Related papers: The Development of ADS Virtual Accelerator Based o…

In multi-domain learning (MDL) scenarios, high labeling effort is required due to the complexity of collecting data from various domains. Active Learning (AL) presents an encouraging solution to this issue by annotating a smaller number of…

AlphaGo's astonishing performance has ignited an explosive interest in developing deep reinforcement learning (DRL) for numerous real-world applications, such as intelligent robotics. However, the often prohibitive complexity of DRL stands…

The recent breakthroughs and prohibitive complexities of Deep Neural Networks (DNNs) have excited extensive interest in domain-specific DNN accelerators, among which optical DNN accelerators are particularly promising thanks to their…

Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many…

We describe the new version of the PDDL-to-ASP translator plasp. First, it widens the range of accepted PDDL features. Second, it contains novel planning encodings, some inspired by SAT planning and others exploiting ASP features such as…

Diffusion models (DMs) have become the leading choice for generative tasks across diverse domains. However, their reliance on multiple sequential forward passes significantly limits real-time performance. Previous acceleration methods have…

Surgical instrument segmentation in robot-assisted surgery (RAS) - especially that using learning-based models - relies on the assumption that training and testing videos are sampled from the same domain. However, it is impractical and…

Accelerator design languages (ADLs), high-level languages that compile to hardware units, help domain experts quickly design efficient application-specific hardware. ADL compilers optimize datapaths and convert software-like control flow…

Recent years have seen spectacular progress in the development of innovative acceleration methods that are not based on traditional RF accelerating structures. These novel developments are at the interface of laser, plasma and accelerator…

We present a status update on the dedicated R\&D facility SINBAD which is currently under construction at DESY. The facility will host multiple independent experiments on the acceleration of ultra-short electron bunches and novel, high…

Building an accelerator at six geographically dispersed sites is quite mad, but politically expedient. The Spallation Neutron Source (SNS), currently under construction in Oak Ridge, Tennessee, combines a pulsed 1 Gev H- superconducting…

Heterogeneous accelerator-centric compute clusters are emerging as efficient solutions for diverse AI workloads. However, current integration strategies often compromise data movement efficiency and encounter compatibility issues in…

3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, subsequently extending into numerous spatial AI applications. However, most existing 3DGS methods operate in isolation, focusing on specific domains.…

exa-AMD is a Python-based application designed to accelerate the discovery and design of functional materials by integrating AI/ML tools, materials databases, and quantum mechanical calculations into scalable, high-performance workflows.…

This paper presents the ARCAD simulator for the rapid development of Unmanned Aerial Systems (UAS), including underactuated and fully-actuated multirotors, fixed-wing aircraft, and Vertical Take-Off and Landing (VTOL) hybrid vehicles. The…

Particle accelerators are among the largest, most complex devices. To meet the challenges of increasing energy, intensity, accuracy, compactness, complexity and efficiency, increasingly sophisticated computational tools are required for…

Rescue robotics sets high requirements to perception algorithms due to the unstructured and potentially vision-denied environments. Pivoting Frequency-Modulated Continuous Wave radars are an emerging sensing modality for SLAM in this kind…

Virtual development and prototyping has already become an integral part in the field of automated driving systems (ADS). There are plenty of software tools that are used for the virtual development of ADS. One such tool is CarMaker from IPG…

In a recent study, Reinforcement Learning (RL) used in combination with many-objective search, has been shown to outperform alternative techniques (random search and many-objective search) for online testing of Deep Neural Network-enabled…

In the realm of automated driving simulation and sensor modeling, the need for highly accurate sensor models is paramount for ensuring the reliability and safety of advanced driving assistance systems (ADAS). Hence, numerous works focus on…