IR-drop is a critical power integrity challenge in modern VLSI designs that can cause timing degradation, reliability issues, and functional failures if not detected early in the design flow. Conventional IR-drop analysis relies on physics-based signoff tools, which provide high accuracy but incur significant computational cost and require near-final layout information, making them unsuitable for rapid early-stage design exploration. In this work, we propose a deep learning-based surrogate modeling approach for early-stage IR-drop estimation using a CNN. The task is formulated as a dense pixel-wise regression problem, where spatial physical layout features are mapped directly to IR-drop heatmaps. A U-Net-based encoder-decoder architecture with skip connections is employed to effectively capture both local and global spatial dependencies within the layout. The model is trained on a physics-inspired synthetic dataset generated by us, which incorporates key physical factors including power grid structure, cell density distribution, and switching activity. Model performance is evaluated using standard regression metrics such as Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR). Experimental results demonstrate that the proposed approach can accurately predict IR-drop distributions with millisecond-level inference time, enabling fast pre-signoff screening and iterative design optimization. The proposed framework is intended as a complementary early-stage analysis tool, providing designers with rapid IR-drop insight prior to expensive signoff analysis. The implementation, dataset generation scripts, and the interactive inference application are publicly available at: https://github.com/riteshbhadana/IR-Drop-Predictor. The live application can be accessed at: https://ir-drop-predictor.streamlit.app/.
PDNNet: PDN-Aware GNN-CNN Heterogeneous Network for Dynamic IR Drop Prediction
School of Integrated Circuits, Peking University(北京大学集成电路学院);School of Microelectronics, Wuhan University(武汉大学微电子学院);Hubei Luojia Laboratory(湖北珞珈实验室);Institute of Electronic Design Automation, Peking University(北京大学电子设计自动化研究所);Beijing Advanced Innovation Center for Integrated Circuits(北京集成电路高精尖创新中心)
针对大规模 IC 设计中动态 IR drop 仿真成本高且 CNN 方法忽视 PDN 配置的问题,提出 PDNGraph 与双分支 GNN-CNN 异构网络 PDNNet,实现更准确、可解释的预测,并较商业工具加速 545 倍。
Renewable Energy Prediction: A Comparative Study of Deep Learning Models for Complex Dataset Analysis
Texas A&M International University(德克萨斯农工国际大学);University of South Alabama(南阿拉巴马大学);Southern University and A&M College(南方大学及农工学院);Angelo State University(安吉洛州立大学);The University of Mississippi(密西西比大学)
Graph-Based Bayesian Optimization for Quantum Circuit Architecture Search with Uncertainty Calibrated Surrogates
Department of Physics, Indian Institute of Technology (BHU)(印度理工学院(BHU)物理系);eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD)(纽约大学阿布扎赫分校(NYUAD)工程系eBRAIN实验室);Center for Quantum and Topological Systems (CQTS), NYUAD Research Institute, NYUAD(纽约大学阿布扎赫分校(NYUAD)量子与拓扑系统中心(CQTS))
Surrogate modeling of Cellular-Potts Agent-Based Models as a segmentation task using the U-Net neural network architecture
