large language models

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...

Integrating AI into optical engineering: experiences in workflow transformation

We report experiences integrating a large-language-model agent into a production camera-lens design workflow. Rather than claiming the AI designs better lenses, we describe a division of labor: the AI writes analytical tooling and runs trade-space sweeps that would otherwise consume weeks of expert time, while the engi...

Content Deviation Recognition and Recommendation Model for Sports and Health Information: Based on Improved Text Rank Algorithm and Deep Fusion Transformer Architecture

A multimodal deep learning-driven model for assessing drawing composition quality

In recent years, digital art education, computerized evaluation systems, and aesthetic computing have prioritized drawing composition quality assessment. Traditional assessments have relied on subjective judgment or single-modal analysis, limiting scalability and uniformity. Existing methods use visual characteristics...

Geração de Workloads Sintéticos com LLMs: Um Estudo sobre o Impacto de Logs de Produção na Representatividade de Testes de Desempenho

Este pacote de replicação reúne os artefatos utilizados em um estudo quasi-experimental sobre a geração de workloads sintéticos para testes de desempenho com Large Language Models (LLMs). O estudo analisou duas plataformas web do setor de biogás, biometano, bioenergia e sustentabilidade: Portal Energia e Biogás e Biogá...

Mechanistic Interpretability and Explainable AI (XAI) in Foundation Models: Reverse-Engineering Circuits, Superposition, and Safety Bounds

Abstract—Foundation models, particularly autoregressive Transformer Large Language Models (LLMs) and Vision-Language Models (VLMs), have exhibited unprecedented reasoning and generative capabilities across computer science and engineering. However, their internal representations operate as opaque, high-dimensional 'bla...

Intelligent Circuit Design: Exploring Artificial Intelligence for Logic Gate Synthesis and Optimization

Modern integrated circuits contain billions of logic gates, while thermal and sub-micron parasitic limits make every design decision more expensive. Classical logic synthesis relies on deterministic minimization and hand-engineered heuristics that struggle to balance Power, Performance, and Area (PPA) at the same time....

Generative AI as a Creative Paradigm in Marketing Communication

Generative artificial intelligence is redefining marketing communication by extending the discipline beyond human-driven creativity into a data-supported, emotionally responsive, and context-aware domain. Unlike traditional AI focused on automation and analytics, generative AI enables personalized content creation, imm...

"O'ZBEK VA TURK TILLARIDA AVTOMATIK MORFOLOGIK TAHLIL VA LEMMATIZATSIYA: MASHINA TARJIMASI UCHUN ZAMONAVIY YONDASHUVLAR"

This article analyzes contemporary approaches to automatic morphological analysis and lemmatization in the Uzbek and Turkish languages, which have an agglutinative structure. It also highlights major linguistic challenges characteristic of these languages, including the large number of word forms (vocabulary explosion)...

Dataset for "A flexible language model-assisted electronic design automation framework"

This dataset relates to the manuscript "A flexible language model-assisted electronic design automation framework" authored by Cristian Sestito, Panagiota Kontou, Pratibha Verma, Atish Dixit, Alexandros D. Keros, Michael O'Boyle, Christos-Savvas Bouganis, and Themis Prodromakis, accepted for publication in Scientific R...

Coarse-to-Fine Label Distribution Learning for High-Cardinality Survey Simulation

Modeling fine-grained survey distributions for high-cardinality large language model prediction is challenging under mixed-cardinality supervision. Because low-cardinality surveys dominate training, standard label distribution learning (LDL) develops positional bias toward early response regions and fails to generalize...

Research on solid-state battery information mining based on large language models and chain-of-thought reasoning

Solid-state batteries (SSBs) represent a next-generation energy storage technology. However, the wide diversity of solid-state electrolyte (SSE) chemistries, coupled with the complexity of their synthesis and processing routes, makes systematic investigation, knowledge reuse, and database construction particularly chal...