CoSP: Reconfigurable Metamaterial Inverse Design via Contrastive Pretrained Large Language Model
In this work, CoSP (contrastive multi‐state pretrain), an intelligent inverse design method for reconfigurable metamaterials based on a contrastive pretrained large language model, is proposed. Numerical experiments demonstrate that CoSP can design reconfigurable metamaterial structures for multi‐state, multi‐band optical responses, showing great ...
Shujie Yang +4 more
wiley +1 more source
Classification of soft decision-making methods via fuzzy parameterized fuzzy soft matrices and their performance-based statistical analysis in machine learning. [PDF]
Karakoç Ö, Memiş S, Sennaroglu B.
europepmc +1 more source
Technical limitations often let dominant signals overshadow rare cell types and fine‐grained heterogeneity in spatial transcriptomics. SemanticST, a graph neural network using multi‐semantic graph fusion and a novel min‐cut loss, recovers these subtle patterns.
Roxana Zahedi +7 more
wiley +1 more source
Digital Standardized Patients: Conceptual Framework for Generative AI-Empowered Medical Education. [PDF]
Jia C, Qi L.
europepmc +1 more source
Performance Estimation and Ex Vivo Validation of Untethered Magnetic Robots in Soft Tissue
This study presents an empirical model that quantitatively predicts the step‐out frequency of screw‐type untethered magnetic robots (UMRs) in soft viscoelastic environments, including ex vivo brain tissue. By integrating key parameters into a dimensionless framework, the model enables estimation of robot performance across a range of biological ...
Leendert‐Jan W. Ligtenberg +19 more
wiley +1 more source
Long-Horizon Constraint-Aware Collaborative Scheduling for Multiple Phased-Array Radars Using Mamba Temporal Encoding and Structured Hybrid Actions. [PDF]
Liu J, Xu J, Xing W, Li M.
europepmc +1 more source
Machine Learning of Temperature‐Dependent Chemical Kinetics Using Parallel Droplet Microreactors
An integrated droplet microfluidics and machine learning framework enables high‐throughput characterization of temperature‐dependent reaction kinetics. Time‐resolved measurements from thousands of droplets train Neural ODE models that accurately predict nonlinear reaction dynamics across diverse thermal environments, bridging large‐scale ...
Mamoru Saita, Yutaka Hori
wiley +1 more source
Variable-Damping Impedance Control for Contact Tasks: A Reinforcement Learning Method Integrating HER and Importance Sampling. [PDF]
Guo X, Ding H, Ning X, Hou H, Cai J.
europepmc +1 more source
A metasurface‐enabled helical wavefront fingerprint (MHWF) paradigm is proposed for quantitative and specific retrieval of a liquid medium's refractive index and extinction coefficient. The liquid's complex dielectric response governs the wavefront evolution of the metasurface‐generated focused vortex beam, forming a distinctive three‐dimensional ...
Yuting Zhou +10 more
wiley +1 more source
Parameterized quantum random number generators for superconducting quantum hardware: novel architectures and NIST SP 800-22 evaluation under IBM noisy simulators. [PDF]
Salehi R, Malik AW, Novotny MA, Khan SU.
europepmc +1 more source

