Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.17558 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911221901426688 |
|---|---|
| author | Fleuret, François |
| author_facet | Fleuret, François |
| contents | We propose an extension of the decoder Transformer that conditions its generative process on random latent variables which are learned without supervision thanks to a variational procedure. Experimental evaluations show that allowing such a conditioning translates into substantial improvements on downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17558 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Free Transformer Fleuret, François Machine Learning We propose an extension of the decoder Transformer that conditions its generative process on random latent variables which are learned without supervision thanks to a variational procedure. Experimental evaluations show that allowing such a conditioning translates into substantial improvements on downstream tasks. |
| title | The Free Transformer |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.17558 |