Composition‐Aware Cross‐Sectional Integration for Spatial Transcriptomics
Advanced Intelligent Discovery, EarlyView.Multi‐section spatial transcriptomics demands coherent cell‐type deconvolution, domain detection, and batch correction, yet existing pipelines treat these tasks separately. FUSION unifies them within a composition‐aware latent framework, modeling reads as cell‐type–specific topics and clustering in embedding space.
Qishi Dong +5 more
wiley +1 more source
Correction: A meta-learning-based robust federated learning for diagnosing lung adenocarcinoma and tuberculosis granulomas. [PDF]
Front OncolChen Y +14 more
europepmc +1 more source
The Interoperability Challenge in DFT Workflows Across Implementations
Advanced Intelligent Discovery, EarlyView.Interoperability and cross‐validation remain major challenges in the computational materials science. In this work, we introduce a common input/output standard that enables internal translation across multiple workflow managers—AiiDA, PerQueue, Pipeline Pilot, and SimStack—while producing results in a unified schema.
Simon K. Steensen +13 more
wiley +1 more source
Reusability Report: Evaluating the performance of a meta-learning foundation model on predicting the antibacterial activity of natural products. [PDF]
Nat Mach IntellButt CM, Walker AS.
europepmc +1 more source
An Autonomous Large Language Model‐Agent Framework for Transparent and Local Time Series Forecasting
Advanced Intelligent Discovery, EarlyView.Architecture of the proposed large language model (LLM)‐based agent framework for autonomous time series forecasting in thermal power generation systems. The framework operates through a vertical pipeline initiated by natural language queries from users, which are processed by the LLM Agent Core powered by Llama.cpp and a ReAct loop with persistent ...
William Gouvêa Buratto +5 more
wiley +1 more source
Few-shot cross-domain fault diagnosis via adversarial meta-learning. [PDF]
Sci RepGuo Y, Dai J, Zhang J.
europepmc +1 more source
Overcoming the Nyquist Limit in Molecular Hyperspectral Imaging by Reinforcement Learning
Advanced Intelligent Discovery, EarlyView.Explorative spectral acquisition guide automatically selects informative spectral bands to optimize downstream tasks, outperforming full‐spectrum acquisition. The selected hyperspectral data are used for tasks such as unmixing and segmentation. BandOptiNet encodes selection states and outputs optimal bands to guide spectral acquisition. Recent advances
Xiaobin Tang +4 more
wiley +1 more source
A joint span-entity prediction approach with generative and cross-lingual meta-learning for low-resource Japanese NER. [PDF]
Sci RepShao X, Zhu D, Liu Q, Pan X.
europepmc +1 more source
A learning theory of meta learning [PDF]
Natl Sci RevThis paper gives a brief introduction to recent theoretical advance of meta learning.
europepmc +3 more sources
Advanced Intelligent Discovery, EarlyView.AI‐based tools enable rapid characterization of bacterial ultrastructure in low‐dose cryogenic transmission electron microscopy. The envelope thickness tool quantifies membrane thickness and anisotropy. The flagella module analyzes filament morphology and detects cell‐flagella contacts.
Sita Sirisha Madugula +10 more
wiley +1 more source