{"ID":2877985,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.00066","arxiv_id":"2509.00066","title":"T-MLP: Tailed Multi-Layer Perceptron for Level-of-Detail Signal Representation","abstract":"Level-of-detail (LoD) representation is critical for efficiently modeling and transmitting various types of signals, such as images and 3D shapes. In this work, we propose a novel network architecture that enables LoD signal representation. Our approach builds on a modified Multi-Layer Perceptron (MLP), which inherently operates at a single scale and thus lacks native LoD support. Specifically, we introduce the Tailed Multi-Layer Perceptron (T-MLP), which extends the MLP by attaching an output branch, also called tail, to each hidden layer. Each tail refines the residual between the current prediction and the ground-truth signal, so that the accumulated outputs across layers correspond to the target signals at different LoDs, enabling multi-scale modeling with supervision from only a single-resolution signal. Extensive experiments demonstrate that our T-MLP outperforms existing neural LoD baselines across diverse signal representation tasks.","short_abstract":"Level-of-detail (LoD) representation is critical for efficiently modeling and transmitting various types of signals, such as images and 3D shapes. In this work, we propose a novel network architecture that enables LoD signal representation. Our approach builds on a modified Multi-Layer Perceptron (MLP), which inherentl...","url_abs":"https://arxiv.org/abs/2509.00066","url_pdf":"https://arxiv.org/pdf/2509.00066v2","authors":"[\"Chuanxiang Yang\",\"Yuanfeng Zhou\",\"Guangshun Wei\",\"Siyu Ren\",\"Yuan Liu\",\"Junhui Hou\",\"Wenping Wang\"]","published":"2025-08-26T08:16:13Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.GR\",\"eess.IV\"]","methods":"[]","has_code":false}