Word embeddings play a significant role in today's Natural Language Processing tasks and applications. While pre-trained models may be directly employed and integrated into existing pipelines, they are often fine-tuned to better fit with specific languages or domains. In this paper, we attempt to improve available embeddings in the uncovered niche of the Italian medical domain through the combination of Contrastive Learning (CL) and Knowledge Graph Embedding (KGE). The main objective is to improve the accuracy of semantic similarity between medical terms, which is also used as an evaluation task. Since the Italian language lacks medical texts and controlled vocabularies, we have developed a specific solution by combining preexisting CL methods (multi-similarity loss, contextualization, dynamic sampling) and the integration of KGEs, creating a new variant of the loss. Although without having outperformed the state-of-the-art, represented by multilingual models, the obtained results are encouraging, providing a significant leap in performance compared to the starting model, while using a significantly lower amount of data.

Existing automated techniques for software documentation typically attempt to reason between two main sources of information: code and natural language. However, this reasoning process is often complicated by the lexical gap between more abstract natural language and more structured programming languages. One potential bridge for this gap is the Graphical User Interface (GUI), as GUIs inherently encode salient information about underlying program functionality into rich, pixel-based data representations. This paper offers one of the first comprehensive empirical investigations into the connection between GUIs and functional, natural language descriptions of software. First, we collect, analyze, and open source a large dataset of functional GUI descriptions consisting of 45,998 descriptions for 10,204 screenshots from popular Android applications. The descriptions were obtained from human labelers and underwent several quality control mechanisms. To gain insight into the representational potential of GUIs, we investigate the ability of four Neural Image Captioning models to predict natural language descriptions of varying granularity when provided a screenshot as input. We evaluate these models quantitatively, using common machine translation metrics, and qualitatively through a large-scale user study. Finally, we offer learned lessons and a discussion of the potential shown by multimodal models to enhance future techniques for automated software documentation.

Recent efforts in Neural Rendering Fields (NeRF) have shown impressive results on novel view synthesis by utilizing implicit neural representation to represent 3D scenes. Due to the process of volumetric rendering, the inference speed for NeRF is extremely slow, limiting the application scenarios of utilizing NeRF on resource-constrained hardware, such as mobile devices. Many works have been conducted to reduce the latency of running NeRF models. However, most of them still require high-end GPU for acceleration or extra storage memory, which is all unavailable on mobile devices. Another emerging direction utilizes the neural light field (NeLF) for speedup, as only one forward pass is performed on a ray to predict the pixel color. Nevertheless, to reach a similar rendering quality as NeRF, the network in NeLF is designed with intensive computation, which is not mobile-friendly. In this work, we propose an efficient network that runs in real-time on mobile devices for neural rendering. We follow the setting of NeLF to train our network. Unlike existing works, we introduce a novel network architecture that runs efficiently on mobile devices with low latency and small size, i.e., saving $15\times \sim 24\times$ storage compared with MobileNeRF. Our model achieves high-resolution generation while maintaining real-time inference for both synthetic and real-world scenes on mobile devices, e.g., $18.04$ms (iPhone 13) for rendering one $1008\times756$ image of real 3D scenes. Additionally, we achieve similar image quality as NeRF and better quality than MobileNeRF (PSNR $26.15$ vs. $25.91$ on the real-world forward-facing dataset).

We propose a clustering procedure to group K populations into subgroups with the same dependence structure. The method is adapted to paired population and can be used with panel data. It relies on the differences between orthogonal projection coefficients of the K density copulas estimated from the K populations. Each cluster is then constituted by populations having significantly similar dependence structures. A recent test statistic from Ngounou-Bakam and Pommeret (2022) is used to construct automatically such clusters. The procedure is data driven and depends on the asymptotic level of the test. We illustrate our clustering algorithm via numerical studies and through two real datasets: a panel of financial datasets and insurance dataset of losses and allocated loss adjustment expense.

