Related papers: Enabling High Data Throughput Reinforcement Learni…
A parametric adaptive greedy Latent Space Dynamics Identification (gLaSDI) framework is developed for accurate, efficient, and certified data-driven physics-informed greedy auto-encoder simulators of high-dimensional nonlinear dynamical…
Semantic segmentation of microscopy images is a critical task for high-throughput materials characterisation, yet its automation is severely constrained by the prohibitive cost, subjectivity, and scarcity of expert-annotated data. While…
Extreme-edge scientific applications use machine learning models to analyze sensor data and make real-time decisions. Their stringent latency and throughput requirements demand small batch sizes and require that model weights remain fully…
The parametric greedy latent space dynamics identification (gLaSDI) framework has demonstrated promising potential for accurate and efficient modeling of high-dimensional nonlinear physical systems. However, it remains challenging to handle…
Humans perceive the world through multiple senses, enabling them to create a comprehensive representation of their surroundings and to generalize information across domains. For instance, when a textual description of a scene is given,…
Recent advances in generative adversarial networks (GANs) have shown remarkable progress in generating high-quality images. However, this gain in performance depends on the availability of a large amount of training data. In limited data…
High-Performance Computing (HPC) platforms enable scientific software to achieve breakthroughs in many research fields such as physics, biology, and chemistry, by employing Research Software Engineering (RSE) techniques. These include 1)…
Performance evaluation of Retrieval-Augmented Generation (RAG) systems within enterprise environments is governed by multi-dimensional and composite factors extending far beyond simple final accuracy checks. These factors include reasoning…
Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous…
As machine learning models, specifically neural networks, are becoming increasingly popular, there are concerns regarding their trustworthiness, specially in safety-critical applications, e.g. actions of an autonomous vehicle must be safe.…
With the advent of system-in-package (SiP) chiplet-based design and heterogeneous 2.5D/3D integration, thermal-induced warpage has become a critical reliability concern. While conventional numerical approaches can deliver highly accurate…
When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world computing systems do not always provide stable resource…
Most approaches for goal recognition rely on specifications of the possible dynamics of the actor in the environment when pursuing a goal. These specifications suffer from two key issues. First, encoding these dynamics requires careful…
Most reinforcement learning(RL)-based methods for drone racing target fixed, obstacle-free tracks, leaving the generalization to unknown, cluttered environments largely unaddressed. This challenge stems from the need to balance racing speed…
This paper introduces a comprehensive framework designed to analyze and secure decision-support systems trained with Deep Reinforcement Learning (DRL), prior to deployment, by providing insights into learned behavior patterns and…
Accuracy and efficiency remain challenges for multi-party computation (MPC) frameworks. Spin is a GPU-accelerated MPC framework that supports multiple computation parties and a dishonest majority adversarial setup. We propose optimized…
Deep Reinforcement Learning has been able to achieve amazing successes in a variety of domains from video games to continuous control by trying to maximize the cumulative reward. However, most of these successes rely on algorithms that…
Deep Q-Network (DQN) marked a major milestone for reinforcement learning, demonstrating for the first time that human-level control policies could be learned directly from raw visual inputs via reward maximization. Even years after its…
To achieve scenario intelligence, humans must transfer knowledge to robots by developing goal-oriented algorithms, which are sometimes insensitive to dynamically changing environments. While deep reinforcement learning achieves significant…
Widespread use of memory unsafe programming languages (e.g., C and C++) leaves many systems vulnerable to memory corruption attacks. A variety of defenses have been proposed to mitigate attacks that exploit memory errors to hijack the…