搜索和检索仍然是多个领域的主要研究主题，包括计算机图形，计算机视觉，工程设计等。搜索引擎主要需要输入搜索查询和要搜索的项目数据库。在本文的主要背景工程中，数据库由3D CAD模型组成，例如垫圈，活塞，连杆等。用户的查询通常以草图的形式，试图捕获该草图3D模型的详细信息。但是，草图具有某些典型的缺陷，例如间隙，过度划分的部分（多冲程）等。由于检索到的结果仅与输入查询一样好，因此草图需要清理和增强，以更好地检索结果。在本文中，提出了一种深度学习方法来改进或清洁查询草图。最初，分析了来自各个类别的草图，以了解可能发生的许多可能的缺陷。然后根据对这些缺陷的理解创建清理或增强查询草图的数据集。因此，进行了深神网络的端到端培训，以提供有缺陷和干净的草图之间的映射。该网络将有缺陷的查询草图作为输入，并生成清洁或增强的查询草图。拟议方法与其他最新技术的定性和定量比较表明，所提出的方法是有效的。搜索引擎的结果是使用缺陷和增强查询草图报告的，并且显示出使用来自开发方法的增强查询草图可以改善搜索结果。

在本文中，我们提出了一种机器学习方法来识别CAD网格模型中的孔，插槽等的工程形状特征。随着数字归档的出现，较新的制造技术，如3D打印，扫描组件和逆向工程，CAD数据以网格模型表示的形式增殖。由于网格模型的节点和边缘的数量变得更大以及存在噪声的存在，因此基于图形的方法的直接应用不仅是昂贵的，而且难以调整噪声数据。因此，这呼吁更新的方法为以网格形式表示的CAD模型的功能识别。在这里，我们表明，可分立版本的高斯地图可以用作特征学习的签名。我们表明这种方法不仅需要更少的内存要求，而且还需要训练时间更少。由于没有涉及网络架构，超级参数的数量很大，并且可以在更快的时间内调整。识别精度也非常类似于使用3D卷积神经网络（CNN）获得的精度，但在更小的运行时间和存储要求中。已经使用其他非网络的机器学习方法进行了比较，以表明我们的方法具有最高的精度。我们还显示了具有多个功能的CAD模型的识别结果以及从公共基准获得的复杂/交互功能。还证明了处理嘈杂数据的能力。

Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness properties, critical for user experience when deployed in real-life applications, are not well understood. Most existing works on robustness in text or code tasks have focused on classification, while robustness in generation tasks is an uncharted area and to date there is no comprehensive benchmark for robustness in code generation. In this paper, we propose ReCode, a comprehensive robustness evaluation benchmark for code generation models. We customize over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. They are carefully designed to be natural in real-life coding practice, preserve the original semantic meaning, and thus provide multifaceted assessments of a model's robustness performance. With human annotators, we verified that over 90% of the perturbed prompts do not alter the semantic meaning of the original prompt. In addition, we define robustness metrics for code generation models considering the worst-case behavior under each type of perturbation, taking advantage of the fact that executing the generated code can serve as objective evaluation. We demonstrate ReCode on SOTA models using HumanEval, MBPP, as well as function completion tasks derived from them. Interesting observations include: better robustness for CodeGen over InCoder and GPT-J; models are most sensitive to syntax perturbations; more challenging robustness evaluation on MBPP over HumanEval.

While pre-trained language models (LM) for code have achieved great success in code completion, they generate code conditioned only on the contents within the file, i.e., in-file context, but ignore the rich semantics in other files within the same project, i.e., cross-file context, a critical source of information that is especially useful in modern modular software development. Such overlooking constrains code language models' capacity in code completion, leading to unexpected behaviors such as generating hallucinated class member functions or function calls with unexpected arguments. In this work, we develop a cross-file context finder tool, CCFINDER, that effectively locates and retrieves the most relevant cross-file context. We propose CoCoMIC, a framework that incorporates cross-file context to learn the in-file and cross-file context jointly on top of pretrained code LMs. CoCoMIC successfully improves the existing code LM with a 19.30% relative increase in exact match and a 15.41% relative increase in identifier matching for code completion when the cross-file context is provided.

The process of screening molecules for desirable properties is a key step in several applications, ranging from drug discovery to material design. During the process of drug discovery specifically, protein-ligand docking, or chemical docking, is a standard in-silico scoring technique that estimates the binding affinity of molecules with a specific protein target. Recently, however, as the number of virtual molecules available to test has rapidly grown, these classical docking algorithms have created a significant computational bottleneck. We address this problem by introducing Deep Surrogate Docking (DSD), a framework that applies deep learning-based surrogate modeling to accelerate the docking process substantially. DSD can be interpreted as a formalism of several earlier surrogate prefiltering techniques, adding novel metrics and practical training practices. Specifically, we show that graph neural networks (GNNs) can serve as fast and accurate estimators of classical docking algorithms. Additionally, we introduce FiLMv2, a novel GNN architecture which we show outperforms existing state-of-the-art GNN architectures, attaining more accurate and stable performance by allowing the model to filter out irrelevant information from data more efficiently. Through extensive experimentation and analysis, we show that the DSD workflow combined with the FiLMv2 architecture provides a 9.496x speedup in molecule screening with a <3% recall error rate on an example docking task. Our open-source code is available at https://github.com/ryienh/graph-dock.

