{"ID":2859412,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.06035","arxiv_id":"2510.06035","title":"Universal Neural Architecture Space: Covering ConvNets, Transformers and Everything in Between","abstract":"We introduce Universal Neural Architecture Space (UniNAS), a generic search space for neural architecture search (NAS) which unifies convolutional networks, transformers, and their hybrid architectures under a single, flexible framework. Our approach enables discovery of novel architectures as well as analyzing existing architectures in a common framework. We also propose a new search algorithm that allows traversing the proposed search space, and demonstrate that the space contains interesting architectures, which, when using identical training setup, outperform state-of-the-art hand-crafted architectures. Finally, a unified toolkit including a standardized training and evaluation protocol is introduced to foster reproducibility and enable fair comparison in NAS research. Overall, this work opens a pathway towards systematically exploring the full spectrum of neural architectures with a unified graph-based NAS perspective.","short_abstract":"We introduce Universal Neural Architecture Space (UniNAS), a generic search space for neural architecture search (NAS) which unifies convolutional networks, transformers, and their hybrid architectures under a single, flexible framework. Our approach enables discovery of novel architectures as well as analyzing existin...","url_abs":"https://arxiv.org/abs/2510.06035","url_pdf":"https://arxiv.org/pdf/2510.06035v1","authors":"[\"Ondřej Týbl\",\"Lukáš Neumann\"]","published":"2025-10-07T15:31:40Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}