large language models

Automated Calculation of the Pediatric Emergency Care Applied Research Network (PECARN) Intra-Abdominal Injury Rule from Unstructured Emergency Department Notes Using a Large Language Model.

Objective The Pediatric Emergency Care Applied Research Network (PECARN) intra-abdominal injury clinical prediction rule identifies children at very low risk for clinically significant intra-abdominal injury after blunt abdominal trauma. However, retrospective evaluation of the rule's use in practice requires resource-...

Mix-Attention for Multimodal Large Language Model-Enhanced Sequential Recommendation

Sequential recommendation aims to predict the next item that may interest users by modeling their historical item sequence. Recently, multimodal sequential recommendation has achieved promising results in capturing user preferences by incorporating rich modality information. However, existing frameworks suffer from lim...

Fast LM Head via Coarse-Fine Decomposition and Tile-Wise Weight Clustering

Large language models (LLMs) reuse each generated token as the next input during autoregressive decoding, making per-token latency a critical factor in practical inference performance. In this process, the LM Head performs a large-scale linear projection from the hidden state to the full vocabulary space at every decod...

Unified Table Understanding via Context-Aware Cell Embedding Learning

UTUEL is introduced, a self-supervised, task-agnostic framework that casts Table Representation Learning as a Joint-Embedding Predictive Architecture (TRL-JEPA) and substantially improves Table Retrieval over generic embedders while remaining competitive on Column Type Annotation and Table Cell Retrieval.

Agentic AI for Computational Fluid Dynamics: A Review

Computational fluid dynamics (CFD) workflows remain strongly dependent on expert decisions in geometry preparation, meshing, model and solver configuration, convergence assessment, post-processing, and design iteration. This review examines agentic artificial intelligence (AI) for CFD automation and engineering design,...

From Web Search to AI Search: A Comparative Analysis of Information-Seeking Behaviour in Traditional Search Engines and Conversational Systems Based on Large Language Models

AI search is changing how users seek information: instead of typing keywords and clicking through links, users increasingly ask complex questions and obtain direct answers on the results page. This shift, together with the rise of “zero-click search” and of chatbots based on Large Language Models (LLMs), is reshaping t...

Analysis code for: Large language models supply actionable management plans when the implicit clinical premise of a request does not hold

Analysis code behind the quantitative results of the manuscript. It covers prompt construction from the paired scenario library, response collection from seven language models, the blinded manual-coding workflow, inter-rater reliability, the rule-based classifier used in the repetition-stability analysis, and the stati...

Pneumatic retinopexy identification in electronic medical records using an on-premises large language model

Material Suplementar - Large Language Models, UML Diagrams, Software Documentation, Software Maintenance, Systematic Mapping Study

Este pacote de replicação contém a planilha utilizada no mapeamento sistemático da literatura sobre o uso de Modelos de Linguagem de Grande Escala (LLMs) na geração, extração e validação de diagramas UML. O material reúne os registros do processo de busca e seleção dos estudos, incluindo os resultados da busca na Scopu...

The Grand Unified Temporary Protocol: Demystifying "Emergence" and Hardware-Level Safety Chips for AI Executive Summary

I. Why Build a "Grand Unified Theory"? (Eradicating Academic Fragmentation and Cyber-Superstition) Contemporary science has fallen into a paradoxical dilemma: physicists lack AI insight, AI engineers lack neuroscientific perspectives, and economists miss the logic of complex systems. When faced with the emergent capabi...

From Neural Signatures to Narrative Intelligence

The chapter introduces a unique neuromarketing/generative AI model that is expected to enhance emotion-adaptive brand communication. This chapter is aimed at illustrating how neural signatures based on EEG, fMRI, eye-tracking, and biometric data can be combined with large language models and narrative intelligence syst...

Consequential Behaviour and Representational Fairness in the Validation of Synthetic Research

Researchers in industry and academia use synthetic survey respondents powered by large language models as substitutes for human samples. These synthetic populations require validation against real-world data, so researchers often address them using ad hoc comparisons with human surveys. Inspired by the intention–behavi...