{"ID":2852790,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.17558","arxiv_id":"2510.17558","title":"The Free Transformer","abstract":"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.","short_abstract":"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.","url_abs":"https://arxiv.org/abs/2510.17558","url_pdf":"https://arxiv.org/pdf/2510.17558v1","authors":"[\"François Fleuret\"]","published":"2025-10-20T14:05:30Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false}