In this paper, we propose RI3D, a novel 3DGS-based approach that harnesses the power of diffusion models to reconstruct high-quality novel views given a sparse set of input images. Our key contribution is separating the view synthesis process into two tasks of reconstructing visible regions and hallucinating missing regions, and introducing two personalized diffusion models, each tailored to one of these tasks. Specifically, one model ('repair') takes a rendered image as input and predicts the corresponding high-quality image, which in turn is used as a pseudo ground truth image to constrain the optimization. The other model ('inpainting') primarily focuses on hallucinating details in unobserved areas. To integrate these models effectively, we introduce a two-stage optimization strategy: the first stage reconstructs visible areas using the repair model, and the second stage reconstructs missing regions with the inpainting model while ensuring coherence through further optimization. Moreover, we augment the optimization with a novel Gaussian initialization method that obtains per-image depth by combining 3D-consistent and smooth depth with highly detailed relative depth. We demonstrate that by separating the process into two tasks and addressing them with the repair and inpainting models, we produce results with detailed textures in both visible and missing regions that outperform state-of-the-art approaches on a diverse set of scenes with extremely sparse inputs.

Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to the convolutional neural network (CNN)-based models. However, ViTs mainly designed for image classification will generate single-scale low-resolution representations, which makes dense prediction tasks such as semantic segmentation challenging for ViTs. Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs. We balance the model performance and efficiency of HRViT by various branch-block co-optimization techniques. Specifically, we explore heterogeneous branch designs, reduce the redundancy in linear layers, and augment the attention block with enhanced expressiveness. Those approaches enabled HRViT to push the Pareto frontier of performance and efficiency on semantic segmentation to a new level, as our evaluation results on ADE20K and Cityscapes show. HRViT achieves 50.20% mIoU on ADE20K and 83.16% mIoU on Cityscapes, surpassing state-of-the-art MiT and CSWin backbones with an average of +1.78 mIoU improvement, 28% parameter saving, and 21% FLOPs reduction, demonstrating the potential of HRViT as a strong vision backbone for semantic segmentation. Our code is publicly available11https://github.com/facebookresearch/HRViT.

The continued scaling of integrated circuit technologies, along with the increased design complexity, has exacerbated the challenges associated with manufacturability and yield. In today's semiconductor manufacturing, lithography plays a fundamental role in printing design patterns on silicon. However, the growing complexity and variation of the manufacturing process have tremendously increased the lithography modeling and simulation cost. Besides, both the role and cost of resolution enhancement techniques (RETs) - now indispensable in the design process - have increased. Parallel to these developments are the recent advancements in Machine Learning (ML) which have provided a far-reaching data-driven perspective for problem solving. In this work, we shed light on the recent Deep Learning (DL) based approaches that have provided a new lens to examine traditional manufacturability and yield challenges. We present lithography modeling and simulation techniques, leveraging advanced learning paradigms, which have demonstrated unprecedented efficiency. Moreover, we demonstrate the role DL can play in advancing RETs by presenting its successful application in assist feature generation. Also critical to yield is the post fabrication wafer map defect analysis step which our work tackles using a novel confidence-aware deep learning scheme. This paper further discusses the future prospects of DL-based approaches in the scope of circuits manufacturability and yield.

With the continuous shrinking of the semiconductor device dimensions, mask topography effects stand out among the major factors influencing the lithography process. Including these effects in the lithography optimization procedure has become necessary for advanced technology nodes. However, conventional rigorous simulation for mask topography effects is extremely computationally expensive for high accuracy. In this work, we propose TEMPO as a novel generative learning-based framework for efficient and accurate 3D aerial image prediction. At its core, TEMPO comprises a generative adversarial network capable of predicting aerial image intensity at different resist heights. Compared to the default approach of building a unique model for each desired height, TEMPO takes as one of its inputs the desired height to produce the corresponding aerial image. In this way, the global model in TEMPO can capture the shared behavior among different heights, thus, resulting in smaller model size. Besides, across-height information sharing results in better model accuracy and generalization capability. Our experimental results demonstrate that TEMPO can obtain up to 1170x speedup compared with rigorous simulation while achieving satisfactory accuracy.

With the continuous scaling of integrated circuit (IC) technologies, electromigration (EM) prevails as one of the major reliability challenges facing the design of robust circuits. With such aggressive scaling in advanced technology nodes, signal nets experience high switching frequency, which further exacerbates the signal EM effect. Traditionally, signal EM fixing approaches analyze EM violations after the routing stage and repair is attempted via iterative incremental routing or cell resizing techniques. However, these "EM-analysis-then fix" approaches are ill-equipped when faced with the ever-growing EM violations in advanced technology nodes. In this work, we propose a novel signal EM handling framework that (i) incorporates EM detection and fixing techniques into earlier stages of the physical design process, and (ii) integrates machine learning based detection alongside a multistage mitigation. Experimental results demonstrate that our framework can achieve 15x speedup when compared to the state-of-the-art EDA tool while achieving similar performance in terms of EM mitigation and overhead.

