Results 141 to 150 of about 6,965,125 (303)

Stable Diffusion Models Reveal a Persisting Human–AI Gap in Visual Creativity

Advanced Science, EarlyView.
This study examines visual creativity in humans and generative AI using the TCIA framework. Human artists outperform AI overall, yet structured human guidance substantially improves AI outputs and evaluations. Findings reveal that alignment with human creativity depends critically on contextual framing, highlighting both the promise and current ...
Silvia Rondini, Claudia Alvarez‐Martin, Paula Angermair‐Barkai, Olivier Penacchio, Marc Paz, Matthew Pelowski, Dan Dediu, Antoni Rodriguez‐Fornells, Xim Cerda‐Company   +8 more
wiley   +1 more source

Discovering Interpretable Semantics from Radio Signals for Contactless Cardiac Monitoring

Advanced Science, EarlyView.
This study presents a semantic representation framework for clinically interpretable cardiac monitoring from contactless radio signals. It formulates radio semantic learning as an information‐bottleneck problem and approximates the objective via intra‐modal compression and cross‐modal alignment, structuring radio measurements into meaningful semantic ...
Jinbo Chen, Haoyu Wang, Guixin Xu, Yuqin Yuan, Xinmeng Cai, Zhengwu Wei, Dongheng Zhang, Qibin Sun, Tianwei Zhang, Cuntai Guan, Yan Chen   +10 more
wiley   +1 more source

A Context-Theoretic Framework for Compositionality in Distributional Semantics

Computational Linguistics, 2021
Daoud Clarke
doaj   +1 more source

Beyond MSE in Poisson Ridge Regression: New Ridge Parameter Estimators with Additional Distributional Performance Criteria

Mathematics
Despite its widespread use for mitigating multicollinearity in count data models, Poisson ridge regression (PRR) remains methodologically constrained by the choice of the ridge parameter k.
Selman Mermi
doaj   +1 more source

Semantic discrimination of technicality in French nominalizations

Zeitschrift für Wortbildung, 2020
French suffixations in -age, -ion and -ment are considered roughly equivalent, yet some differences have been pointed out regarding the semantics of the resulting nominalizations.
Marine Wauquier, Nabil Hathout, Cécile Fabre   +2 more
doaj   +1 more source

Schooling Trajectories and the Development of Brain Dynamics: A Comparative Study of Montessori and Traditional Education

Advanced Science, EarlyView.
We investigate whether Montessori and traditional schooling systems shape the developmental trajectory of large‐scale brain dynamics in different ways. We quantify the arrow of time (“non‐reversibility”) in neural activity during resting state and movie‐watching, revealing distinct maturational patterns.
Elvira del Agua, Anira Escrichs, Yonatan Sanz Perl, Morten L. Kringelbach, Adele Diamond, Solange Denervaud, Gustavo Deco   +6 more
wiley   +1 more source

Distributional Memory: A General Framework for Corpus-Based Semantics

Computational Linguistics, 2021
Marco Baroni, Alessandro Lenci
doaj   +1 more source

MGDP: Mastering a Generalized Depth Perception Model for Quadruped Locomotion

Advanced Science, EarlyView.
ABSTRACT Perception‐based Deep Reinforcement Learning (DRL) controllers demonstrate impressive performance on challenging terrains. However, existing controllers still face core limitations, struggling to achieve both terrain generality and platform transferability, and are constrained by high computational overhead and sensitivity to sensor noise.
Yinzhao Dong, Ji Ma, Yidan Lu, Jiahui Zhang, Wanyue Li, Yeke Chen, Teng Zhang, Xuechao Chen, Zhangguo Yu, Peng Lu   +9 more
wiley   +1 more source

Artificial Intelligence Powers Protein Functional Annotation

Advanced Science, EarlyView.
This review systematically summarizes how artificial intelligence advances protein functional annotation. It organizes existing methods into six unified modeling paradigms and analyzes their applications in Gene Ontology and Enzyme Commission prediction.
Wenkang Wang, Qiurong Yang, Min Zeng, Ruiqing Zheng, Min Li   +4 more
wiley   +1 more source

PAIR: Reconstructing Single‐Cell Open‐Chromatin Landscapes for Transcription Factor Regulome Mapping

Advanced Science, EarlyView.
scATAC‐seq analysis is often constrained by limited sequencing depth, extreme sparsity, and pervasive technical missingness. PAIR is a probabilistic framework that restores scATAC‐seq accessibility profiles by directly modeling the native cell–peak bipartite structure of chromatin accessibility.
Yanchi Su, Qi Qi, Yi Fan, Yubo Wang, Gaoyang Hao, Ka‐Chun Wong, Yunhe Wang, Xiangtao Li   +7 more
wiley   +1 more source