听诊器录制的胸部声音为新生儿的偏远有氧呼吸健康监测提供了机会。然而，可靠的监控需要高质量的心脏和肺部声音。本文介绍了新生胸部声音分离的新型非负基质分子（NMF）和非负矩阵协同分解（NMCF）方法。为了评估这些方法并与现有的单源分离方法进行比较，产生人工混合物数据集，包括心脏，肺和噪音。然后计算用于这些人造混合物的信噪比。这些方法也在现实世界嘈杂的新生儿胸部声音上进行测试，并根据生命符号估计误差评估，并在我们以前的作品中发达1-5的信号质量得分。此外，评估所有方法的计算成本，以确定实时处理的适用性。总的来说，所提出的NMF和NMCF方法都以2.7db到11.6db的下一个最佳现有方法而言，对于人工数据集，0.40至1.12的现实数据集的信号质量改进。发现10S记录的声音分离的中值处理时间为NMCF和NMF的342ms为28.3。由于稳定且稳健的性能，我们认为我们的提出方法可用于在真实的环境中弃绝新生儿心脏和肺部。提出和现有方法的代码可以在：https://github.com/egrooby-monash/heart-and-lung-sound-eparation。

我们展示了基本的头部动作单位被称为行为分析的Kinemes，以预测人格和面试特征。将头部运动模式转换为一系列型术语有助于发现表征目标性状的潜在时间签名，从而实现有效和可说明的特征预测。利用Kinemes和面部动作编码系统（FACS）特征来预测（a）在第一次印象上的海洋人格性状候选筛选视频中，（b）在MIT数据集上的面试特征，我们注意到：（1）长期用Kineme序列训练的内存（LSTM）网络表现优于或类似于用面部图像培训的卷积神经网络（CNN）;（2）与Kinemes组合的FACS动作单位（AUS）组合实现了精确的预测和解释，并且（3）预测性能受到朝向头部和面部运动的时间长度的影响。

我们考虑通过连接到中央服务器的一组边缘设备的大规模分布式优化，其中服务器和边缘设备之间的有限通信带宽对优化过程提出了显着的瓶颈。灵感来自最近在联邦学习的进步，我们提出了一种分布式随机梯度下降（SGD）类型算法，该算法利用梯度的稀疏性，尽可能降低沟通负担。在算法的核心，用于使用压缩的感测技术来压缩器件侧的局部随机梯度;在服务器端，从嘈杂的聚合压缩的本地梯度恢复全局随机梯度的稀疏近似。我们对通信信道产生的噪声扰动的存在，对我们算法的收敛性进行了理论分析，并且还进行了数值实验以证实其有效性。

基于机器学习（ML）的转向可以通过在线选择更科学意义的计算来提高基于合奏的模拟的性能。我们提出了DeepDrivemd，这是ML驱动的科学模拟转向的框架，我们用来通过在大型平行计算机上的有效耦合ML和HPC来实现分子动力学（MD）性能的稳定性提高。我们讨论了DeepDrivemd的设计，并描述了其性能。我们证明，与其他方法相对于其他方法，DeepDrivemd可以在100-1000倍加速度之间达到100-1000倍的加速度，这是通过执行的模拟时间量来衡量的，同时覆盖了模拟过程中采样的状态所量化的相同构象景观。实验是在最多1020个节点的领导级平台上进行的。该结果将DeepDrivemd作为ML驱动的HPC模拟方案的高性能框架建立，该场景支持不同的MD仿真和ML后端，并通过改善当前计算能力来改善长度和时间尺度来实现新的科学见解。

State-of-the-art visual perception models for a wide range of tasks rely on supervised pretraining. ImageNet classification is the de facto pretraining task for these models. Yet, ImageNet is now nearly ten years old and is by modern standards "small". Even so, relatively little is known about the behavior of pretraining with datasets that are multiple orders of magnitude larger. The reasons are obvious: such datasets are difficult to collect and annotate. In this paper, we present a unique study of transfer learning with large convolutional networks trained to predict hashtags on billions of social media images. Our experiments demonstrate that training for large-scale hashtag prediction leads to excellent results. We show improvements on several image classification and object detection tasks, and report the highest ImageNet-1k single-crop, top-1 accuracy to date: 85.4% (97.6% top-5). We also perform extensive experiments that provide novel empirical data on the relationship between large-scale pretraining and transfer learning performance. Name template Description train-IG-I-1.5k Instagram training set of I images and ∼1.5k hashtags from ImageNet-1k. train-IG-I-8.5k Instagram training set of I images and ∼8.5k hashtags from WordNet. train-IG-I-17k Instagram training set of I images and ∼17k hashtags from WordNet. train-IN-1M-1k The standard ImageNet-1k ILSVRC training set with 1.28M images. val-IN-50k-1k The standard ImageNet-1k ILSVRC validation set with 50k images. train-IN-I-L Extended ImageNet training set of I images and L ∈ {5k, 9k} labels. val-IN-I-L Extended ImageNet validation set of I images and L ∈ {5k, 9k} labels. train-CUB-6k-200 The Caltech-UCSD Birds-200-2011 training set. val-CUB-6k-200 The Caltech-UCSD Birds-200-2011 validation set. train-Places-1.8M-365 The Places365-Standard training set (high-resolution version). val-Places-37k-365 The Places365-Standard validation set (high-resolution version). train-COCO-135k-80 The standard COCO detection training set (2017 version). val-COCO-5k-80 The standard COCO detection validation set (2017 version). test-COCO-20k-80 The standard COCO detection test-dev set (2017 version).Table 1: Summary of image classification datasets. Each dataset is named with a template, role-source-I-L, that indicates its role (training, validation, testing), source, number of images I, and number of labels L.