{"ID":2856597,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.11955","arxiv_id":"2510.11955","title":"Y-Shaped Generative Flows","abstract":"Modern continuous-time generative models typically induce \\emph{V-shaped} flows: each sample travels independently along a nearly straight trajectory from the prior to the data. Although effective, this independent movement overlooks the hierarchical structures that exist in real-world data. To address this, we introduce \\emph{Y-shaped generative flows}, a framework in which samples travel together along shared pathways before branching off to target-specific endpoints. Our formulation is theoretically justified, yet remains practical, requiring only minimal modifications to standard velocity-driven models. We implement this through a scalable, neural network-based training objective. Experiments on synthetic, image, and biological datasets demonstrate that our method recovers hierarchy-aware structures, improves distributional metrics over strong flow-based baselines, and reaches targets in fewer steps.","short_abstract":"Modern continuous-time generative models typically induce \\emph{V-shaped} flows: each sample travels independently along a nearly straight trajectory from the prior to the data. Although effective, this independent movement overlooks the hierarchical structures that exist in real-world data. To address this, we introdu...","url_abs":"https://arxiv.org/abs/2510.11955","url_pdf":"https://arxiv.org/pdf/2510.11955v3","authors":"[\"Arip Asadulaev\",\"Semyon Semenov\",\"Abduragim Shtanchaev\",\"Eric Moulines\",\"Fakhri Karray\",\"Martin Takac\"]","published":"2025-10-13T21:33:37Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}