Related papers: Active-Code Replacement in the OODIDA Data Analyti…
End-to-end visuomotor policies trained using behavior cloning have shown a remarkable ability to generate complex, multi-modal low-level robot behaviors. However, at deployment time, these policies still struggle to act reliably when faced…
Imitation learning has shown promise in learning from large-scale real-world datasets. However, pretrained policies usually perform poorly without sufficient in-domain data. Besides, human-collected demonstrations entail substantial labour…
Offloading resource-intensive jobs to the cloud and nearby users is a promising approach to enhance mobile devices. This paper investigates a hybrid offloading system that takes both infrastructure-based networks and Ad-hoc networks into…
Monitoring of the large-scale data processing of the ATLAS experiment includes monitoring of production and user analysis jobs. The Experiment Dashboard provides a common job monitoring solution, which is shared by ATLAS and CMS…
Increasingly sophisticated function development is taking place with the aim of developing efficient, safe and increasingly Automated Driving Functions. This development is possible with the use of diverse data from sources such as…
Previous OOD detection systems only focus on the semantic gap between ID and OOD samples. Besides the semantic gap, we are faced with two additional gaps: the domain gap between source and target domains, and the class-imbalance gap between…
Autotuning techniques are a promising approach to minimize the otherwise tedious manual effort of optimizing scientific applications for a specific target platform. Ideally, an autotuning approach is capable of reliably identifying the most…
Metadata hotspots remain one of the key obstacles to scalable Input/Output (I/O) in both High-Performance Computing (HPC) and cloud-scale storage environments. Situations such as job start-ups, checkpoint storms, or heavily skewed namespace…
Outlier detection is an important task for various data mining applications. Current outlier detection techniques are often manually designed for specific domains, requiring large human efforts of database setup, algorithm selection, and…
Due to the pervasive diffusion of personal mobile and IoT devices, many ``smart environments'' (e.g., smart cities and smart factories) will be, among others, generators of huge amounts of data. Currently, this is typically achieved through…
Dialogue systems have the potential to change how people interact with machines but are highly dependent on the quality of the data used to train them. It is therefore important to develop good dialogue annotation tools which can improve…
Distributed computing, in which a resource-intensive task is divided into subtasks and distributed among different machines, plays a key role in solving large-scale problems. Coded computing is a recently emerging paradigm where redundancy…
Virtually all of today's Big Data systems are passive in nature, responding to queries posted by their users. Instead, we are working to shift Big Data platforms from passive to active. In our view, a Big Active Data (BAD) system should…
Multimodal IoT systems coordinate diverse IoT devices to deliver human-centered services. The ability to incorporate new IoT devices under the management of a centralized platform is an essential requirement. However, it requires…
Modern large-scale scientific discovery requires multidisciplinary collaboration across diverse computing facilities, including High Performance Computing (HPC) machines and the Edge-to-Cloud continuum. Integrated data analysis plays a…
Most machine learning and data analytics applications, including performance engineering in software systems, require a large number of annotations and labelled data, which might not be available in advance. Acquiring annotations often…
Human annotation is a time-consuming task that requires a significant amount of effort. To address this issue, interactive data annotation utilizes an annotation model to provide suggestions for humans to approve or correct. However,…
In the context of modern machine learning, models deployed in real-world scenarios often encounter diverse data shifts like covariate and semantic shifts, leading to challenges in both out-of-distribution (OOD) generalization and detection.…
When testing conditions differ from those represented in training data, so-called out-of-distribution (OOD) inputs can mar the reliability of learned components in the modern robot autonomy stack. Therefore, coping with OOD data is an…
End-to-end differentiable learning for autonomous driving (AD) has recently become a prominent paradigm. One main bottleneck lies in its voracious appetite for high-quality labeled data e.g. 3D bounding boxes and semantic segmentation,…