ARFlow: Autoregressive Flow with Hybrid Linear Attention
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916793687212032 |
|---|---|
| author | Hui, Mude Zhu, Rui-Jie Yang, Songlin Zhang, Yu Wang, Zirui Zhou, Yuyin Eshraghian, Jason Xie, Cihang |
| author_facet | Hui, Mude Zhu, Rui-Jie Yang, Songlin Zhang, Yu Wang, Zirui Zhou, Yuyin Eshraghian, Jason Xie, Cihang |
| contents | Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single corrupted image. To address this limitation, we propose integrating autoregressive modeling -- known for its excellence in modeling complex, high-dimensional joint probability distributions -- into flow models. During training, at each step, we construct causally-ordered sequences by sampling multiple images from the same semantic category and applying different levels of noise, where images with higher noise levels serve as causal predecessors to those with lower noise levels. This design enables the model to learn broader category-level variations while maintaining proper causal relationships in the flow process. During generation, the model autoregressively conditions the previously generated images from earlier denoising steps, forming a contextual and coherent generation trajectory. Additionally, we design a customized hybrid linear attention mechanism tailored to our modeling approach to enhance computational efficiency. Our approach, termed ARFlow, achieves 6.63 FID scores on ImageNet at 256 * 256 without classifier-free guidance, reaching 1.96 FID with classifier-free guidance 1.5, outperforming the previous flow-based model SiT's 2.06 FID. Extensive ablation studies demonstrate the effectiveness of our modeling strategy and chunk-wise attention design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16085 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ARFlow: Autoregressive Flow with Hybrid Linear Attention Hui, Mude Zhu, Rui-Jie Yang, Songlin Zhang, Yu Wang, Zirui Zhou, Yuyin Eshraghian, Jason Xie, Cihang Computer Vision and Pattern Recognition Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single corrupted image. To address this limitation, we propose integrating autoregressive modeling -- known for its excellence in modeling complex, high-dimensional joint probability distributions -- into flow models. During training, at each step, we construct causally-ordered sequences by sampling multiple images from the same semantic category and applying different levels of noise, where images with higher noise levels serve as causal predecessors to those with lower noise levels. This design enables the model to learn broader category-level variations while maintaining proper causal relationships in the flow process. During generation, the model autoregressively conditions the previously generated images from earlier denoising steps, forming a contextual and coherent generation trajectory. Additionally, we design a customized hybrid linear attention mechanism tailored to our modeling approach to enhance computational efficiency. Our approach, termed ARFlow, achieves 6.63 FID scores on ImageNet at 256 * 256 without classifier-free guidance, reaching 1.96 FID with classifier-free guidance 1.5, outperforming the previous flow-based model SiT's 2.06 FID. Extensive ablation studies demonstrate the effectiveness of our modeling strategy and chunk-wise attention design. |
| title | ARFlow: Autoregressive Flow with Hybrid Linear Attention |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.16085 |