{"ID":2887182,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.01537","arxiv_id":"2508.01537","title":"FluidFormer: Transformer with Continuous Convolution for Particle-based Fluid Simulation","abstract":"Learning-based fluid simulation networks have been proven as viable alternatives to traditional numerical solvers for the Navier-Stokes equations. Existing neural methods follow Smoothed Particle Hydrodynamics (SPH) frameworks, which inherently rely only on local inter-particle interactions. However, we emphasize that global context integration is also essential for learning-based methods to stabilize complex fluid simulations. We propose the first Fluid Attention Block (FAB) with a local-global hierarchy, where continuous convolutions extract local features while self-attention captures global dependencies. This fusion suppresses the error accumulation and models long-range physical phenomena. Furthermore, we pioneer the first Transformer architecture specifically designed for continuous fluid simulation, seamlessly integrated within a dual-pipeline architecture. Our method establishes a new paradigm for neural fluid simulation by unifying convolution-based local features with attention-based global context modeling. FluidFormer demonstrates state-of-the-art performance, with stronger stability in complex fluid scenarios.","short_abstract":"Learning-based fluid simulation networks have been proven as viable alternatives to traditional numerical solvers for the Navier-Stokes equations. Existing neural methods follow Smoothed Particle Hydrodynamics (SPH) frameworks, which inherently rely only on local inter-particle interactions. However, we emphasize that...","url_abs":"https://arxiv.org/abs/2508.01537","url_pdf":"https://arxiv.org/pdf/2508.01537v1","authors":"[\"Nianyi Wang\",\"Yu Chen\",\"Shuai Zheng\"]","published":"2025-08-03T01:44:17Z","proceeding":"cs.CE","tasks":"[\"cs.CE\",\"cs.GR\",\"cs.LG\",\"physics.flu-dyn\"]","methods":"[\"Transformer\"]","has_code":false}