Saved in:
Bibliographic Details
Main Author: Fleuret, François
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