Results 141 to 150 of about 283,589 (317)
Advanced Intelligent Systems, EarlyView.A hierarchical multimodal framework coupling a large language model for task decomposition and semantic mapping with a fine‐tuned vision‐language model for semantic perception, enhanced by GridMask, is presented. An aerial‐ground robot team exploits the semantic map for global and local planning.
Haokun Liu +6 more
wiley +1 more source
Securing Generative Artificial Intelligence with Parallel Magnetic Tunnel Junction True Randomness
Advanced Intelligent Systems, EarlyView.True random numbers can protect generative artificial intelligence (GAI) models from attacks. A highly parallel, spin‐transfer torque magnetic tunnel junction‐based system is demonstrated that generates high‐quality, energy‐efficient random numbers.
Youwei Bao, Shuhan Yang, Hyunsoo Yang
wiley +1 more source
Advanced Intelligent Systems, EarlyView.This study presents a new sampling‐based model predictive control minimizing reverse Kullback‐Leibler divergence to quickly find a local optimum. In addition, a modified Nesterov's acceleration method is introduced for faster convergence. The method is effective for real‐time simulations and real‐world operability improvement on a force‐driven mobile ...
Taisuke Kobayashi, Kota Fukumoto
wiley +1 more source
Advanced Intelligent Systems, EarlyView.A surrogate‐model‐based framework is proposed for combining high‐fidelity finite element method and efficient physics simulations to enable fast, accurate soft robot simulation for reinforcement learning, validated through sim‐to‐real experiments. Soft robotics holds immense promise for applications requiring adaptability and compliant interactions ...
Taehwa Hong +3 more
wiley +1 more source
Review of Memristors for In‐Memory Computing and Spiking Neural Networks
Advanced Intelligent Systems, EarlyView.Memristors uniquely enable energy‐efficient, brain‐inspired computing by acting as both memory and synaptic elements. This review highlights their physical mechanisms, integration in crossbar arrays, and role in spiking neural networks. Key challenges, including variability, relaxation, and stochastic switching, are discussed, alongside emerging ...
Mostafa Shooshtari +2 more
wiley +1 more source
On Two Non-Ergodic Reversible Cellular Automata, One Classical, the Other Quantum. [PDF]
Entropy (Basel), 2023 Prosen T.
europepmc +1 more source
Advanced Intelligent Systems, EarlyView.This work presents a hybrid model for predicting the electrical characteristics of fin‐shaped field‐effect transistor devices and SRAM with line edge roughness. The model consists of a convolutional neural network (CNN) and an analytical model that simulates the electrical characteristics of transistors using the outputs of CNN, enabling fast and ...
Jaehyuk Lim +4 more
wiley +1 more source