Department of Biomedical Engineering, University of Virginia(生物医学工程系,弗吉尼亚大学);Department of Cell Biology, University of Virginia(细胞生物学系,弗吉尼亚大学);TRIUMF, Vancouver, BC, Canada(TRIUMF,加拿大温哥华,不列颠哥伦比亚省);Perimeter Institute for Theoretical Physics, Waterloo, ON, Canada(理论物理研究所,加拿大水疗,安大略省);Beirne B. Carter Center for Immunology Research, University of Virginia(免疫学研究中心,弗吉尼亚大学);Biocomplexity Institute and the Department of Computer Science, University of Virginia(生物复杂性研究所和计算机科学系,弗吉尼亚大学);Department of Intelligent Systems Engineering, Indiana University(智能系统工程系,印第安纳大学)
Uncertainty Quantification for AI-Driven Crash Simulation Surrogates: A Comparative Study of Monte Carlo Dropout and Deep Ensemble on Open-Source Bumper Beam Benchmark
Adaptive Uncertainty-Guided Surrogates for Efficient phase field Modeling of Dendritic Solidification
Intelligent Information Systems, Tekniker(智能信息系统,Tekniker);Department of Computer Sciences and Artificial Intelligence, UPV-EHU(计算机科学与人工智能系,UPV-EHU);Advanced Manufacturing Technologies, Tekniker(先进制造技术,Tekniker)
Conditional deep generative models as surrogates for spatial field solution reconstruction with quantified uncertainty in Structural Health Monitoring applications
National Technical University of Athens(雅典国立技术大学);School of Naval Architecture and Marine Engineering(船舶与海洋工程学院)
Deep Monte Carlo Quantile Regression for Quantifying Aleatoric Uncertainty in Physics-informed Temperature Field Reconstruction
College of Aerospace Science and Engineering National University of Defense Technology(国防科技大学航空航天学院);Defense Innovation Institute Chinese Academy of Military Science(中国人民解放军军事科学院国防创新研究院)
Analyzing the Performance of Deep Encoder-Decoder Networks as Surrogates for a Diffusion Equation
University of British Columbia(不列颠哥伦比亚大学);BC Children’s Hospital Research Institute(不列颠哥伦比亚儿童医院研究所);Biocomplexity Institute(生物复杂性研究所);Indiana University(印第安纳大学);University of Virginia(弗吉尼亚大学)
Improved deep learning techniques in gravitational-wave data analysis
Peking University(北京大学);Kavli Institute for Astronomy and Astrophysics, Peking University(北京大学科维理天文与天体物理研究所);National Astronomical Observatories, Chinese Academy of Sciences(中国科学院国家天文台);Beijing Normal University(北京师范大学)
RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr
Baidu Research(百度研究院);University of Macau(澳门大学)
使用预训练模型微调深度卷积神经网络(CNN)有助于将从较大数据集学习的知识转移到目标任务。虽然即使当训练数据集很小时,准确性也可以大大提高,但迁移学习结果通常受到具有接近CNN权重的预训练模型的约束(Liu et al.,2019),因为这里的反向传播为更深的CNN层带来了更小的更新。在这项工作中,我们提出了RIFLE -一个简单而有效的策略,加深反向传播迁移学习设置,通过定期重新初始化全连接层与随机划痕在微调过程中。RIFLE为深层CNN层的权重带来了有意义的更新,并改进了低级特征学习,而随机化的效果可以在整个学习过程中轻松收敛。实验表明,使用RIFLE显著提高了深度迁移学习在广泛数据集上的准确性,在相同设置下,测试准确率提高0.5%-2%,优于用于类似目的的已知技巧,如Dropout,DropConnect,StochasticDepth,Disturb Label和Cyclic学习率。经验案例和消融研究进一步表明,RIFLE为深层CNN层带来了有意义的更新,提高了准确性。
Normalized Conditional Mutual Information Surrogate Loss for Deep Neural Classifiers
Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Canada(滑铁卢大学电气与计算机工程系);The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada(多伦多大学Edward S. Rogers Sr.电气与计算机工程系)
HeatGen: A Guided Diffusion Framework for Multiphysics Heat Sink Design Optimization
Department of Mechanical Engineering(机械工程系);University of British Columbia(不列颠哥伦比亚大学);Institute for Nano- and Microfluidics(纳微流体研究所);Technical University of Darmstadt(德累斯顿技术大学)
Approximated Oracle Filter Pruning for Destructive CNN Width Optimization
Beijing National Research Center for Information Science and Technology (BNRist)(北京信息科学与技术国家研究中心(BNRist));Tsinghua University(清华大学);University of Warwick(华威大学);Hangzhou Dianzi University(杭州电子科技大学)