Results 61 to 70 of about 169,282 (318)
Advanced Science, EarlyView.This study presents BraMARS, an explainable deep learning model that estimates future brain metastasis risk in surgically resected limited‐stage small‐cell lung cancer using routine H&E‐stained whole‐slide images. By linking model‐attributed spatial histopathology with clinical outcomes and proteomic programs, BraMARS provides a biologically ...
Zijian Yang +10 more
wiley +1 more source
Proceedings of the 2025 Conference on Empirical Methods in Natural Language ProcessingIn recent years, developing compact and efficient large language models (LLMs) has emerged as a thriving area of research. Traditional Supervised Fine-Tuning (SFT), which relies on singular ground truth labels, often fails to capture token-level dependencies and linguistic diversity.
Jingyao Li 0001 +6 more
openaire +3 more sources
Bankruptcy Prediction: The Case of the Greek Market
Forecasting, 2020 Financial bankruptcy prediction is an essential issue in emerging economies taking into consideration the economic upheaval that can be caused by business failures.
Angeliki Papana, Anastasia Spyridou
doaj +1 more source
Class-Level Logit Perturbation [PDF]
Features, logits, and labels are the three primary data when a sample passes through a deep neural network (DNN). Feature perturbation and label perturbation receive increasing attention in recent years. They have been proven to be useful in various deep
Wu, Ou +3 more
core +1 more source
Semiparametric Multinomial Logit Models for Analysing Consumer Choice Behaviour [PDF]
, 2006 The multinomial logit model (MNL) is one of the most frequently used statistical models in marketing applications. It allows to relate an unordered categorical response variable, for example representing the choice of a brand, to a vector of covariates ...
Steiner, Winfried J. +2 more
core +1 more source
Learning Work Function via Implicit Reasoning on Electrostatic Potential Landscapes
Advanced Science, EarlyView.StructPot‐CLR establishes a cross‐modal contrastive learning framework that aligns the crystal structures of 2D materials with plane‐averaged electrostatic potential landscapes for physically informed work‐function prediction. The model achieves an MAE of 0.265 eV and an R2 of 0.902 on the held‐out test set while accurately preserving key morphological
Haoyu Wan, Yue Wu, Tianhao Su, Deng Pan
wiley +1 more source
Advanced Science, EarlyView.MethyAnno enables robust and interpretable annotation of single‐cell DNA methylation data by integrating multi‐scale epigenetic information, bidirectional cross‐attention, and prototype‐based metric learning. The framework resolves rare and novel cell types across datasets while revealing cell‐type‐specific epigenetic signatures associated with disease
Yuhang Jia +4 more
wiley +1 more source
Beyond work-life balance: decomposing the gender gap in physical activity
Journal of Applied EconomicsDespite adjustments in work-life balance and the distribution of household tasks, the gender gap in physical activity remains persistent. Physical activity plans should target the gap’s root causes.
Sara Suarez-Fernandez +3 more
doaj +1 more source
Specification(s) of Nested Logit Models [PDF]
The nested logit model has become an important tool for the empirical analysis of discrete outcomes. There is some confusion about its specification of the outcome probabilities. Two major variants show up in the literature.
Florian Heiss
core
Advanced Science, EarlyView.A dynamic Ag+─S coordinated hydrogel with a sulfur–oxygen competitive coordination allosteric switch enables reversible tuning between soft–adhesive and stiff–robust states. Integrated with a lightweight 1DCNN classifier, the smart glove system achieves 99.70% laboratory and 93.35% real‐wear material recognition accuracy, offering a paradigm for self ...
Shixia Lan +4 more
wiley +1 more source