人类代理团队，这是一个问题，其中人类和自治机构合作实现一项任务，是人类AI协作的典型。为有效的合作，人类希望有一个有效的计划，而是在现实的情况下，他们可能难以计算由于认知限制的最佳计划。在这种情况下，具有许多计算资源的代理的指导可能是有用的。但是，如果代理人明确指导人类行为，人类可能会觉得他们已经失去了自主，并由代理商控制。因此，我们调查了通过代理人行为提供的隐性指导。通过这种指导，代理商以一种方式使人类能够易于找到合作任务的有效计划，然后可以改善计划。由于人类自愿改善了他们的计划，他或她保持自治。我们通过将贝叶斯思想理论集成到现有的协作规划算法中并通过行为实验进行了模拟了一个具有隐含指导，并通过隐性指导的行为实验证明了使人们能够在改善计划和保留自治之间保持平衡。

Large-scale vision-language models such as CLIP have shown impressive performance on zero-shot image classification and image-to-text retrieval. However, such zero-shot performance of CLIP-based models does not realize in tasks that require a finer-grained correspondence between vision and language, such as Visual Question Answering (VQA). We investigate why this is the case, and report an interesting phenomenon of CLIP, which we call the Concept Association Bias (CAB), as a potential cause of the difficulty of applying CLIP to VQA and similar tasks. CAB is especially apparent when two concepts are present in the given image while a text prompt only contains a single concept. In such a case, we find that CLIP tends to treat input as a bag of concepts and attempts to fill in the other missing concept crossmodally, leading to an unexpected zero-shot prediction. For example, when asked for the color of a lemon in an image, CLIP predicts ``purple'' if the image contains a lemon and an eggplant. We demonstrate the Concept Association Bias of CLIP by showing that CLIP's zero-shot classification performance greatly suffers when there is a strong concept association between an object (e.g. lemon) and an attribute (e.g. its color). On the other hand, when the association between object and attribute is weak, we do not see this phenomenon. Furthermore, we show that CAB is significantly mitigated when we enable CLIP to learn deeper structure across image and text embeddings by adding an additional Transformer on top of CLIP and fine-tuning it on VQA. We find that across such fine-tuned variants of CLIP, the strength of CAB in a model predicts how well it performs on VQA.

A practical issue of edge AI systems is that data distributions of trained dataset and deployed environment may differ due to noise and environmental changes over time. Such a phenomenon is known as a concept drift, and this gap degrades the performance of edge AI systems and may introduce system failures. To address this gap, a retraining of neural network models triggered by concept drift detection is a practical approach. However, since available compute resources are strictly limited in edge devices, in this paper we propose a lightweight concept drift detection method in cooperation with a recently proposed on-device learning technique of neural networks. In this case, both the neural network retraining and the proposed concept drift detection are done by sequential computation only to reduce computation cost and memory utilization. Evaluation results of the proposed approach shows that while the accuracy is decreased by 3.8%-4.3% compared to existing batch-based detection methods, it decreases the memory size by 88.9%-96.4% and the execution time by 1.3%-83.8%. As a result, the combination of the neural network retraining and the proposed concept drift detection method is demonstrated on Raspberry Pi Pico that has 264kB memory.

Human pose estimation, particularly in athletes, can help improve their performance. However, this estimation is difficult using existing methods, such as human annotation, if the subjects wear loose-fitting clothes such as ski/snowboard wears. This study developed a method for obtaining the ground truth data on two-dimensional (2D) poses of a human wearing loose-fitting clothes. This method uses fast-flushing light-emitting diodes (LEDs). The subjects were required to wear loose-fitting clothes and place the LED on the target joints. The LEDs were observed directly using a camera by selecting thin filmy loose-fitting clothes. The proposed method captures the scene at 240 fps by using a high-frame-rate camera and renders two 30 fps image sequences by extracting LED-on and -off frames. The temporal differences between the two video sequences can be ignored, considering the speed of human motion. The LED-on video was used to manually annotate the joints and thus obtain the ground truth data. Additionally, the LED-off video, equivalent to a standard video at 30 fps, confirmed the accuracy of existing machine learning-based methods and manual annotations. Experiments demonstrated that the proposed method can obtain ground truth data for standard RGB videos. Further, it was revealed that neither manual annotation nor the state-of-the-art pose estimator obtains the correct position of target joints.

