 512p and above. In joint scaling experiments with flow matching generators, we show that scaling both the autoencoder and the generator advances the Pareto frontier of this trade-off.

Philippe Hansen-Estruch, Jiahui Chen, Vivek Ramanujan +9

University of Texas, Austin · University of Washington · 3Stanford University +3

Visual Tokenizers Vision Transformer Autoregressive Image Generation Autoencoder Architectures Scaling

May 6, 2026cs.CV

Taming Outlier Tokens in Diffusion Transformers

We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number of high-norm tokens that attract disproportionate attention while carrying limited local information, but their role in generative models remains underexplored. We show that this phenomenon appears in both the encoder and denoiser of modern Representation Autoencoder (RAE)-DiT pipelines: pretrained ViT encoders can produce outlier representations, and DiTs themselves can develop internal outlier tokens, especially in intermediate layers. Moreover, simply masking high-norm tokens does not improve performance, indicating that the problem is not only caused by a few extreme values, but is more closely related to corrupted local patch semantics. To address this issue, we introduce Dual-Stage Registers (DSR), a register-based intervention for both components: trained registers when available, recursive test-time registers otherwise, and diffusion registers for the denoiser. Across ImageNet and large-scale text-to-image generation, these interventions consistently reduce outlier artifacts and improve generation quality. Our results highlight outlier-token control as an important ingredient in building stronger DiTs.

Xiaoyu Wu, Yifei Wang, Tsu-Jui Fu +3

Rice University · Apple

Diffusion Transformers Visual Tokenizers Vision Transformer Transformer Architectures Image Generation Outliers+1

May 1, 2026cs.CV

End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer

Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision from generation results to the tokenizer. This contrasts with prior two-stage approaches that train tokenizers and generative models separately. We further investigate leveraging vision foundation models to improve 1D tokenizers for autoregressive modeling. Our autoregressive generative model achieves strong empirical results, including a state-of-the-art FID score of 1.48 without guidance on ImageNet 256x256 generation.

Wenda Chu, Bingliang Zhang, Jiaqi Han +4

ByteDance Seed · California Institute of Technology · Stanford University

Autoregressive Image Generation Visual Tokenizers Generative Models

Apr 30, 2026cs.CV

YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal

Recent advances in Diffusion Transformer (DiT)-based video generation technologies have shown impressive results for video object removal. However, these methods still suffer from substantial inference latency. For instance, although MiniMax Remover achieves state-of-the-art visual quality, it operates at only around 10FPS, primarily due to dense computations over the entire spatiotemporal token space, even when only a small masked region actually requires processing. In this paper, we present YOSE, You Only Select Essential Tokens, an efficient fine-tuning framework. YOSE introduces two key components: Batch Variable-length Indexing (BVI) and Diffusion Process Simulator (DiffSim) Module. BVI is a differentiable dynamic indexing operator that adaptively selects essential tokens based on mask information, enabling variable-length token processing across samples. DiffSim provides a diffusion process approximation mechanism for unmasked tokens, which simulates the influence of unmasked regions within DiT self-attention to maintain semantic consistency for masked tokens. With these designs, YOSE achieves mask-aware acceleration, where the inference time scales approximately linearly with the masked regions, in contrast to full-token diffusion methods whose computation remains constant regardless of the mask size. Extensive experiments demonstrate that YOSE achieves up to 2.5X speedup in 70% of cases while maintaining visual quality comparable to the baseline. Code is available at: https://github.com/Wucy0519/YOSE-CVPR26.

Chenyang Wu, Lina Lei, Fan Li +6

1VCIP, CS, Nankai University · 3NKIARI, Shenzhen Futian · 2Huawei Noah’s Ark Lab

Video Object Removal Video Object Segmentation Visual Tokenizers Diffusion Transformers Video Generation

Apr 27, 2026cs.CV

VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations

We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel resolution-agnostic 1D Transformer-based image tokenizer that encodes images into a dynamic, user-controllable sequence of 32-256 tokens, achieving a state-of-the-art efficiency and performance trade-off. Building on VibeToken, we present VibeToken-Gen, a class-conditioned AR generator with out-of-the-box support for arbitrary resolutions while requiring significantly fewer compute resources. Notably, VibeToken-Gen synthesizes 1024x1024 images using only 64 tokens and achieves 3.94 gFID; by comparison, a diffusion-based state-of-the-art alternative requires 1,024 tokens and attains 5.87 gFID. In contrast to fixed-resolution AR models such as LlamaGen -- whose inference FLOPs grow quadratically with resolution (11T FLOPs at 1024x1024) -- VibeToken-Gen maintains a constant 179G FLOPs (63.4x efficient) independent of resolution. We hope VibeToken can help unlock the wide adoption of AR visual generative models in production use cases.

Maitreya Patel, Jingtao Li, Weiming Zhuang +2

Arizona State University · SonyAI · 3Work partially done while at SonyAI. Maitreya is now at Adobe.

