在本文中，我们展示了Facetunegan，一种新的3D面部模型表示分解和编码面部身份和面部表情。我们提出了对图像到图像翻译网络的第一次适应，该图像已经成功地用于2D域，到3D面几何。利用最近释放的大面扫描数据库，神经网络已经过培训，以便与面部更好的了解，使面部表情转移和中和富有效应面的变异因素。具体而言，我们设计了一种适应基础架构的对抗架构，并使用Spiralnet ++进行卷积和采样操作。使用两个公共数据集（FACESCAPE和COMA），Facetunegan具有比最先进的技术更好的身份分解和面部中和。它还通过预测较近地面真实数据的闪烁形状并且由于源极和目标之间的面部形态过于不同的面部形态而越来越多的不期望的伪像来优异。

Current language models are considered to have sub-human capabilities at natural language tasks like question-answering or writing code. However, language models are not trained to perform well at these tasks, they are trained to accurately predict the next token given previous tokes in tokenized text. It is not clear whether language models are better or worse than humans at next token prediction. To try to answer this question, we performed two distinct experiments to directly compare humans and language models on this front: one measuring top-1 accuracy and the other measuring perplexity. In both experiments, we find humans to be consistently \emph{worse} than even relatively small language models like GPT3-Ada at next-token prediction.

The estimation of the generalization error of classifiers often relies on a validation set. Such a set is hardly available in few-shot learning scenarios, a highly disregarded shortcoming in the field. In these scenarios, it is common to rely on features extracted from pre-trained neural networks combined with distance-based classifiers such as nearest class mean. In this work, we introduce a Gaussian model of the feature distribution. By estimating the parameters of this model, we are able to predict the generalization error on new classification tasks with few samples. We observe that accurate distance estimates between class-conditional densities are the key to accurate estimates of the generalization performance. Therefore, we propose an unbiased estimator for these distances and integrate it in our numerical analysis. We show that our approach outperforms alternatives such as the leave-one-out cross-validation strategy in few-shot settings.

The use of needles to access sites within organs is fundamental to many interventional medical procedures both for diagnosis and treatment. Safe and accurate navigation of a needle through living tissue to an intra-tissue target is currently often challenging or infeasible due to the presence of anatomical obstacles in the tissue, high levels of uncertainty, and natural tissue motion (e.g., due to breathing). Medical robots capable of automating needle-based procedures in vivo have the potential to overcome these challenges and enable an enhanced level of patient care and safety. In this paper, we show the first medical robot that autonomously navigates a needle inside living tissue around anatomical obstacles to an intra-tissue target. Our system leverages an aiming device and a laser-patterned highly flexible steerable needle, a type of needle capable of maneuvering along curvilinear trajectories to avoid obstacles. The autonomous robot accounts for anatomical obstacles and uncertainty in living tissue/needle interaction with replanning and control and accounts for respiratory motion by defining safe insertion time windows during the breathing cycle. We apply the system to lung biopsy, which is critical in the diagnosis of lung cancer, the leading cause of cancer-related death in the United States. We demonstrate successful performance of our system in multiple in vivo porcine studies and also demonstrate that our approach leveraging autonomous needle steering outperforms a standard manual clinical technique for lung nodule access.

To apply federated learning to drug discovery we developed a novel platform in the context of European Innovative Medicines Initiative (IMI) project MELLODDY (grant n{\deg}831472), which was comprised of 10 pharmaceutical companies, academic research labs, large industrial companies and startups. The MELLODDY platform was the first industry-scale platform to enable the creation of a global federated model for drug discovery without sharing the confidential data sets of the individual partners. The federated model was trained on the platform by aggregating the gradients of all contributing partners in a cryptographic, secure way following each training iteration. The platform was deployed on an Amazon Web Services (AWS) multi-account architecture running Kubernetes clusters in private subnets. Organisationally, the roles of the different partners were codified as different rights and permissions on the platform and administrated in a decentralized way. The MELLODDY platform generated new scientific discoveries which are described in a companion paper.

