数字双胞胎（DT）本质上是动态数据驱动的模型，可作为现实世界系统的实时共生“虚拟副本”。 DT可以利用动态数据驱动的应用系统（DDDAS）双向共生感应反馈循环的基本面来进行连续更新。因此，传感循环可以操纵测量，分析和重新配置，旨在在DT中进行更准确的建模和分析。重新配置决策可以是自主的或互动的，可以保持人类在循环中。这些决定的可信赖性可能会因理由的解释性不足而阻碍，并在实施替代方案之间对给定情况的决定中获得了实用性。此外，不同的决策算法和模型具有不同的复杂性，质量，并可能导致模型获得不同的效用。解释性的不足可能会限制人类可以评估决策的程度，通常会导致更新，这些更新不适合给定的情况，错误，损害了模型的整体准确性。本文的新颖贡献是一种利用人类界DDDA和DT系统中解释性的方法，利用双向共生感应反馈。该方法利用可解释的机器学习和目标建模来解释性，并考虑了获得的实用程序的权衡分析。我们使用智能仓储中的示例来演示这种方法。

乘车共享因其方便和乘客的便利性和成本效率而获得了全球知名度，以及其强大的潜力有助于实施联合国可持续发展目标。结果，近年来，目睹了RSODP的研究兴趣（用于乘车共享的原产地预测）问题，目的是预测未来的乘车共享请求并提前为车辆提供时间表。大多数现有的预测模型都利用深度学习，但是它们无法有效地考虑空间和时间动态。在本文中，提出了基准的门控注意复发网络（BGARN），该网络（BGARN）使用具有多头门的图形卷积来提取空间特征，以提取时间特征的复发模块以及基线转移层来计算最终结果。该模型是使用Pytorch和DGL（Deep Graph库）实施的，并使用纽约出租车需求数据集对实验进行了评估。结果表明，BGARN在预测准确性方面优于所有其他现有模型。

View-dependent effects such as reflections pose a substantial challenge for image-based and neural rendering algorithms. Above all, curved reflectors are particularly hard, as they lead to highly non-linear reflection flows as the camera moves. We introduce a new point-based representation to compute Neural Point Catacaustics allowing novel-view synthesis of scenes with curved reflectors, from a set of casually-captured input photos. At the core of our method is a neural warp field that models catacaustic trajectories of reflections, so complex specular effects can be rendered using efficient point splatting in conjunction with a neural renderer. One of our key contributions is the explicit representation of reflections with a reflection point cloud which is displaced by the neural warp field, and a primary point cloud which is optimized to represent the rest of the scene. After a short manual annotation step, our approach allows interactive high-quality renderings of novel views with accurate reflection flow. Additionally, the explicit representation of reflection flow supports several forms of scene manipulation in captured scenes, such as reflection editing, cloning of specular objects, reflection tracking across views, and comfortable stereo viewing. We provide the source code and other supplemental material on https://repo-sam.inria.fr/ fungraph/neural_catacaustics/

Modern speech recognition systems exhibits rapid performance degradation under domain shift. This issue is especially prevalent in data-scarce settings, such as low-resource languages, where diversity of training data is limited. In this work we propose M2DS2, a simple and sample-efficient finetuning strategy for large pretrained speech models, based on mixed source and target domain self-supervision. We find that including source domain self-supervision stabilizes training and avoids mode collapse of the latent representations. For evaluation, we collect HParl, a $120$ hour speech corpus for Greek, consisting of plenary sessions in the Greek Parliament. We merge HParl with two popular Greek corpora to create GREC-MD, a test-bed for multi-domain evaluation of Greek ASR systems. In our experiments we find that, while other Unsupervised Domain Adaptation baselines fail in this resource-constrained environment, M2DS2 yields significant improvements for cross-domain adaptation, even when a only a few hours of in-domain audio are available. When we relax the problem in a weakly supervised setting, we find that independent adaptation for audio using M2DS2 and language using simple LM augmentation techniques is particularly effective, yielding word error rates comparable to the fully supervised baselines.

In this work, we propose a novel framework for estimating the dimension of the data manifold using a trained diffusion model. A trained diffusion model approximates the gradient of the log density of a noise-corrupted version of the target distribution for varying levels of corruption. If the data concentrates around a manifold embedded in the high-dimensional ambient space, then as the level of corruption decreases, the score function points towards the manifold, as this direction becomes the direction of maximum likelihood increase. Therefore, for small levels of corruption, the diffusion model provides us with access to an approximation of the normal bundle of the data manifold. This allows us to estimate the dimension of the tangent space, thus, the intrinsic dimension of the data manifold. Our method outperforms linear methods for dimensionality detection such as PPCA in controlled experiments.

