ChannelTok: Efficient Flexible-Length Vision Tokenization

• URL: http://arxiv.org/abs/2606.04461v1
• Date: Wed, 03 Jun 2026 05:10:51 GMT
• Title: ChannelTok: Efficient Flexible-Length Vision Tokenization
• Abstract summary: We introduce a simple, lightweight, and fast channel-wise flexible-length tokenizer.<n>Our method treats each latent channel as a visual token, enabling a parameter-efficient CNN-Transformer hybrid backbone.<n>We validate our approach through extensive experiments on ImageNet, demonstrating consistent quality across diverse token budgets.
• Score: 50.67214721388959
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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

Related papers

• EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation [80.13014959623452]
  EVATok is a framework to produce $textbfE$fficient $textbfV$ideo $textbfA$daptive $textbfTok$enizers.<n>We show that EVATok achieves superior reconstruction and state-of-the-art class-to-video generation on UCF-101.
  arXiv  Detail & Related papers  (2026-03-12T17:59:59Z)
• TrajTok: Learning Trajectory Tokens enables better Video Understanding [63.1260672430712]
  Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens.<n>We propose TrajTok, an end-to-end video tokenizer module that is fully integrated and co-trained with video models for a downstream objective.<n>We show that it can be seamlessly integrated as either a probing head for pretrained visual features (TrajAdapter) or an alignment connector in vision-language models (TrajVLM) with especially strong performance in long-video reasoning.
  arXiv  Detail & Related papers  (2026-02-26T09:15:34Z)
• Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space [94.07013629356113]
  AdapTok is an adaptive temporal causal video tokenizer that can flexibly allocate tokens for different frames based on video content.<n>AdapTok consistently improves reconstruction quality and generation performance under different token budgets.
  arXiv  Detail & Related papers  (2025-05-22T17:59:02Z)
• SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity [32.99546963983819]
  Spiking Neural Networks (SNNs) have shown competitive performance to Artificial Neural Networks (ANNs) in various vision tasks.<n>In this paper, we introduce SpikeVideoFormer, an efficient spike-driven video Transformer.<n>We show our method achieves state-of-the-art (SOTA) performance compared to existing SNN approaches.
  arXiv  Detail & Related papers  (2025-05-15T14:43:35Z)
• VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models [35.38573641029626]
  We introduce the novel task of Extreme Short Token Reduction, which aims to represent entire videos using a minimal set of discrete tokens.<n>On the Extreme Short Token Reduction task, our VQToken compresses sequences to just 0.07 percent of their original length while incurring only a 0.66 percent drop in accuracy on the NextQA-MC benchmark.
  arXiv  Detail & Related papers  (2025-03-21T09:46:31Z)
• Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition [57.74076383449153]
  We propose a novel dual-stream framework for event stream-based pattern recognition via differentiated fusion, termed EFV++. It models two common event representations simultaneously, i.e., event images and event voxels. We achieve new state-of-the-art performance on the Bullying10k dataset, i.e., $90.51%$, which exceeds the second place by $+2.21%$.
  arXiv  Detail & Related papers  (2024-06-27T02:32:46Z)
• Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference [14.030836300221756]
  textbfSparse-Tuning is a novel PEFT method that accounts for the information redundancy in images and videos. Sparse-Tuning minimizes the quantity of tokens processed at each layer, leading to a quadratic reduction in computational and memory overhead. Our results show that our Sparse-Tuning reduces GFLOPs to textbf62%-70% of the original ViT-B while achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-05-23T15:34:53Z)
• Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP [52.25478388220691]
  Vision multi-layer perceptrons (MLPs) have shown promising performance in computer vision tasks. They use token-mixing layers to capture cross-token interactions, as opposed to the multi-head self-attention mechanism used by Transformers. We propose a new positional spacial gating unit (PoSGU) to efficiently encode the cross-token relations for token mixing.
  arXiv  Detail & Related papers  (2022-07-15T04:18:06Z)

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

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