Bidirectional Beta-Tuned Diffusion Model
Diffusion models have gained significant attention in the field of generative modeling due to their capability to produce high-quality samples. However, recent studies show that applying a uniform treatment to all distributions during the training of diffusion models is sub-optimal. In this paper, w...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 48(2026), 1 vom: 01. Jan., Seite 359-373
|
|---|
| 1. Verfasser: |
Zheng, Tianyi
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Zou, Jiayang,
Jiang, Peng-Tao,
Zhang, Hao,
Chen, Jinwei,
Wang, Jia,
Li, Bo |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2026
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|