{"ID":2862090,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.00883","arxiv_id":"2510.00883","title":"GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling","abstract":"In this work we introduce GreenLightningAI (GLAI), a new architectural block designed as an alternative to conventional MLPs. The central idea is to separate two types of knowledge that are usually entangled during training: (i) *structural knowledge*, encoded by the stable activation patterns induced by ReLU activations; and (ii) *quantitative knowledge*, carried by the numerical weights and biases. By fixing the structure once stabilized, GLAI reformulates the MLP as a combination of paths, where only the quantitative component is optimized. This reformulation retains the universal approximation capabilities of MLPs, yet achieves a more efficient training process, reducing training time by ~40% on average across the cases examined in this study. Crucially, GLAI is not just another classifier, but a generic block that can replace MLPs wherever they are used, from supervised heads with frozen backbones to projection layers in self-supervised learning or few-shot classifiers. Across diverse experimental setups, GLAI consistently matches or exceeds the accuracy of MLPs with an equivalent number of parameters, while converging faster. Overall, GLAI establishes a new design principle that opens a direction for future integration into large-scale architectures such as Transformers, where MLP blocks dominate the computational footprint.","short_abstract":"In this work we introduce GreenLightningAI (GLAI), a new architectural block designed as an alternative to conventional MLPs. The central idea is to separate two types of knowledge that are usually entangled during training: (i) *structural knowledge*, encoded by the stable activation patterns induced by ReLU activatio...","url_abs":"https://arxiv.org/abs/2510.00883","url_pdf":"https://arxiv.org/pdf/2510.00883v2","authors":"[\"Jose I. Mestre\",\"Alberto Fernández-Hernández\",\"Cristian Pérez-Corral\",\"Manuel F. Dolz\",\"Jose Duato\",\"Enrique S. Quintana-Ortí\"]","published":"2025-10-01T13:31:34Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Transformer\"]","has_code":false}