Intrinsically Design‐Rule‐Compliant Nanophotonic Inverse Design via Learned Generative Manifolds
A generative reparameterization framework for nanophotonic inverse design is introduced, restricting optimization to a learned manifold of design‐rule‐compliant geometries. Unlike conventional penalty‐based approaches, fabrication constraints are encoded intrinsically within the design representation.
Bahrem Serhat Danis +8 more
wiley +1 more source
Robust topology and dispatch optimization for renewable distribution networks with electric vehicle mobility uncertainty. [PDF]
Xu L, Jiang J, Hu S, Wang T, Dong J.
europepmc +1 more source
A Self‐Evolving Agentic Framework for Metasurface Inverse Design
Turning a target optical response into working inverse‐design code normally demands specialized computational‐electromagnetics and software‐engineering expertise. A self‐evolving agentic framework lowers this barrier: from a natural‐language request, it writes the optimization code that drives a physical solver and improves itself by revising human ...
Yi Huang +6 more
wiley +1 more source
Adaptive Localization for Underwater Nodes in Uncertain Environments: A Geometric Topology Perception-Enhanced Multi-Stage Reinforcement Learning Strategy. [PDF]
Hao L, Ma C, Cui J, Ao J.
europepmc +1 more source
Mass Spectrometry‐Based Extracellular Vesicle Proteomics for Biomarker Discovery
ABSTRACT Extracellular vesicle (EV) proteomics has emerged as a powerful platform for decoding intercellular communication and advancing biomarker discovery across human diseases. EVs carry proteins that reflect their cells of origin, offering a minimally invasive window into physiological and pathological processes.
Ya‐Juan Liu, Juan Peng, Chao Kang
wiley +1 more source
A stochastic model for dynamic reconfiguration of multi-microgrid networks under demand and supply uncertainties. [PDF]
Yahia Z, Gheith M.
europepmc +1 more source
SUZUKI, Yusaku +2 more
openaire +2 more sources
We present DataEX_Sc, a specialized model for parsing scatter plots, to make valuable contributions to data‐driven materials science. It improves accuracy by 0.23 (absolute F1 gain when relative error threshold = 0.02) over full‐automatic tools and boosts efficiency by 80% compared with semi‐automated tools.
Qianxue Tang +4 more
wiley +1 more source
Optimization and Deployment of Real-Time On-Orbit Intelligent Interpretation Algorithms for Spaceborne Remote Sensing. [PDF]
Li C +5 more
europepmc +1 more source
Interdiction Models and Heuristics for Graph Propagation
ABSTRACT Given a graph G=(V,E)$$ G=\left(V,E\right) $$ and a set S⊂V$$ S\subset V $$ of activated/infected nodes, we consider the problem of determining the set of c$$ c $$ nodes that minimizes the network propagation on the subgraph that results from the removal of those c$$ c $$ nodes. To measure network propagation, we assume that a node i$$ i $$ is
Agostinho Agra, José Maria Samuco
wiley +1 more source