语音活动检测（VAD）旨在检测音频信号上的语音段，这对于许多今天的基于语音的应用程序来说是必要的第一步。当前的最新方法着重于训练直接包含声学中包含的神经网络，例如MEL Filter Basks（MFBS）。因此，此类方法需要一个额外的归一化步骤，以适应影响声学的新领域，这可能仅仅是由于说话者，麦克风或环境的变化所致。此外，这个归一化步骤通常是一种具有一定局限性的基本方法，例如高度容易受到新域可用的数据量。在这里，我们利用了众包共同的声音（CV）语料库，以表明基于自我监督学习（SSL）的表示形式可以很好地适应不同的领域，因为它们是通过跨多个领域的语音表达来计算的。 SSL表示也比基于手工制作的表示（MFB）和现成的VAD的系统获得更好的结果，并在跨域设置方面有了显着改善。

大多数自动情绪识别系统利用情绪的时间连续注释，以提供对自发表达的细粒度描述，如现实生活中所观察到的那样。由于情感是相当主观的，因此通常由几个注释者执行的注释，这些注释为给定维度提供痕迹，即描述诸如唤醒或价值之类的维度的时间连续系列。但是，相同表达式的注释在时间或价值之间很少一致，这增加了用于学习情感预测模型的迹线的偏见和延迟。因此，我们提出了一种可以动态补偿注释之间的矛盾的方法，并使用复发性神经网络将痕迹与相应的声学特征同步。进行了几个情绪数据集进行实验评估，其中包括中文，法语，德语和匈牙利参与者，他们在无噪声条件或野外进行远程互动。结果表明，对于唤醒和价值，我们的方法可以显着增加通道间的一致性以及迹线和音频特征之间的相关性。此外，在使用简单的轻量重量模型对这些维度的自动预测中获得了改进，尤其是在无噪声条件下的价值中，并唤醒了在野外捕获的记录。

受数字孪生系统的启发，开发了一个新型的实时数字双框架，以增强机器人对地形条件的感知。基于相同的物理模型和运动控制，这项工作利用了与真实机器人同步的模拟数字双重同步，以捕获和提取两个系统之间的差异信息，这两个系统提供了多个物理数量的高维线索，以表示代表差异建模和现实世界。柔软的，非刚性的地形会导致腿部运动中常见的失败，因此，视觉感知完全不足以估计地形的这种物理特性。我们使用了数字双重来开发可折叠性的估计，这通过动态步行过程中的物理互动来解决此问题。真实机器人及其数字双重双重测量之间的感觉测量的差异用作用于地形可折叠性分析的基于学习的算法的输入。尽管仅在模拟中受过培训，但学习的模型可以在模拟和现实世界中成功执行可折叠性估计。我们对结果的评估表明，对不同方案和数字双重的优势的概括，可在地面条件下可靠地检测到细微差别。

算法选择向导是有效且通用的工具，它们会自动选择有关该问题和可用计算资源的高级信息的优化算法，例如决策变量的数量和类型，最大程度的评估数量，并行评估等。艺术算法选择向导很复杂且难以改进。我们在这项工作中建议使用自动配置方法来通过找到构成它们的算法的更好配置来改善其性能。特别是，我们使用精英迭代赛车（IRACE）来找到特定人工基准测试的CMA配置，这些基准取代了Nevergrad平台提供的NGOPT向导中当前使用的手工制作的CMA配置。我们详细讨论了IRACE的设置，目的是生成在每个基准内的各种问题实例集合中都可以正常工作的配置。我们的方法也提高了NGOPT向导的性能，即使在不属于Irace的一部分的基准套件上。

在过去的十年中，图上的信号处理已成为一个非常活跃的研究领域。具体而言，使用从图形上构建的框架（例如图上的小波）在统计或深度学习中的应用数量显着增加。我们特别考虑通过数据驱动的小波紧密框架方法在图表上进行信号的情况。这种自适应方法基于使用Stein的无偏风险估计校准的阈值，该阈值适合于紧密框架表示。我们可以使用Chebyshev-Jackson多项式近似值将其扩展到大图，从而可以快速计算小波系数，而无需计算laplacian特征性组成。但是，紧密框架的过度本质将白噪声转化为相关的噪声。结果，转换噪声的协方差出现在确定的差异项中，因此需要计算和存储框架，从而导致大图的不切实际计算。为了估计这种协方差，我们基于零均值和单位方差随机变量的快速转换制定和分析蒙特卡洛策略。这种新的数据驱动的denoisisy方法可以在差异隐私中发现自然应用。从真实和模拟数据的大小变化图上进行了全面的性能分析。