Linear Diffusion Networks
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909552261201920 |
|---|---|
| author | Fein-Ashley, Jacob |
| author_facet | Fein-Ashley, Jacob |
| contents | We present Linear Diffusion Networks (LDNs), a novel architecture that reinterprets sequential data processing as a unified diffusion process. Our model integrates adaptive diffusion modules with localized nonlinear updates and a diffusion-inspired attention mechanism. This design enables efficient global information propagation while preserving fine-grained temporal details. LDN overcomes the limitations of conventional recurrent and transformer models by allowing full parallelization across time steps and supporting robust multi-scale temporal representations. Experiments on benchmark sequence modeling tasks demonstrate that LDN delivers competitive performance across ImageNet and LRA tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12381 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Linear Diffusion Networks Fein-Ashley, Jacob Machine Learning We present Linear Diffusion Networks (LDNs), a novel architecture that reinterprets sequential data processing as a unified diffusion process. Our model integrates adaptive diffusion modules with localized nonlinear updates and a diffusion-inspired attention mechanism. This design enables efficient global information propagation while preserving fine-grained temporal details. LDN overcomes the limitations of conventional recurrent and transformer models by allowing full parallelization across time steps and supporting robust multi-scale temporal representations. Experiments on benchmark sequence modeling tasks demonstrate that LDN delivers competitive performance across ImageNet and LRA tasks. |
| title | Linear Diffusion Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.12381 |