Dynamic movement primitives are widely used for learning skills which can be demonstrated to a robot by a skilled human or controller. While their generalization capabilities and simple formulation make them very appealing to use, they possess no strong guarantees to satisfy operational safety constraints for a task. In this paper, we present constrained dynamic movement primitives (CDMP) which can allow for constraint satisfaction in the robot workspace. We present a formulation of a non-linear optimization to perturb the DMP forcing weights regressed by locally-weighted regression to admit a Zeroing Barrier Function (ZBF), which certifies workspace constraint satisfaction. We demonstrate the proposed CDMP under different constraints on the end-effector movement such as obstacle avoidance and workspace constraints on a physical robot. A video showing the implementation of the proposed algorithm using different manipulators in different environments could be found here https://youtu.be/hJegJJkJfys.

研究过程包括许多决定，例如如何应有资格以及在何处发表论文。在本文中，我们介绍了一个一般框架，以调查此类决策的影响。研究效果的主要困难是我们需要了解反事实结果，而实际上并非现实。我们框架的主要见解是灵感来自现有的反事实分析，其中研究人员将双胞胎视为反事实单位。提出的框架将一对彼此引用为双胞胎的论文。这些论文往往是平行的作品，在类似的主题和类似社区中。我们调查了采用不同决策的双论文，观察这些研究带来的研究影响的进展，并通过这些研究的影响来估算决策的影响。我们发布了我们的代码和数据，我们认为由于数据集缺乏反事实研究，因此这是非常有益的。

三维（3D）医学图像的产生可能具有巨大的应用潜力，因为它考虑了3D解剖结构。但是，有两个问题可以防止有效培训3D医疗生成模型：（1）3D医学图像的获取和注释非常昂贵，导致培训图像不足，（2）大量参数是参与3D卷积。为了解决这两个问题，我们提出了一种名为3D Split＆Shuffle-Gan的新型GAN模型。为了解决3D数据稀缺问题，我们首先使用丰富的图像切片预先培训二维（2D）GAN模型，并夸大2D卷积权重以改善3D GAN的初始化。为GAN模型的生成器和鉴别器提出了新型的3D网络体系结构，以显着减少参数的数量，同时保持图像生成的质量。研究了许多体重通胀策略和参数有效的3D架构。对心脏（Stanford Aimi冠状动脉钙）和大脑（阿尔茨海默氏病神经成像计划）的实验表明，所提出的方法会导致改善的3D图像产生质量，参数较少。

我们提出了一个框架，该框架会自动将不可缩放的GNN转换为基于预典型的GNN，该GNN对于大型图表有效且可扩展。我们框架的优势是两倍。1）它通过将局部特征聚合与其图形卷积中的重量学习分开，2）通过将其边缘分解为小型图形，将其有效地在GPU上进行了预先执行，将各种局部特征聚合与重量学习分开，将各种局部特征聚合从重量学习中分离出来，从而使各种不可估计的GNN转换为大规模图表。和平衡的集合。通过大规模图的广泛实验，我们证明了转化的GNN在训练时间内的运行速度比现有的GNN更快，同时实现了最先进的GNN的竞争精度。因此，我们的转型框架为可伸缩GNN的未来研究提供了简单有效的基础。

自我监督学习的最新发展使我们有可能进一步减少人类干预的多步管道中的干预，其中重点围绕着特定感兴趣的对象而发展。在本文中，焦点在组织病理学图像中的细胞核中放置。特别是，我们旨在以无监督的方式提取蜂窝信息，以完成下游任务。随着核以各种尺寸表现出来，我们提出了一个新的依赖量表卷积层来绕过调整核时尺寸的问题。在三个核数据集上，我们基准了以下方法：手工制作的，预先训练的重新系统，有监督的重新系统和自我监督的特征。我们表明，所提出的卷积层提高了性能，并且与Barlows-Twins结合使用，与低样本设置中的监督范式相比，该层可以更好地编码核编码，并且胜过所有其他建议的无监督方法。此外，我们将现有的TNBC数据集扩展到合并核类别的注释，以丰富和公开释放一个小样本设置数据集以进行核分割和分类。

捍卫深层神经网络免受对抗性示例是AI安全的关键挑战。为了有效地提高鲁棒性，最近的方法集中在对抗训练中的决策边界附近的重要数据点上。但是，这些方法容易受到自动攻击的影响，这是无参数攻击的合奏，可用于可靠评估。在本文中，我们通过实验研究了其脆弱性的原因，发现现有方法会减少真实标签和其他标签的逻辑之间的利润，同时保持其梯度规范非微小值。减少的边缘和非微小梯度规范会导致其脆弱性，因为最大的logit可以轻松地被扰动翻转。我们的实验还表明，logit边缘的直方图具有两个峰，即小和大的logit边缘。从观察结果来看，我们提出了切换单重损失（SOVR），当数据具有较小的logit rumgins时，它会使用单重损失，从而增加边缘。我们发现，SOVR比现有方法增加了logit的利润率，同时使梯度规范保持较小，并且在针对自动攻击的鲁棒性方面超越了它们。