{"ID":2842166,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.10101","arxiv_id":"2511.10101","title":"Balancing Centralized Learning and Distributed Self-Organization: A Hybrid Model for Embodied Morphogenesis","abstract":"We investigate how to couple a learnable brain-like'' controller to a cell-like'' Gray--Scott substrate to steer pattern formation with minimal effort. A compact convolutional policy is embedded in a differentiable PyTorch reaction--diffusion simulator, producing spatially smooth, bounded modulations of the feed and kill parameters ($ΔF$, $ΔK$) under a warm--hold--decay gain schedule. Training optimizes Turing-band spectral targets (FFT-based) while penalizing control effort ($\\ell_1/\\ell_2$) and instability. We compare three regimes: pure reaction--diffusion, NN-dominant, and a hybrid coupling. The hybrid achieves reliable, fast formation of target textures: 100% strict convergence in $\\sim 165$ steps, matching cell-only spectral selectivity (0.436 vs.\\ 0.434) while using $\\sim 15\\times$ less $\\ell_1$ effort and $\u003e200\\times$ less $\\ell_2$ power than NN-dominant control. An amplitude sweep reveals a non-monotonic Goldilocks'' zone ($A \\approx 0.03$--$0.045$) that yields 100\\% quasi convergence in 94--96 steps, whereas weaker or stronger gains fail to converge or degrade selectivity. These results quantify morphological computation: the controller seeds then cedes,'' providing brief, sparse nudges that place the system in the correct basin of attraction, after which local physics maintains the pattern. The study offers a practical recipe for building steerable, robust, and energy-efficient embodied systems that exploit an optimal division of labor between centralized learning and distributed self-organization.","short_abstract":"We investigate how to couple a learnable brain-like'' controller to a cell-like'' Gray--Scott substrate to steer pattern formation with minimal effort. A compact convolutional policy is embedded in a differentiable PyTorch reaction--diffusion simulator, producing spatially smooth, bounded modulations of the feed and ki...","url_abs":"https://arxiv.org/abs/2511.10101","url_pdf":"https://arxiv.org/pdf/2511.10101v1","authors":"[\"Takehiro Ishikawa\"]","published":"2025-11-13T09:05:27Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Diffusion Model\",\"Generative Adversarial Network\"]","has_code":false}