HOFAR: High-Order Augmentation of Flow Autoregressive Transformers

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liang, Yingyu, Sha, Zhizhou, Shi, Zhenmei, Song, Zhao, Wan, Mingda
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913729924300800
author Liang, Yingyu
Sha, Zhizhou
Shi, Zhenmei
Song, Zhao
Wan, Mingda
author_facet Liang, Yingyu
Sha, Zhizhou
Shi, Zhenmei
Song, Zhao
Wan, Mingda
contents Flow Matching and Transformer architectures have demonstrated remarkable performance in image generation tasks, with recent work FlowAR [Ren et al., 2024] synergistically integrating both paradigms to advance synthesis fidelity. However, current FlowAR implementations remain constrained by first-order trajectory modeling during the generation process. This paper introduces a novel framework that systematically enhances flow autoregressive transformers through high-order supervision. We provide theoretical analysis and empirical evaluation showing that our High-Order FlowAR (HOFAR) demonstrates measurable improvements in generation quality compared to baseline models. The proposed approach advances the understanding of flow-based autoregressive modeling by introducing a systematic framework for analyzing trajectory dynamics through high-order expansion.
format Preprint
id arxiv_https___arxiv_org_abs_2503_08032
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HOFAR: High-Order Augmentation of Flow Autoregressive Transformers
Liang, Yingyu
Sha, Zhizhou
Shi, Zhenmei
Song, Zhao
Wan, Mingda
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Flow Matching and Transformer architectures have demonstrated remarkable performance in image generation tasks, with recent work FlowAR [Ren et al., 2024] synergistically integrating both paradigms to advance synthesis fidelity. However, current FlowAR implementations remain constrained by first-order trajectory modeling during the generation process. This paper introduces a novel framework that systematically enhances flow autoregressive transformers through high-order supervision. We provide theoretical analysis and empirical evaluation showing that our High-Order FlowAR (HOFAR) demonstrates measurable improvements in generation quality compared to baseline models. The proposed approach advances the understanding of flow-based autoregressive modeling by introducing a systematic framework for analyzing trajectory dynamics through high-order expansion.
title HOFAR: High-Order Augmentation of Flow Autoregressive Transformers
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2503.08032