ULBERT: a domain-adapted BERT model for bilingual information retrieval from Pakistan's constitution. [PDF]
Abbas Q, Nawaz W, Niazi S, Awais M.
europepmc +1 more source
Polynomial time learning of simple deterministic languages via queries and a representative sample
Yasuhiro Tajima +3 more
openalex +1 more source
Dynamic Neural Deactivation Bridges Direct and Competitive Inhibition Processes
Dynamic neural deactivation bridges traditionally distinct inhibitory mechanisms—direct inhibition and competition‐induced inhibition—revealing a common neural signature across modalities. Multimodal neuroimaging and behavioral experiments demonstrate a temporal dynamic characterized by progressive frontoparietal activation decay and enhanced sensory ...
Zhenhong He +6 more
wiley +1 more source
Digital twins as self-models for intelligent structures. [PDF]
Shen X, Wagg DJ, Tipuric M, Bonney MS.
europepmc +1 more source
The Potential of Cognitive‐Inspired Neural Network Modeling Framework for Computer Vision
In article number 202507730, Guorun Li, Lei Liu, Yuefeng Du, and co‐workers present a cognitive modeling framework (CMF) to bridge the ‘representation gap’ and ‘conceptual gap’ between cognitive theory and vision deep neural networks (VDNNs). The research findings provide new insights and solid theoretical support for VDNN modeling inspired by ...
Guorun Li +5 more
wiley +1 more source
Semantic Matching of Natural Language Web Queries
Naouel Karam +3 more
openalex +1 more source
An analysis of literature trends and a historical overview of organic and inorganic piezoelectric materials, focusing on their structural diversity, functional mechanisms, and inherent characteristics. It then explores cutting‐edge developments in material synthesis, fabrication processes, and performance optimization, highlighting their applicability ...
Bangul Khan +7 more
wiley +1 more source
Development and Evaluation of a Retrieval-Augmented Generation-Based Electronic Medical Record Chatbot System. [PDF]
Son N +5 more
europepmc +1 more source
Partially ordered regular languages for graph queries
Sergio Flesca, Sergio Greco
openalex +1 more source
Interpretable PROTAC Degradation Prediction With Structure‐Informed Deep Ternary Attention Framework
PROTAC‐STAN, a structure‐informed deep learning framework is presented for interpretable PROTAC degradation prediction. By modeling molecular hierarchies and protein structures, and simulating ternary interactions via a novel attention network, PROTAC‐STAN achieves significant performance gains over baselines.
Zhenglu Chen +11 more
wiley +1 more source