我们提出了三种新型的修剪技术，以提高推理意识到的可区分神经结构搜索（DNAS）的成本和结果。首先，我们介绍了DNA的随机双路构建块，它可以通过内存和计算复杂性在内部隐藏尺寸上进行搜索。其次，我们在搜索过程中提出了一种在超级网的随机层中修剪块的算法。第三，我们描述了一种在搜索过程中修剪不必要的随机层的新技术。由搜索产生的优化模型称为Prunet，并在Imagenet Top-1图像分类精度的推理潜伏期中为NVIDIA V100建立了新的最先进的Pareto边界。将Prunet作为骨架还优于COCO对象检测任务的GPUNET和EFIDENENET，相对于平均平均精度（MAP）。

在发展强化学习（RL）培训系统方面取得了重大进展。过去的作品，例如Impala，Apex，Seed RL，样本工厂等，旨在改善系统的整体吞吐量。在本文中，我们试图解决RL训练系统中的常见瓶颈，即平行环境执行，这通常是整个系统中最慢的部分，但很少受到关注。通过针对RL环境的策划设计，我们改善了不同硬件设置的RL环境模拟速度，从笔记本电脑和适度的工作站到NVIDIA DGX-A100等高端机器。在高端机器上，Envpool在Atari环境上的环境执行每秒可实现100万帧，在Mujoco环境上每秒执行300万帧。在笔记本电脑上运行时，Envpool的速度是Python子过程的2.8倍。此外，在开源社区中已经证明了与现有RL培训库的极大兼容性，包括Cleanrl，RL_Games，DeepMind Acme等。最后，Envpool允许研究人员以更快的速度迭代他们的想法，并具有巨大的潜力，并具有巨大的潜力事实上的RL环境执行引擎。示例运行表明，在笔记本电脑上训练Atari Pong和Mujoco Ant只需5分钟即可。 Envpool已经在https://github.com/sail-sg/envpool上开源。

当通过模拟量化训练神经网络时，我们观察到，量化的权重可以意外地在两个网格点之间振荡。这种效果的重要性及其对量化感知培训（QAT）的影响并未在文献中得到充分理解或研究。在本文中，我们更深入地研究了重量振荡现象，并表明由于推理过程中错误估计的批次纳入统计量和训练期间的噪声增加，它可能导致明显的准确性降解。这些效果在低位（$ \ leq $ 4位）的高效网络中尤其明显，具有深度可分开的层，例如mobilenets和效率网络。在我们的分析中，我们研究了一些先前提出的QAT算法，并表明其中大多数无法克服振荡。最后，我们提出了两种新型的QAT算法来克服训练期间的振荡：振荡衰减和迭代重量冻结。我们证明，我们的算法对于低位（3＆4位）的重量（3＆4位）的最新精度以及有效体系结构的激活量化，例如MobilenetV2，MobilenetV3和Imagenet上的EfficentNet-Lite。我们的源代码可在{https://github.com/qualcomm-ai-research/oscillations-qat}上获得。

本文试图分析表格数据处理深度学习的有效性。据信，决策树及其合奏是该域中的领先方法，深神经网络必须具有计算机视觉的内容等。但是深度神经网络是构建基于梯度的分层表示的框架，并且该关键特征应该能够提供通用结构（表格）数据的最佳处理，而不仅仅是图像矩阵和音频谱图。通过yandex变换挑战（换句话说，yandex变化的天气任务）来考虑这个问题。此任务是古典表格数据回归问题的变体。它还与另一个重要问题有关：机器学习中的泛化和不确定性。本文提出了一种结束于结束算法，用于解决表格数据的不确定性的回归问题，这是基于四个想法的组合：1）自正常化神经网络的深度集合，2）回归作为参数估计高斯目标错误分布，3）分层多任务学习，4）简单数据预处理。所提出的算法的三种修改形成了Yandex的前3个排行榜分别为天气挑战而转变。本文认为，由于深度学习算法的基本属性，并试图证明这一点，这一成功已经发生。

我们提出了一种从视频中共同估计3D运动，3D形状和高度运动模糊物体的外观的方法。为此，我们通过参加多个帧的预定时间窗口的持续时间来模拟生成时尚以生成方式模拟快速移动物体的模糊外观。使用可微分渲染，我们能够通过通过在短时间间隔上平均输出来减少对输入视频来实现对输入视频的像素方向刻录误差来估计所有参数。为此目的，我们还估计相同优化内的相机曝光间隙时间。要考虑突然的运动变化，如弹跳，我们将运动轨迹模拟为片断多项式，我们能够在子帧精度下估计反弹的特定时间。建立的基准数据集的实验表明，我们的方法优于先前的快速移动物体去孔和3D重建方法。