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

Roman Bachmann; Jesse Allardice; David Mizrahi; Enrico Fini; Oğuzhan Fatih Kar; Elmira Amirloo; Alaaeldin El-Nouby; Amir Zamir; Afshin Dehghan

2025 ICML ICML 2025

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

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Computer Vision

Authors

Roman Bachmann, Jesse Allardice, David Mizrahi, Enrico Fini, Oğuzhan Fatih Kar, Elmira Amirloo, Alaaeldin El-Nouby, Amir Zamir, Afshin Dehghan

Topics

Deep Learning > Architectures > Transformers Deep Learning > Models > Generative Models Computer Vision > Generation > Image Generation

Keywords

autoregressive generation nested dropout visual vocabulary rectified flow model tokenizer gpt-style transformer

Download PDF