Physics-informed AI Accelerated Retention Analysis of Ferroelectric Vertical NAND: From Day-Scale TCAD to Second-Scale Surrogate Model

该研究提出了一种基于物理信息神经算子(PINO)的人工智能代理模型,通过嵌入物理原理,将铁电垂直 NAND 器件的阈值电压漂移和保持特性模拟速度提升了超过 10000 倍,从而克服了传统 TCAD 工具在大规模参数优化中计算成本过高的问题。

Gyujun Jeong (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Sungwon Cho (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Minji Shon (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Namhoon Kim (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Woohyun Hwang (Semiconductor Research and Development, Samsung Electronics Co., Ltd, South Korea), Kwangyou Seo (Semiconductor Research and Development, Samsung Electronics Co., Ltd, South Korea), Suhwan Lim (Semiconductor Research and Development, Samsung Electronics Co., Ltd, South Korea), Wanki Kim (Semiconductor Research and Development, Samsung Electronics Co., Ltd, South Korea), Daewon Ha (Semiconductor Research and Development, Samsung Electronics Co., Ltd, South Korea), Prasanna Venkatesan (NVIDIA, Santa Clara, CA, USA), Kihang Youn (NVIDIA, Santa Clara, CA, USA), Ram Cherukuri (NVIDIA, Santa Clara, CA, USA), Yiyi Wang (NVIDIA, Santa Clara, CA, USA), Suman Datta (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Asif Khan (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Shimeng Yu (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA)2026-03-10🤖 cs.LG

Physics-Consistent Neural Networks for Learning Deformation and Director Fields in Microstructured Media with Loss-Based Validation Criteria

本文提出了一种基于物理一致性的神经网络方法,结合有限元法求解具有微结构的 Cosserat 弹性体平衡构型,并通过推导准凸性、秩一凸性及 Legendre-Hadamard 不等式等稳定性判据,构建了一套能够验证神经网络预测解能量稳定性的物理约束框架。

Milad Shirani, Pete H. Gueldner, Murat Khidoyatov, Jeremy L. Warren, Federica Ninno2026-03-10🤖 cs.LG

Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines

该论文通过构建系统性实验框架,首次全面评估了图稀疏化在大规模图神经网络流水线中的应用,发现其不仅能显著加速训练与推理过程(如在 Products 图上实现 11.7 倍加速),还能在极小精度损失甚至提升模型性能的同时有效缓解数据移动瓶颈。

Yuhang Song, Naima Abrar Shami, Romaric Duvignau, Vasiliki Kalavri2026-03-10🤖 cs.LG

Post-Training with Policy Gradients: Optimality and the Base Model Barrier

该论文研究了基于策略梯度的后训练方法,证明了在基础模型具备非平凡似然时,该方法能以最优样本复杂度提升性能,但指出仅使用结果奖励会因基础模型支持集限制而遭遇指数级查询复杂度障碍,而引入过程奖励模型则能通过依赖令牌级似然分位数有效克服这一维度灾难。

Alireza Mousavi-Hosseini, Murat A. Erdogdu2026-03-10🤖 cs.LG

A SISA-based Machine Unlearning Framework for Power Transformer Inter-Turn Short-Circuit Fault Localization

本文提出了一种基于 SISA(分片、隔离、切片和聚合)的机器遗忘框架,用于解决电力变压器匝间短路故障定位中因传感器故障导致训练数据中毒的问题,该方法通过仅重训受影响的分片模型,在保持与全量重训相当诊断精度的同时显著降低了重训时间。

Nanhong Liu, Jingyi Yan, Mucun Sun, Jie Zhang2026-03-10🤖 cs.LG

Topology-Aware Reinforcement Learning over Graphs for Resilient Power Distribution Networks

该研究提出了一种融合拓扑数据分析(特别是持久同调)的图强化学习框架,用于提升配电网在极端事件下的韧性,实验表明该方法能显著优化网络重构与负荷削减策略,从而在增加电力供应的同时减少电压越限并提升系统自愈能力。

Roshni Anna Jacob, Prithvi Poddar, Jaidev Goel, Souma Chowdhury, Yulia R. Gel, Jie Zhang2026-03-10🤖 cs.LG