This project leverages advances in multi-agent reinforcement learning (MARL) to improve the efficiency and flexibility of order-picking systems for commercial warehouses. We envision a warehouse of the future in which dozens of mobile robots and human pickers work together to collect and deliver items within the warehouse. The fundamental problem we tackle, called the order-picking problem, is how these worker agents must coordinate their movement and actions in the warehouse to maximise performance (e.g. order throughput) under given resource constraints. Established industry methods using heuristic approaches require large engineering efforts to optimise for innately variable warehouse configurations. In contrast, the MARL framework can be flexibly applied to any warehouse configuration (e.g. size, layout, number/types of workers, item replenishment frequency) and the agents learn via a process of trial-and-error how to optimally cooperate with one another. This paper details the current status of the R&D effort initiated by Dematic and the University of Edinburgh towards a general-purpose and scalable MARL solution for the order-picking problem in realistic warehouses.

Industry 4.0 aims to optimize the manufacturing environment by leveraging new technological advances, such as new sensing capabilities and artificial intelligence. The DRAEM technique has shown state-of-the-art performance for unsupervised classification. The ability to create anomaly maps highlighting areas where defects probably lie can be leveraged to provide cues to supervised classification models and enhance their performance. Our research shows that the best performance is achieved when training a defect detection model by providing an image and the corresponding anomaly map as input. Furthermore, such a setting provides consistent performance when framing the defect detection as a binary or multiclass classification problem and is not affected by class balancing policies. We performed the experiments on three datasets with real-world data provided by Philips Consumer Lifestyle BV.

Quality control is a crucial activity performed by manufacturing companies to ensure their products conform to the requirements and specifications. The introduction of artificial intelligence models enables to automate the visual quality inspection, speeding up the inspection process and ensuring all products are evaluated under the same criteria. In this research, we compare supervised and unsupervised defect detection techniques and explore data augmentation techniques to mitigate the data imbalance in the context of automated visual inspection. Furthermore, we use Generative Adversarial Networks for data augmentation to enhance the classifiers' discriminative performance. Our results show that state-of-the-art unsupervised defect detection does not match the performance of supervised models but can be used to reduce the labeling workload by more than 50%. Furthermore, the best classification performance was achieved considering GAN-based data generation with AUC ROC scores equal to or higher than 0,9898, even when increasing the dataset imbalance by leaving only 25\% of the images denoting defective products. We performed the research with real-world data provided by Philips Consumer Lifestyle BV.

With the success of Vision Transformers (ViTs) in computer vision tasks, recent arts try to optimize the performance and complexity of ViTs to enable efficient deployment on mobile devices. Multiple approaches are proposed to accelerate attention mechanism, improve inefficient designs, or incorporate mobile-friendly lightweight convolutions to form hybrid architectures. However, ViT and its variants still have higher latency or considerably more parameters than lightweight CNNs, even true for the years-old MobileNet. In practice, latency and size are both crucial for efficient deployment on resource-constraint hardware. In this work, we investigate a central question, can transformer models run as fast as MobileNet and maintain a similar size? We revisit the design choices of ViTs and propose an improved supernet with low latency and high parameter efficiency. We further introduce a fine-grained joint search strategy that can find efficient architectures by optimizing latency and number of parameters simultaneously. The proposed models, EfficientFormerV2, achieve about $4\%$ higher top-1 accuracy than MobileNetV2 and MobileNetV2$\times1.4$ on ImageNet-1K with similar latency and parameters. We demonstrate that properly designed and optimized vision transformers can achieve high performance with MobileNet-level size and speed.

Multimodal learning pipelines have benefited from the success of pretrained language models. However, this comes at the cost of increased model parameters. In this work, we propose Adapted Multimodal BERT (AMB), a BERT-based architecture for multimodal tasks that uses a combination of adapter modules and intermediate fusion layers. The adapter adjusts the pretrained language model for the task at hand, while the fusion layers perform task-specific, layer-wise fusion of audio-visual information with textual BERT representations. During the adaptation process the pre-trained language model parameters remain frozen, allowing for fast, parameter-efficient training. In our ablations we see that this approach leads to efficient models, that can outperform their fine-tuned counterparts and are robust to input noise. Our experiments on sentiment analysis with CMU-MOSEI show that AMB outperforms the current state-of-the-art across metrics, with 3.4% relative reduction in the resulting error and 2.1% relative improvement in 7-class classification accuracy.