Tag
A研究提出基于物理信息神经网络（PINNs）求解漂移-扩散方程的方法，用于半导体器件建模，在PN结正反向问题上达到与传统TCAD仿真相当的精度，并能在非平衡条件下从电场或电位分布反演掺杂剖面。
The paper investigates whether text conditioning actually steers neural PDE surrogates using OperatorCLIP, a CLIP-style contrastively aligned FNO with FiLM control, finding that constant-prompt controls often match or beat task-text conditioning and that single-description training makes text alignment unidentifiable.
This paper introduces Staged Depth Training (SDT), a representation curriculum for Physics-Informed Neural Networks (PINNs) that explicitly learns and transfers hidden representations to improve training performance.
The paper introduces a reinforcement learning-based approach for adaptively selecting full and reduced order models in hybrid domain decomposition simulations, using deep Q-networks to balance accuracy and cost in transient problems.
The Well is a large-scale collection of 15TB of diverse physics simulation datasets across 16 domains, designed to benchmark machine learning surrogate models for spatiotemporal physical systems. It provides a unified PyTorch interface and example baselines to accelerate simulation-based workflows.