As modern integrated circuits scale up with escalating complexity of layout design patterns, lithography hotspot detection, a key stage of physical verification to ensure layout finishing and design closure, has raised a higher demand on its efficiency and accuracy. Among all the hotspot detection approaches, machine learning distinguishes itself for achieving high accuracy while maintaining low false alarms. However, due to the class imbalance problem, the conventional practice which uses the accuracy and false alarm metrics to evaluate different machine learning models is becoming less effective. In this work, we propose the use of the area under the ROC curve (AUC), which provides a more holistic measure for imbalanced datasets compared with the previous methods. To systematically handle class imbalance, we further propose the surrogate loss functions for direct AUC maximization as a substitute for the conventional cross-entropy loss. Experimental results demonstrate that the new surrogate loss functions are promising to outperform the cross-entropy loss when applied to the state-of-the-art neural network model for hotspot detection.

Lithography simulation is one of the most fundamental steps in process modeling and physical verification. Conventional simulation methods suffer from a tremendous computational cost for achieving high accuracy. Recently, machine learning was introduced to trade off between accuracy and runtime through speeding up the resist modeling stage of the simulation flow. In this work, we propose LithoGAN, an end-to-end lithography modeling framework based on a generative adversarial network (GAN), to map the input mask patterns directly to the output resist patterns. Our experimental results show that LithoGAN can predict resist patterns with high accuracy while achieving orders of magnitude speedup compared to conventional lithography simulation and previous machine learning based approach.

Lithography hotspot detection is one of the fundamental steps in physical verification. Due to the increasingly complicated design patterns, early and quick feedback for lithography hotspots is desired to guide design closure in early stages. Machine learning approaches have been successfully applied to hotspot detection while demonstrating a remarkable capability of generalization to unseen hotspot patterns. However, most of the proposed machine learning approaches are not yet able to answer one critical question: how much a hotspot predicted from a trained model can be trusted? In this work, we present Litho-GPA, a lithography hotspot detection framework, with Gaussian Process assurance to provide confidence in each prediction. The framework also incorporates a data selection scheme with a sequence of weak classifiers to sample representative data and eventually reduce the amount of training data and lithography simulations needed. Experimental results demonstrate that our Litho-GPA is able to achieve the state-of-the-art accuracy while obtaining on average 28% reduction in false alarms.

With the dramatic increase in the complexity of modern integrated circuits (ICs), direct analysis and verification of IC power distribution networks (PDNs) have become extremely computationally expensive. Various power grid reduction methods are proposed to reduce the grid size for fast verification and simulation but usually suffer from poor scalability. In this paper, we present a convex optimization-based framework for power grid reduction. Edge sparsification is formulated as a weighted convex optimization problem with sparsity-inducing penalties, which provides an accurate control over the final error. A greedy coordinate descent (GCD) method with optimality guarantee is proposed along with a novel coordinate selection strategy to improve the efficiency and accuracy of edge sparsification. Experimental results demonstrate that the proposed approach achieves better performance compared with traditional gradient descent methods, and 98% accuracy and good sparsity for industrial benchmarks.

Yield learning and optimization are critical for advanced IC design and manufacturing. Recent advance in machine learning has brought a lot of new opportunities in improving the performance and efficiency of IC yield learning and optimization. This paper surveys some recent results of using various machine learning/deep learning techniques for such purpose, including performance modeling under uncertainty, lithography modeling with transfer/active learning, lithography hotspot detection, and IC mask optimization. The state-of-the-art methods are explained, and challenges/opportunities are discussed.

In advanced technology nodes, power grid metal wires are prone to electromigration (EM) failures due to small wire sizes and high unidirectional current densities. Power grid EM failures usually happen around weak power grid connections delivering current to high power-consuming regions. Previously, power grid EM was mostly addressed at the post-routing stage, which may be too late for a large number of EM violations in modern designs. In this paper, we propose a new set of incremental placement techniques to mitigate power grid EM, including cell move, single row placement, and single tile placement. Experimental results demonstrate the proposed placement techniques can effectively reduce EM violations with negligible wirelength and placement density impacts.

As minimum feature size and pitch spacing further decrease in advanced technology nodes, many new design constraints and challenges are introduced, such as regularity, middle of line (MOL) structures, and pin-access challenges. In this work, we propose a comprehensive study on standard cell layout regularity and pin access optimization. Given irregular cell layout from old technology nodes, our cell optimization tool can search unidirectional migrated result where the self-aligned double patterning (SADP) and MOL based design constraints are satisfied, and the pin-accessibility is optimized. This problem is formulated as a general integer linear programming (ILP), which may suffer from long runtime for some large standard cell cases. Therefore, we also develop a set of hybrid techniques to quickly search for high-quality solutions. The experimental results demonstrate the effectiveness of our approaches.