{"ID":2835934,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.22355","arxiv_id":"2511.22355","title":"AutoTailor: Automatic and Efficient Adaptive Model Deployment for Diverse Edge Devices","abstract":"On-device machine learning (ML) has become a fundamental component of emerging mobile applications. Adaptive model deployment delivers efficient inference for heterogeneous device capabilities and performance requirements through customizing neural architectures. SuperNet-based approaches offer a promising solution by generating a large number of model variants from a pre-trained ML model. However, applying SuperNet in existing frameworks suffers from tedious model-aware development and time-consuming hardware-aware profiling, which limits their practical adoption. We present AutoTailor, the first framework to enable automated, end-to-end SuperNet-based adaptive model deployment for edge devices. Unlike manual SuperNet construction, AutoTailor employs a computation graph-guided compilation approach to automatically transform user-provided ML models into SuperNets. To support efficient specialization, AutoTailor incorporates learning-free latency and accuracy predictors, enabling low-cost yet accurate performance prediction. Our extended evaluations demonstrate that AutoTailor reduces the lines of code for SuperNet construction by 11--27$\\times$, decreases hardware-aware profiling costs by at least 11$\\times$, and achieves up to 15.60\\% absolute accuracy improvement and 60.03\\% latency reduction compared to state-of-the-art approaches across diverse models and devices.","short_abstract":"On-device machine learning (ML) has become a fundamental component of emerging mobile applications. Adaptive model deployment delivers efficient inference for heterogeneous device capabilities and performance requirements through customizing neural architectures. SuperNet-based approaches offer a promising solution by...","url_abs":"https://arxiv.org/abs/2511.22355","url_pdf":"https://arxiv.org/pdf/2511.22355v1","authors":"[\"Mengyang Liu\",\"Chenyu Lu\",\"Haodong Tian\",\"Fang Dong\",\"Ruiting Zhou\",\"Wei Wang\",\"Dian Shen\",\"Guangtong Li\",\"Ye Wan\",\"Li Li\"]","published":"2025-11-27T11:47:56Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}