Autoregressive Image Generation Visual Tokenizers Autoregressive Generation Generative Models Autoregressive Model

Apr 18, 2026eess.SP

E2E-WAVE: End-to-End Learned Waveform Generation for Underwater Video Multicasting

We present E2E-WAVE, the first end-to-end learned waveform generation system for underwater video multicasting. Acoustic channels exhibit 20--46% bit error rates where forward error correction becomes counterproductive -- LDPC increases rather than decreases errors beyond its decoding threshold. E2E-WAVE addresses this by embedding semantic similarity directly into physical layer waveforms: when decoding errors are unavoidable, the system preferentially selects semantically similar tokens rather than arbitrary corruption. Combining VideoGPT tokenization (1024x compression) with a trainable waveform bank and fully differentiable OFDM transmission, E2E-WAVE achieves +5 dB (19.26%) PSNR and +0.10 (14.28%) SSIM over the strongest FEC-protected baseline in less challenging underwater channel (NOF1) while delivering real-time 16 FPS video at 128x128 resolution over 2.3 kbps channels -- impossible for conventional digital modulation. The performance gap only increases in harsher channels (BCH1, NCS1). Trained on a single channel, E2E-WAVE generalizes to unseen underwater environments without retraining, while HEVC fails at sub-5 kbps rates and SoftCast's AWGN assumptions collapse on frequency-selective channels.

Khizar Anjum, Tingcong Jiang, Dario Pompili

Department of Electrical and Computer Engineering, Rutgers University–New Brunswick, NJ, USA

Waveforms Video Coding Visual Tokenizers

Apr 16, 2026cs.CV

(1D) Ordered Tokens Enable Efficient Test-Time Search

Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, tokens describe local information, such as regions of pixels in images or word pieces in text, and AR generation predicts these tokens in a fixed order. A worthwhile question is whether token structures affect the ability to steer the generation through test-time search, where multiple candidate generations are explored and evaluated by a verifier. Using image generation as our testbed, we hypothesize that recent 1D ordered tokenizers with coarse-to-fine structure can be more amenable to search than classical 2D grid structures. This is rooted in the fact that the intermediate states in coarse-to-fine sequences carry semantic meaning that verifiers can reliably evaluate, enabling effective steering during generation. Through controlled experiments, we find that AR models trained on coarse-to-fine ordered tokens exhibit improved test-time scaling behavior compared to grid-based counterparts. Moreover, we demonstrate that, thanks to the ordered structure, pure test-time search over token sequences (i.e., without training an AR model) can perform training-free text-to-image generation when guided by an image-text verifier. Beyond this, we systematically study how classical search algorithms (best-of-N, beam search, lookahead search) interact with different token structures, as well as the role of different verifiers and AR priors. Our results highlight the impact of token structure on inference-time scalability and provide practical guidance for test-time scaling in AR models.

Zhitong Gao, Parham Rezaei, Ali Cy +7

1Swiss Federal Institute of Technology Lausanne (EPFL) · 2Apple

Autoregressive Image Generation Autoregressive Generation Visual Tokenizers Generative Models Object Tokens Test Time

Feb 24, 2026cs.CV

COMiT: Learning Structured Visual Tokens through Sequential Communication

Discrete image tokenizers provide a sequential interface for vision and multimodal models, but are typically optimized for reconstruction or compression and therefore tend to encode local appearance rather than object-level structure. We introduce COMiT, a communication-inspired framework for learning structured discrete visual representations. COMiT constructs a fixed-length latent message through sequential visual observations: at each step, a transformer processes a localized image crop and updates, refines, and reorganizes the existing token sequence. After several iterations, the resulting message conditions a flow-matching decoder that reconstructs the complete image. The encoder and decoder are implemented within a single transformer and trained end-to-end using flow-matching reconstruction and semantic representation-alignment objectives. COMiT substantially improves compositional generalization and relational reasoning over prior methods. Our experiments show that, while semantic alignment helps ground the representation, attentive sequential tokenization is critical for inducing more interpretable, object-centric token structures.

Aram Davtyan, Yusuf Sahin, Yasaman Haghighi +4

Computer Vision Group, University of Bern, Switzerland · VITA Lab, EPFL, Switzerland

Visual Tokenizers Self-Supervised Vision Transformers Visual Representations Contrastive Flow Matching

Feb 17, 2026cs.CV

LGQ: Learnable Geometric Quantization for Image Tokenization

Recent collapse-free quantizers such as FSQ achieve stable training by replacing the learnable codebook with an engineered geometry: a fixed scalar grid whose structure is dictated by the codebook size K. We show this trade-off is unnecessary. We introduce Learnable Geometric Quantization (LGQ), which retains a learnable codebook of codes and performs soft-to-hard assignment via temperature annealing, regularized by two cheap terms: A diversity term scaled by codebook size that penalizes concentrated batch-average usage is the primary driver of collapse resistance, complemented by a peakedness term that sharpens each token's soft-assignment toward one-hot; together they prevent codebook collapse without EMA, reset heuristics, or codebook reparameterization. Under a fixed VQ-GAN backbone, we benchmark LGQ against RotVQ, FSQ, SimVQ, and IBQ on ImageNet 256x256 at K=16,384 and sweep LGQ over K={4096,..,65,536} without any per-K hyperparameter tuning. LGQ attains the best reconstruction FID at K = 16,384 while maintaining 100% codebook utilization, and continues to improve as the codebook grows to K = 65,536 with utilization unchanged. Training MaskGIT on the frozen tokenizers, LGQ further attains the best class-conditional generation among the compared quantizers, leading on reconstruction and generation alike. Code is available at https://github.com/KurbanIntelligenceLab/LGQ.

Idil Bilge Altun, Mert Onur Cakiroglu, Elham Buxton +2

Luddy School of Informatics, Computing and Engineering, Indiana University Bloomington · Department of Computer Science, University of Illinois Springfield · College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar

Codebooks Visual Tokenizers