Št. zadetkov: 213
Objavljeni znanstveni prispevek na konferenci
Oznake:
multimodal retrieval-augmentation generation;evaluation;large language models;
Multi-modal retrieval-augmented generation (MMRAG) promises grounded biomedical QA, but it is unclear when to (i) convert figures/tables into text versus (ii) use optical character recognition (OCR)-free visual retrieval that returns page images and leaves interpretation to the generator. We study t ...
Leto:
2026
Vir:
Fakulteta za zdravstvene vede (UM FZV)
Izvirni znanstveni članek
Oznake:
modeliranje;taksonomska zasnova;veliki jezikovni modeli;taxonomy design;conceptual modeling;large language models;patents;
Leto:
2026
Vir:
Institut Jožef Stefan (IJS)
Magistrsko delo
Oznake:
umetna inteligenca;visoko šolstvo;izobraževanje;veliki jezikovni modeli;ChatGTP;
Umetna inteligenca v visokem šolstvu
Leto:
2024
Vir:
Mednarodna fakulteta za družbene in poslovne študije (MFDPŠ)
Objavljeni znanstveni prispevek na konferenci
Oznake:
mobilno zaznavanje;veliki jezikovni modeli;opisna lokacija;mobile sensing;large language models;semantic location;
Understanding a user's semantic location is of critical importance in numerous areas of mobile computing, such as mobile healthcare, mobile advertising, and mobile personal assistance. Nevertheless, inferring semantic location remains challenging and often relies on translating raw geographical coor ...
Leto:
2025
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Izvirni znanstveni članek
Oznake:
Over the past few years, large language models have become technologically ubiquitous and now offer a powerful route to accelerate discoveries in chemistry. In this article, we highlight current impactful applications of large language models in inorganic chemistry, from smart text mining of the ino ...
Leto:
2026
Vir:
Institut Jožef Stefan (IJS)
Objavljeni znanstveni prispevek na konferenci
Oznake:
večjezično zagotavljanje kakovosti;optično prepoznavanje besedila;veliki jezikovni modeli;multilingual QA;OCR text;large language models;
Optical Character Recognition (OCR) plays a crucial role in digitizing historical and multilingual documents, yet OCR errors - imperfect extraction of text, including character insertion, deletion, and substitution can significantly impact downstream tasks like question-answering (QA). In this work, ...
Leto:
2025
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Objavljeni znanstveni prispevek na konferenci
Oznake:
veliki jezikovni modeli;mobilno zaznavanje;ugotavljanje depresije;vseprisotno računalništvo;large language models;mobile sensing;depression inference;ubiquitous computing;
Modern large language models (LLMs) trained on huge amounts of textual data excel in a number of tasks related to generation and analysis of textual and even multimodal input. Automated infer-
ences related to mental health status are crucial as humanity faces an epidemic of mental illness. The pot ...
Leto:
2025
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Magistrsko delo
Oznake:
veliki jezikovni model;vektorske vložitve besed;senzorji;
Leto:
2024
Vir:
Fakulteta za matematiko, naravoslovje in informacijske tehnologije Koper (UP FAMNIT)
Izvirni znanstveni članek
Oznake:
kibernetska varnost;veliki jezikovni modeli;modeliranje groženjcyber;trajnost;prožna infrastruktura;cybersecurity;large language models;threat modelling;sustainability;resilient infrastructure;SDG 9;
With the increased complexity of applications and systems, threat modelling struggles to keep pace with the evolution of risks. This article addresses this challenge by exploring how large language models (LLMs) can be leveraged to create comprehensive threat models across different risk assessment ...
Leto:
2025
Vir:
Fakulteta za elektrotehniko, računalništvo in informatiko (UM FERI)
Magistrsko delo
Oznake:
malware;large language models;detection;
This thesis examines the success rate of large language models (LLM) in detecting macOS malware through Endpoint Security logs. A literature review and 144 experiments with three ChatGPT variants and six prompt types evaluated accuracy, precision, recall, specificity, and F1-score. Results show that ...
Leto:
2025
Vir:
Fakulteta za elektrotehniko, računalništvo in informatiko (UM FERI)