large language models

Packi: demonstrations and LoRA fine-tuning for online 3D bin packing with LLMs

Demonstration data and training code for the paper 'Packi: Robotic 3D Bin Packing With Large Language Models Fine-Tuned by Learning From Demonstration' (Journal of Robotics, under revision): the interactive demonstration recorder, human and privileged-expert demonstrations, the data preparation and LoRA training script...

Emerging Trends in Large Language Models

Agentic Synthesis of Open-Source Biomedical Repositories and Clinical Literature into Interactive Diagnostic & Medical Learning Tools for Low-Resource Healthcare Settings

Frontline community health workers (CHWs) and rural clinics in low-resource settings—particularly across underserved municipalities in South Asia and rural regions of the United States—face a severe clinical knowledge bottleneck. While peer-reviewed biomedical literature, genomic variant databases, and open-source clin...

What makes a good agricultural decision support system? A scoping review on user perspectives.

Abstract Agricultural decision support systems (agri-DSS) are increasingly developed to support complex farm decision-making, yet their adoption and sustained use remain limited. One frequently cited reason is that DSS development is insufficiently user-centred, while existing research on user perspectives is fragmente...

The Vanderbilt Report’s critique of humanistic scholarship is itself bad scholarship and should be corrected or retracted

Vanderbilt University’s “Report on the State of Scholarship in the Humanities and the Humanistic Social Sciences” (Boghossian et al., June 25, 2026) argued that humanistic scholarship has experienced “a deterioration in scholarly standards fueled by the substitution of political criteria for properly scholarly criteria...

TMC-LewisGen: Automated Generation of Lewis-like Structures for Transition–Metal Complexes

Abstract Lewis structures constitute a foundational language in chemical education, mechanistic reasoning, synthesis, and modern cheminformatics. With the accelerating shift toward data-driven and AI-assisted molecular science, the ability to rapidly generate Lewis-like representations, including RDKit-parsable SMILES,...

AI use and risk disclosure by investment advisers

Introduction Investment advisers increasingly report using artificial intelligence (AI), but little is known about what they disclose about it in fiduciary filings. The SEC brought its first AI-washing enforcement actions in 2024, so regulators and researchers need a reproducible measure of AI disclosure. We provide la...

A TYPOLOGY-INFORMED METHODOLOGICAL MODEL FOR BUILDING AN UZBEK–CHINESE PARALLEL CORPUS

Uzbek and Mandarin Chinese lie at opposite ends of the morphological spectrum: Uzbek is an agglutinative Turkic language with SOV order and a rich case system, whereas Chinese is an isolating Sino-Tibetan language with SVO order, function words and numeral classifiers, written without word boundaries. Our search did no...

Neuro-Symbolic Artificial Intelligence: Integrating Large Language Models with SMT Solvers, Knowledge Graphs, and Formal Automated Theorem Provers

Abstract—Modern deep neural networks, particularly autoregressive Large Language Models (LLMs), have achieved state-of-the-art empirical performance across natural language generation, semantic translation, and broad pattern recognition. However, pure statistical connectionist architectures suffer from fundamental epis...

High Average Accuracy Coexists with Substantial Between-Setting Variability: A Systematic Review and Meta-analysis of Large Language Models for Data Extraction in Evidence Synthesis

AI-Assisted Metadata Enhancement for Digital Image Collections: A Pilot Study of Vision-Enabled Language Models in Cultural Heritage Description

This study evaluates the efficacy of Large Vision-Language Models (LVLMs) for remediating and creating metadata within the Pittsburgh City Photographer Collection. By comparing outputs from several OpenAI and Google Gemini models against a human-remediated baseline, the research identifies a significant performance gap...

Artificial Intelligence Across the Surgical Research Workflow: A Stage-Specific Framework for Benefits, Failure Modes, and Oversight

Artificial intelligence (AI) tools, particularly large language models (LLMs), have rapidly integrated into surgical and biomedical research, prompting fundamental questions about their appropriate role. This review presents a stage-specific framework mapping each phase of the surgical research workflow (literature rev...