FARMER：基于像素的流自回归Transformer
FARMER: Flow AutoRegressive Transformer over Pixels
AI总结：
针对视觉像素连续自回归建模的长序列高维问题，提出融合归一化流与自回归模型的FARMER框架，搭配自监督降维、一步蒸馏等方案，实现可扩展的精确似然估计与高质量图像生成。
摘要：
直接建模原始数据分布的显式似然是机器学习领域的核心课题，该方向通过自回归建模在大语言模型中实现了规模化成功。然而，针对视觉像素数据的连续自回归建模面临序列极长和空间高维的问题。本文提出FARMER，这是一种新颖的端到端生成框架，它将归一化流（Normalizing Flows, NF）与自回归（Autoregressive, AR）模型相结合，可直接从原始像素实现可处理的似然估计与高质量图像合成。FARMER采用可逆自回归流将图像转换为潜在序列，该序列的分布由自回归模型隐式建模。为解决像素级建模中的冗余与复杂度问题，我们提出一种自监督降维方案，将NF潜在通道划分为信息组和冗余组，使自回归建模更高效有效。此外，我们设计了一步蒸馏方案以显著加快推理速度，并引入基于重采样的无分类器引导算法来提升图像生成质量。大量实验表明，FARMER在提供精确似然值与可扩展训练的同时，性能与现有基于像素的生成模型相当。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
