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

arXiv: https://arxiv.org/abs/2502.13967 · HTML: https://mlsanity.com/paper/2502.13967/

## Key facts

- Cited by 110 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2025.

## Built on by (most cited first, 30 of 110)

- [GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation](https://mlsanity.com/paper/2504.08736/) (2025)
- [Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization](https://mlsanity.com/paper/2503.11056/) (2025)
- [Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning](https://mlsanity.com/paper/2505.07538/) (2025)
- ["Principal Components" Enable A New Language of Images](https://mlsanity.com/paper/2503.08685/) (2025)
- [UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation](https://mlsanity.com/paper/2510.10575/) (2025)
- [Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation](https://mlsanity.com/paper/2507.08441/) (2025)
- [Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model](https://mlsanity.com/paper/2506.05289/) (2025)
- [Latent Denoising Makes Good Tokenizers](https://mlsanity.com/paper/2507.15856/) (2025)
- [Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation](https://mlsanity.com/paper/2507.02608/) (2025)
- [DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction](https://mlsanity.com/paper/2505.21473/) (2025)
- [Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space](https://mlsanity.com/paper/2505.17011/) (2025)
- [OAT: Ordered Action Tokenization](https://mlsanity.com/paper/2602.04215/) (2026)
- [ELT: Elastic Looped Transformers for Visual Generation](https://mlsanity.com/paper/2604.09168/) (2026)
- [TokBench: Evaluating Your Visual Tokenizer before Visual Generation](https://mlsanity.com/paper/2505.18142/) (2025)
- [DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer](https://mlsanity.com/paper/2507.04947/) (2025)
- [Adapting Self-Supervised Representations as a Latent Space for Efficient Generation](https://mlsanity.com/paper/2510.14630/) (2025)
- [Single-pass Adaptive Image Tokenization for Minimum Program Search](https://mlsanity.com/paper/2507.07995/) (2025)
- [Mode Seeking meets Mean Seeking for Fast Long Video Generation](https://mlsanity.com/paper/2602.24289/) (2026)
- [Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation](https://mlsanity.com/paper/2604.21221/) (2026)
- [Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis](https://mlsanity.com/paper/2503.08354/) (2025)
- [SceneTok: A Compressed, Diffusable Token Space for 3D Scenes](https://mlsanity.com/paper/2602.18882/) (2026)
- [D-AR: Diffusion via Autoregressive Models](https://mlsanity.com/paper/2505.23660/) (2025)
- [WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction](https://mlsanity.com/paper/2508.05599/) (2025)
- [GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation](https://mlsanity.com/paper/2509.01109/) (2025)
- [Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing](https://mlsanity.com/paper/2603.12254/) (2026)
- [What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion](https://mlsanity.com/paper/2605.07915/) (2026)
- [HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation](https://mlsanity.com/paper/2509.23736/) (2025)
- [InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression](https://mlsanity.com/paper/2512.16975/) (2025)
- [Decoupling High and Low Frequencies for Faithful Image Generation with Fine Details](https://mlsanity.com/paper/2509.05441/) (2025)
- [SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization](https://mlsanity.com/paper/2510.04961/) (2025)

## Abstract (arXiv)

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 grid tokenization, recent methods like TiTok have shown that 1D tokenization can achieve high generation quality by eliminating grid redundancies. However, these methods typically use a fixed number of tokens and thus cannot adapt to an image's inherent complexity. We introduce FlexTok, a tokenizer that projects 2D images into variable-length, ordered 1D token sequences. For example, a 256x256 image can be resampled into anywhere from 1 to 256 discrete tokens, hierarchically and semantically compressing its information. By training a rectified flow model as the decoder and using nested dropout, FlexTok produces plausible reconstructions regardless of the chosen token sequence length. We evaluate our approach in an autoregressive generation setting using a simple GPT-style Transformer. On ImageNet, this approach achieves an FID<2 across 8 to 128 tokens, outperforming TiTok and matching state-of-the-art methods with far fewer tokens. We further extend the model to support to text-conditioned image generation and examine how FlexTok relates to traditional 2D tokenization. A key finding is that FlexTok enables next-token prediction to describe images in a coarse-to-fine "visual vocabulary", and that the number of tokens to generate depends on the complexity of the generation task.