NVIDIA Academic Grant: New Research Areas and Compute Resources

Hands-on learning is where innovation begins. We’re thrilled to see Arm bringing practical AI optimization to #IECON2025 📍 Madrid – Hotel Meliá Castilla 🗓 16 October 2025 | 10:50–12:50 💡 Optimizing AI on Arm CPUs and NPUs Join Kieran Hejmadi and Matt Cossins for a deep dive into: - Deploying AI across Arm-based compute architectures - Optimizing TensorFlow Lite models using the Vela compiler - Exploring TOSA and model portability - Evaluating hardware choices for real-world AI The Semiconductor Education Alliance believes skills like these are essential for the next generation of engineers — turning knowledge into capability and capability into impact. #AI #EdgeAI #Semiconductors #Arm #STEM #Education #Innovation #IECON2025

Hands-on learning is where innovation begins. We’re thrilled to see Arm bringing practical AI optimization to #IECON2025 with: 📍 Madrid – Hotel Meliá Castilla 🗓 16 October 2025 | 10:50–12:50 💡 Optimizing AI on Arm CPUs and NPUs   Join Kieran Hejmadi and Matt Cossins for a deep dive into: - Deploying AI across Arm-based compute architectures - Optimizing TensorFlow Lite models using the Vela compiler - Exploring TOSA and model portability - Evaluating hardware choices for real-world AI   The Semiconductor Education Alliance believes skills like these are essential for the next generation of engineers — turning knowledge into capability and capability into impact. #AI #EdgeAI #Semiconductors #Arm #STEM #Education #Innovation #IECON2025

We are pleased to announce that our latest chapter, titled "Membrane Pseudo-Bacterial Potential Field with GPU Acceleration for Mobile Robot Path Planning," has been published in the book Artificial Intelligence and Quantum Computing: Early Innovations, Volume 1. This research was a collaboration with Kenia Picos and Oscar Montiel Ross. In this work, we introduce the membrane pseudo-bacterial potential field algorithm with GPU (Graphics Processing Unit) acceleration for mobile robot path planning. The results demonstrate the effectiveness of the approach in terms of computational performance, achieving over 8 times faster on the CPU (Central Processing Unit) and more than 133 times faster on the GPU. https://lnkd.in/gdQaYap9 #ArtificialIntelligence #GPU #PathPlanning #MobileRobots #CETYS #Springer

Want to connect your own graph-based machine learning model to LAMMPS for multi-GPU molecular dynamics simulations? We've helped build an interface and wrote a blog to make this easier for developers. See our blog here: https://lnkd.in/e-EQGGy5 Our DevTech engineers collaborated with Los Alamos and Sandia National Labs to develop the ML-IAP-Kokkos interface, giving MLIP model developers a straightforward way to plug into LAMMPS and run scalable AI-driven atomistic simulations across multiple GPUs. This technical tutorial walks through the process with real code examples, benchmarks, and a ready-to-use container so you can skip the build and start simulating. The interface handles message-passing and GPU acceleration automatically, helping you scale from single systems to exascale computing. The interface also makes it easy to use NVIDIA libraries like cuEquivariance in your LAMMPS simulations for faster, more memory-efficient chemistry and materials research. With Forrest Glines Matt Bettencourt Franco Pellegrini Emine Kucukbenli #AI #moleculardynamics #deeplearning

Free Courses for the theme 'NVIDIA / GPU & AI Hardware' AI Infrastructure and Operations Fundamentals https://lnkd.in/gdhyZN5b Exam Prep (NCA-GENL): NVIDIA-Certified Generative AI LLMs Specialization https://lnkd.in/gmBuPkdn Jetson Nano Starter to Pro - A Computer Vision Course https://lnkd.in/gC3bgvmf Introduction to Networking https://lnkd.in/gZ-u9fV3 The Fundamentals of RDMA Programming https://lnkd.in/g_Za-KJa NVIDIA: Fundamentals of Machine Learning https://lnkd.in/gb4TtZjG GPU Programming Specialization https://lnkd.in/gijGAxqZ Self-Driving Cars Specialization https://lnkd.in/gpaDpGB9 Introduction to Parallel Programming with CUDA https://lnkd.in/gA2ZNAnz NVIDIA: Fundamentals of Deep Learning https://lnkd.in/gsSs_zCZ Happy learning! The original content of this is credited to its respective author. #NVIDIA #AIHardware #GPUComputing

🚀 E-track Best paper nominee at DATE2025 in Lyon “RankMap: Priority-Aware Multi-DNN Manager for Heterogeneous Embedded Devices” Andreas Karatzas, Dimitrios Stamoulis, Iraklis Anagnostopoulos from Southern Illinois University Carbondale, and The University of Texas at Austin Modern edge systems often run multiple deep neural networks (DNNs) simultaneously, but efficiently managing them across CPUs, GPUs, and other heterogeneous components remains a major challenge. RankMap takes this head-on. RankMap is a priority-aware multi-DNN manager that intelligently distributes DNN workloads across heterogeneous embedded devices. By combining fine-grained DNN partitioning, a multi-task attention-based performance estimator, and Monte Carlo Tree Search (MCTS) for smart mapping, RankMap achieves impressive gains: ⚡ Up to 3.6× higher throughput than state-of-the-art methods 🚫 Zero DNN starvation under heavy workloads 🎯 57.5× improvement in meeting priority constraints RankMap dynamically balances performance and fairness, ensuring that critical applications get the resources they need—without sacrificing system efficiency. This work paves the way for smarter, more reliable AI execution at the edge, where every millisecond and every core matters. #DATE2025 #EdgeAI #EmbeddedSystems #DeepLearning #Research #HPC #AIOptimization Aida Todri-Sanial Theo Theocharides Alberto Bosio Matteo Sonza Reorda Nele Mentens

We recently introduced NVIDIA NV-Tesseract, a family of models designed to unify anomaly detection, classification, and forecasting within a single framework. NVIDIA NV-Tesseract-AD builds on this foundation, introducing diffusion modeling stabilized through curriculum learning and paired with adaptive thresholding methods—addressing noisy, high-dimensional signals that drift over time. Learn more.

We recently introduced NVIDIA NV-Tesseract, a family of models designed to unify anomaly detection, classification, and forecasting within a single framework. NVIDIA NV-Tesseract-AD builds on this foundation, introducing diffusion modeling stabilized through curriculum learning and paired with adaptive thresholding methods—addressing noisy, high-dimensional signals that drift over time. Learn more.

We recently introduced NVIDIA NV-Tesseract, a family of models designed to unify anomaly detection, classification, and forecasting within a single framework. NVIDIA NV-Tesseract-AD builds on this foundation, introducing diffusion modeling stabilized through curriculum learning and paired with adaptive thresholding methods—addressing noisy, high-dimensional signals that drift over time. Learn more.

We recently introduced NVIDIA NV-Tesseract, a family of models designed to unify anomaly detection, classification, and forecasting within a single framework. NVIDIA NV-Tesseract-AD builds on this foundation, introducing diffusion modeling stabilized through curriculum learning and paired with adaptive thresholding methods—addressing noisy, high-dimensional signals that drift over time. Learn more.