Enhancing Digital Breast Tomosynthesis Sinograms via Budget-Constrained PSO-Nelder-Mead: A Vision Transformer Assessment. [PDF]
Rosas-Ordaz LF +5 more
europepmc +1 more source
Crystal Structure Prediction of Inorganic Materials: A Benchmark and Modern Evaluation
Predicting a crystal’s structure from composition alone is a long‐standing challenge in materials discovery. The CSP180 benchmark of 180 inorganic crystals evaluates thirteen crystal structure prediction algorithms requiring no density functional theory (DFT) against DFT‐based baselines across twelve metrics.
Lai Wei +9 more
wiley +1 more source
Test-Time Optimization of Physical ISP Parameters from a Single Calibration Pair for Cross-Camera Adaptation. [PDF]
Lee J, Kang MG.
europepmc +1 more source
Ecoefficiency Analysis and Regression in Data Conversion for Spiking Neural Network Training
The environmental footprint of spiking neural networks is quantified during dataset encoding and training for autonomous driving regression across three benchmarks. Temporal depth emerges as the dominant driver of energy consumption and CO2 emissions, while the accuracy–energy trade‐off proves dataset‐dependent. On conventional hardware, spiking models
Fernando S. Martínez +3 more
wiley +1 more source
A Scalable and Resource‐Efficient Pipelined p‐Computer for Probabilistic Ising Machines
(a) Block diagram of the portfolio optimization problem: given M assets, the goal is to determine the optimal weights w that maximize the expected return (based on the mean historical assets return u), while minimizing the risk, quantified by the assets covariance matrix S.
Deborah Volpe +9 more
wiley +1 more source
Optimising a national screen-and-treat cervical cancer strategy in Uganda: a microsimulation cost-effectiveness and budget impact analysis. [PDF]
Rukundo-Ayeh T +8 more
europepmc +1 more source
A training‐free two‐stage BO–RL framework extracts compact model parameters for a‐IGZO TFTs, reaching BO‐level fitting quality at a constant per‐simulation optimization cost. Bayesian optimization performs exploration and provides an optimized starting point.
Seunghyun Son +4 more
wiley +1 more source
Distributed electricity-carbon co-optimization of hydrogen energy storage microgrids with dynamic laplace perturbation and model predictive control. [PDF]
Li Z +5 more
europepmc +1 more source
Hardware‐learning co‐design combines volar‐plate‐inspired passive‐joint constraints with mechanism‐aware reinforcement learning for a low‐cost parallel‐linkage gripper. The resulting system performs quasi‐static object adjustment and dynamic pinch grasping, demonstrating reliable planar in‐hand manipulation and successful sim‐to‐real transfer. Parallel
Yanzhou Jin +4 more
wiley +1 more source
HeaTrace: A Parametric Design‐to‐Fabrication Workflow for Thermally Programmable Soft Robots
A programmable thermal actuation workflow enables soft robots to be designed and fabricated with embedded heaters that drive multiple responses. By combining performance‐driven heater design with multimaterial fabrication, the system supports thermally triggered shape change, stiffness tuning, and thermochromic visual response, as demonstrated through ...
Naresh Kumar Thanigaivel +9 more
wiley +1 more source

