FARMER: Flow AutoRegressive Transformer over Pixels

zhengzhou, Qinyu Zhao, Tao Yang, Fei Xiao, Zhijie Lin, wujie10558@gmail.com, Jiajun Deng, Yanyong Zhang, Rui Zhu

FARMER: Flow AutoRegressive Transformer over Pixels: 51 upvotes on Hugging Face Daily Papers, #4 of 36 papers on 2025-10-28. Day-by-day upvote history. It lost 8 votes when the Hub removed votes in bulk.

Directly modeling the explicit likelihood of the raw data distribution is key topic in the machine learning area, which achieves the scaling successes in Large Language Models by autoregressive modeling. However, continuous AR modeling over visual pixel data suffer from extremely long sequences and high-dimensional spaces. In this paper, we present FARMER, a novel end-to-end generative framework that unifies Normalizing Flows (NF) and Autoregressive (AR) models for tractable likelihood estimation and high-quality image synthesis directly from raw pixels. FARMER employs an invertible autoregressive flow to transform images into latent sequences, whose distribution is modeled implicitly by an autoregressive model. To address the redundancy and complexity in pixel-level modeling, we propose a self-supervised dimension reduction scheme that partitions NF latent channels into informative and redundant groups, enabling more effective and efficient AR modeling. Furthermore, we design a one-step distillation scheme to significantly accelerate inference speed and introduce a resampling-based classifier-free guidance algorithm to boost image generation quality. Extensive experiments demonstrate that FARMER achieves competitive performance compared to existing pixel-based generative models while providing exact likelihoods and scalable training.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.