Results 91 to 100 of about 109,600 (254)

Benchmarking the engineering reliability of LLM-based design for resonant wireless power transfer systems

open access: yes
Designing high-frequency wireless power transfer (HFWPT) systems is a complex process that demands considerable time and domain expertise. To address these challenges, this study employs both general purpose and finetuned large language model (LLM ...
Harrison, Lee   +4 more
core   +1 more source

Who is watching who? Regulation of media and freedom of expression in Uganda : a critical analysis of the Press and Journalists Act of 1995 [PDF]

open access: yes, 2008
Thesis (LLM (Human Rights and Democratisation in Africa)) -- University of Pretoria, 2008.A Dissertation submitted to the Faculty of Law University of Pretoria, in partial fulfilment of the requirements for the degree Masters of Law (LLM in Human Rights ...

core  

A Generative Neuro‐Symbolic AI for Protein Sequence Design

open access: yesAdvanced Science, EarlyView.
We introduce EffieDes, a neuro‐symbolic framework coupling deep learning‐based fitness landscape parameterization with exact automated reasoning. Unlike greedy sampling, EffieDes identifies sequences that globally optimize fitness while satisfying intricate design constraints.
Marianne Defresne   +12 more
wiley   +1 more source

Benchmarking Deepseek-LLM-7B-Chat and Qwen1.5-7B-Chat for Indonesian Product Review Emotion Classification

open access: yesJournal of Applied Informatics and Computing
Upon completing their shopping experience on an e-commerce platform, users have the opportunity to leave a review. By analyzing reviews, businesses can gain insight into customer emotions, while researchers and policymakers can monitor social dynamics ...
Galih Setiawan Nurohim   +2 more
doaj   +1 more source

LLM-Driven Generation of Summaries for Symbolic Execution (Klee Workshop 2026)

open access: yes
Symbolic summaries are a standard mechanism for addressing two central limitations of symbolic execution: interactions with the runtime environment and path explosion. However, writing such summaries by hand is notoriously error-prone. We present a novel
Frederico Ramos (11818910)
core   +1 more source

Cancer‐Associated BCL‐2 Mutants Reveal Mechanisms Towards Venetoclax Resistance

open access: yesAdvanced Science, EarlyView.
Venetoclax (VEN) resistance in chronic lymphocytic leukemia arises from diverse BCL2 mutations. We map mechanisms contributing to VEN resistance across common BCL‐2 variants. G101V and D103Y reduce drug binding and increase sequestration of pro‐apoptotic proteins. V156D blocks VEN allosterically.
Jonas Aufdermauer   +9 more
wiley   +1 more source

The African Commission on Human and Peoples' Rights and the Regional Economic Communities: the need for co-operation [PDF]

open access: yes, 2009
Dissertation submitted to the Faculty of Law University of Pretoria, in partial fulfilment of the requirements for the degree Masters of Law (LLM in Human Rights and Democratisation in Africa).

core   +1 more source

Improving Retrieval-Augmented Generation Performance Using the MAF-RAG Architecture, EVR–VOR Vector Retrieval, and Multi-Agent Fallback Reasoning

open access: yesJournal of Applied Informatics and Computing
Retrieval-Augmented Generation (RAG) AI chatbots have gained popularity for their effectiveness in producing accurate, fast, and reliable responses; however, they have faced critical challenges stemming from limited datasets, outdated documents, and ...
Erlanda Prasetio   +2 more
doaj   +1 more source

Evaluation of LLM-based Tools for the Automated Repair of Security Vulnerabilities in Android Apps [PDF]

open access: yes
openThe ever-growing landscape of Android applications necessitates robust security mechanisms to mitigate potential vulnerabilities. This thesis presents a comprehensive evaluation of three Language Model (LLM)-based tools—ChatGPT, Google Bard, and ...
AHMED, SAAD
core  

CLRe: A Synergistic Dual‐Engine Framework for One‐Step Retrosynthesis Prediction

open access: yesAdvanced Science, EarlyView.
CLRe uses a contrastive difficulty score to order pretrained seq2seq fine‐tuning for retrosynthesis. Reaction embeddings define the ranking score, and a cumulative easy‐to‐hard schedule expands from the easiest subset to the full training set while earlier examples remain active.
Tianhao Su   +5 more
wiley   +1 more source

Home - About - Disclaimer - Privacy