Tactile perception is key to dexterous manipulation, yet simulating high-resolution elastomer deformation remains computationally prohibitive. Finite element methods (FEM) deliver high fidelity but demand costly remeshing, while Material Point Methods (MPM) suffer from heavy particle-memory tradeoffs. We propose a {reduced-order neural simulation framework} that couples coarse-grained MPM dynamics with an implicit neural decoder to reconstruct sub-particle tactile details from compact latent states. The framework learns a continuous deformation manifold from paired high- and low-resolution simulations, enabling physically consistent, differentiable inference. Compared to the TacIPC, our method achieves over 65\% faster simulation and {40\% lower memory usage}, while maintaining better geometric fidelity. In tactile rendering and 3D surface reconstruction, our methods further improve accuracy by 25\% and produce realistic depth images and surface mesh within a faster inference speed. These results demonstrate that the proposed reduced-order neural model enables high-detail, physically grounded tactile simulation with substantial efficiency gains for robotic interaction and optimization.
@article{arxiv.2605.05053,
title = {Reduced-order Neural Modeling with Differentiable Simulation for High-Detail Tactile Perception},
author = {Yuhu Guo and Zhikai Shen and Jiasheng Qu and Chenghao Qian and Yuming Huang and Bin Chen and Guoxing Fang},
journal= {arXiv preprint arXiv:2605.05053},
year = {2026}
}