arXiv:2604. 01802v2 Announce Type: replace Abstract: Real-time inference of inaccessible interior physical fields from sparse boundary observations is a fundamental but unresolved problem in scientific machine learning, with direct relevance to safety-critical monitoring across many engineering applications.
arXiv:2608.27883v1 Announce Type: new Abstract: Physical systems are often modeled by solution operators that map input fields, parameters, geometries, or past states to steady or future physical sta...
arXiv:2608. 07106v1 Announce Type: new Abstract: Deploying three-dimensional deep learning frameworks to low-power embedded processors is bottlenecked by the unstructured nature of spatial data and the resource-intensive distance sorting algorithms often used before neural network inference.
The paper introduces the Sparse-Activation-ReLU (SAR) layer, a single‑step neural operator that promotes activation sparsity without surrogate‑gradient training and is compatible with event‑based computing. In a trunk‑based NOMAD architecture, SAR improves the combined Latency‑Error‑Energy (LEE) metric by over fivefold compared to Variable Spiking Neuron (VSN) and Leaky Integrate‑and‑Fire (LIF) models. Additional techniques such as synthetic knowledge distillation, a ReLU‑based spiking loss, and graph‑neighbor thresholding further reduce LEE and L2 error on the Heat Exchanger dataset, advancing energy‑efficient virtual sensing for edge deployment.
arXiv:2412. 00107v2 Announce Type: replace-cross Abstract: Real-time monitoring of safety-critical interior states remains an open problem in energy systems where physical instrumentation is infeasible.
The paper studies how sharing spatial computation can lower the energy consumption of neural operator updates in virtual sensing tasks. By comparing compiler freezing, explicit trunk reuse, and graph replay, the authors find energy reductions ranging from about 1% at low request rates to 20% at high rates, with a 22–22.5% saving over eager execution in a 15 W mode. The work also highlights how different neural operator architectures (DeepONet and FNO) and overheads such as preparation and worker replacement affect the overall energy profile.
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.
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. To address these challenges, we propose PGD-NO, a neural operator with Precomputed Geometry Decomposition, that relocates the computational overhead of geometric encoding to a deterministic pre-computation phase.
arXiv:2602. 04940v2 Announce Type: replace Abstract: Deep learning has emerged as a transformative tool for the neural surrogate modeling of partial differential equations (PDEs), known as neural PDE solvers.
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.
arXiv:2607. 20535v1 Announce Type: cross Abstract: Traditional Predictive Digital Twins often remain geometrically rigid, requiring extensive retraining or fine-tuning whenever the underlying physical domain or boundary conditions change.
arXiv:2608. 08608v1 Announce Type: cross Abstract: Fourier neural operators (FNOs) provide efficient nonlocal spectral learning, but varying geometries and independently chosen discretizations remain difficult to accommodate.
arXiv:2608. 13827v1 Announce Type: new Abstract: Machine-learned physical surrogate models have become promising alternatives to mesh-based numerical solvers.