RAC: Rectified Flow Auto Coder
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912947584892928 |
|---|---|
| author | Fang, Sen Feng, Yalin Zhang, Yanxin Metaxas, Dimitris N. |
| author_facet | Fang, Sen Feng, Yalin Zhang, Yanxin Metaxas, Dimitris N. |
| contents | In this paper, we propose a Rectified Flow Auto Coder (RAC) inspired by Rectified Flow to replace the traditional VAE: 1. It achieves multi-step decoding by applying the decoder to flow timesteps. Its decoding path is straight and correctable, enabling step-by-step refinement. 2. The model inherently supports bidirectional inference, where the decoder serves as the encoder through time reversal (hence Coder rather than encoder or decoder), reducing parameter count by nearly 41%. 3. This generative decoding method improves generation quality since the model can correct latent variables along the path, partially addressing the reconstruction--generation gap. Experiments show that RAC surpasses SOTA VAEs in both reconstruction and generation with approximately 70% lower computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05925 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RAC: Rectified Flow Auto Coder Fang, Sen Feng, Yalin Zhang, Yanxin Metaxas, Dimitris N. Computer Vision and Pattern Recognition Artificial Intelligence In this paper, we propose a Rectified Flow Auto Coder (RAC) inspired by Rectified Flow to replace the traditional VAE: 1. It achieves multi-step decoding by applying the decoder to flow timesteps. Its decoding path is straight and correctable, enabling step-by-step refinement. 2. The model inherently supports bidirectional inference, where the decoder serves as the encoder through time reversal (hence Coder rather than encoder or decoder), reducing parameter count by nearly 41%. 3. This generative decoding method improves generation quality since the model can correct latent variables along the path, partially addressing the reconstruction--generation gap. Experiments show that RAC surpasses SOTA VAEs in both reconstruction and generation with approximately 70% lower computational cost. |
| title | RAC: Rectified Flow Auto Coder |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.05925 |