Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2503.16562 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916658783715328 |
|---|---|
| author | Feng, Ling Yang, SK |
| author_facet | Feng, Ling Yang, SK |
| contents | In Rectified Flow, by obtaining the rectified flow several times, the mapping relationship between distributions can be distilled into a neural network, and the target distribution can be directly predicted by the straight lines of the flow. However, during the pairing process of the mapping relationship, a large amount of error accumulation will occur, resulting in a decrease in performance after multiple rectifications. In the field of flow models, knowledge distillation of multi - teacher diffusion models is also a problem worthy of discussion in accelerating sampling. I intend to combine multi - teacher knowledge distillation with Bezier curves to solve the problem of error accumulation. Currently, the related paper is being written by myself. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16562 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bezier Distillation Feng, Ling Yang, SK Machine Learning In Rectified Flow, by obtaining the rectified flow several times, the mapping relationship between distributions can be distilled into a neural network, and the target distribution can be directly predicted by the straight lines of the flow. However, during the pairing process of the mapping relationship, a large amount of error accumulation will occur, resulting in a decrease in performance after multiple rectifications. In the field of flow models, knowledge distillation of multi - teacher diffusion models is also a problem worthy of discussion in accelerating sampling. I intend to combine multi - teacher knowledge distillation with Bezier curves to solve the problem of error accumulation. Currently, the related paper is being written by myself. |
| title | Bezier Distillation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.16562 |