TRACE is a graph‑network simulator that stores granular contact history on edges using attention‑based message passing and a gated recurrent unit, with an edge‑identity dictionary to preserve memory as contacts change. It predicts normal and tangential forces while enforcing Coulomb friction and internal force balance, and is trained via single‑step pretraining followed by autoregressive fine‑tuning. On 2D and 3D granular column‑collapse benchmarks, TRACE achieves significantly lower long‑rollout position and deposit errors than existing simulators, uses fewer parameters, maintains near‑zero particle interpenetration, and outperforms the material point method by 12.2× (2D) and 8.9× (3D).
arXiv:2608. 13827v1 Announce Type: new Abstract: Machine-learned physical surrogate models have become promising alternatives to mesh-based numerical solvers.
arXiv:2606. 10909v1 Announce Type: cross Abstract: Reconstructing local stress fields in heterogeneous microstructures under non-linear, history-dependent loading remains a major computational bottleneck in multi-scale simulations.
MeshGraphNet-Transformer (MGN‑T) is a new architecture that fuses Transformers’ global modeling with MeshGraphNets’ geometric inductive bias, keeping a mesh‑based graph representation. It replaces iterative message passing with a physics‑attention Transformer that updates all nodal states simultaneously, enabling efficient learning on high‑resolution meshes with diverse geometries, topologies, and boundary conditions. MGN‑T accurately models impact dynamics, self‑contact, plasticity, and multivariate outputs, outperforming state‑of‑the‑art methods on classical benchmarks while using far fewer parameters.
arXiv:2606. 09065v1 Announce Type: cross Abstract: In science and engineering, Lagrangian simulation methods such as Smooth Particle Hydrodynamics (SPH) or Material Point Method (MPM) are often employed to study the behavior of dynamic systems.
The paper introduces a physics‑informed graph attention network that directly operates on the tetrahedral mesh used in TCAD simulations of FinFET devices. By predicting electrostatic potential and quasi‑Fermi levels at every mesh node and training with both data loss and finite‑volume current‑continuity residuals, the surrogate retains the underlying carrier‑transport physics while achieving size generalization. Benchmarks against Sentaurus Device show sub‑volt RMSE for the drift‑diffusion fields and a per‑design throughput that is orders of magnitude faster, enabling rapid Pareto‑front exploration of large multi‑fin arrays that would otherwise be prohibitively slow to simulate.
The paper introduces AdaptGNS, a particle simulation framework that dynamically adjusts the interaction graph based on per-particle uncertainty estimates. By training a variance head jointly with the acceleration head using a heteroscedastic Gaussian NLL loss, the model expands the neighborhood of high‑uncertainty particles, improving long‑horizon accuracy. Experiments show a strict Pareto improvement on the WaterDrop benchmark and a modest gain on Sand, suggesting adaptive graphs are especially beneficial in spatially complex regions.
arXiv:2606. 09432v1 Announce Type: new Abstract: Modeling interacting dynamical systems requires capturing spatial interactions alongside long-range temporal dependencies.
arXiv:2606. 08287v1 Announce Type: new Abstract: Finite element analysis (FEA) is essential for structural design but remains computationally expensive, particularly when evaluating multiple design iterations or load scenarios.
arXiv:2608. 01833v1 Announce Type: cross Abstract: Grokking is a striking phenomenon in neural network training, where a model can undergo a prolonged period of pure memorization before abrupt generalization.
arXiv:2605. 22845v2 Announce Type: replace-cross Abstract: Explicit dynamic finite element (FE) simulations are widely used for large deformation engineering analysis, but repeated simulations remain costly during design space exploration and optimisation.
arXiv:2607. 08025v1 Announce Type: new Abstract: While neural PDE solvers have demonstrated significant potential for accelerating engineering simulations, existing architectures remain constrained by high memory consumption and the single node bottleneck, where the maximum processable mesh resolution is strictly limited by the VRAM of a single compute unit.
arXiv:2609.05542v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) provide a mesh-free framework for solving governing equations, but their application to granular avalanche d...