Publication

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

2025

Abstract

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

Official source

https://infoscience.epfl.ch/entities/publication/80ea11e5-d50f-4825-b877-5f0dfe3818dc

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

2025

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/80ea11e5-d50f-4825-b877-5f0dfe3818dc

About this result

Related concepts (32)

Diffusion model

In machine learning, diffusion models, also known as diffusion probabilistic models or score-based generative models, are a class of latent variable models. They are Markov chains trained using variational inference. The goal of diffusion models is to learn the latent structure of a dataset by modeling the way in which data points diffuse through the latent space. In computer vision, this means that a neural network is trained to denoise images blurred with Gaussian noise by learning to reverse the diffusion process.

Transformer (machine learning model)

A transformer is a deep learning architecture that relies on the parallel multi-head attention mechanism. The modern transformer was proposed in the 2017 paper titled 'Attention Is All You Need' by Ashish Vaswani et al., Google Brain team. It is notable for requiring less training time than previous recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models on large (language) datasets, such as the Wikipedia corpus and Common Crawl, by virtue of the parallelized processing of input sequence.

Artificial intelligence art

Artificial intelligence art is any visual artwork created through the use of artificial intelligence (AI) programs. Artists began to create AI art in the mid- to late-20th century, when the discipline was founded. In the early 21st century, the availability of AI art tools to the general public increased, providing opportunities for use outside of academia and professional artists. Throughout its history, artificial intelligence art has raised many philosophical concerns, including related to copyright, deception, and impact on more traditional artists.

Related publications (9)

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

Chat with Graph Search

Challenges for AI in Multimodal STEM Assessments: a Human-AI Comparison

Building hybrid models of neuromodulation from automatic segmentation of peripheral nerve histological sections

Text-Graph Encoders and Retrieval-Augmented Generation