paper-with-me

Papers

ChannelTok: Efficient Flexible-Length Vision Tokenization

2026-06-03 · Sukriti Paul, Arpit Bansal, Tom Goldstein arxiv

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

📄 PDF Abstract BibTeX arXiv:2606.04461

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness

2025-06-10 · Jinkwan Jang, Hyungjin Park, Jinmyeong Choi, Taesup Kim

Real-world time series data are inherently multivariate, often exhibiting complex inter-channel dependencies. Each channel is typically sampled at its own period and is prone to missing values due to various practical an…

Missing ValuesMultivariate Time Series ForecastingTime SeriesTime Series Forecasting

Improving Flexible Image Tokenizers for Autoregressive Image Generation

2026-01-04 · Zixuan Fu, Lanqing Guo, Chong Wang, Binbin Song 외 arxiv

Flexible image tokenizers aim to represent an image using an ordered 1D variable-length token sequence. This flexible tokenization is typically achieved through nested dropout, where a portion of trailing tokens is rando…

Image Generation

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

2025-02-19 · Roman Bachmann, Jesse Allardice, David Mizrahi, Enrico Fini 외

Image tokenization has enabled major advances in autoregressive image generation by providing compressed, discrete representations that are more efficient to process than raw pixels. While traditional approaches use 2D g…

Image Generation

Flexibly Scaling Large Language Models Contexts Through Extensible Tokenization

2024-01-15 · Ninglu Shao, Shitao Xiao, Zheng Liu, Peitian Zhang

Large language models (LLMs) are in need of sufficient contexts to handle many critical applications, such as retrieval augmented generation and few-shot learning. However, due to the constrained window size, the LLMs ca…

Few-Shot LearningLanguage ModelingLanguage ModellingRetrieval-augmented Generation

One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression

2025-01-17 · Keita Miwa, Kento Sasaki, Hidehisa Arai, Tsubasa Takahashi 외

Current image tokenization methods require a large number of tokens to capture the information contained within images. Although the amount of information varies across images, most image tokenizers only support fixed-le…

Depth Estimationimage-classificationImage Classificationobject-detection+2