large language models

DWI: Efficient On-Device LLM Decoding Through Dynamic Width Selection on Nested Models

Deploying large language models (LLMs) on resource-constrained mobile devices remains a significant challenge due to memory limitations and high I/O overhead. While existing dynamic sparsity methods reduce computation costs, they often suffer from inefficient loading patterns that degrade I/O throughput. To address thi...

Enhancing large language model navigation via two-stage fine-tuning and sparse-reward reinforcement learning

Designing Teacher-Centered Interfaces to Elicit Pedagogical Context for LLM-Based Content Generation

Abstract Large Language Models (LLMs) can help teachers generate and adapt educational materials, but most interactions still rely on free-form prompting, making instructional intent difficult to express and reuse. In this paper, we study how teacher-facing interfaces can elicit pedagogically meaningful contextual info...

LEAF-1 pretraining corpus: cfDNA fragments

This record documents the cell-free DNA (cfDNA) portion of the pretraining corpus of LEAF-1, a DNA language model of cell-free DNA and chromatin-accessibility fragments. The fragment files themselves (211 GB bgzip-compressed, 34.0 billion fragments) are too large for Zenodo and are hosted on Hugging Face: huggingface.c...

Research Data for “From Extraction Accuracy to Analytical Admissibility: A Human–AI Division of Labor Protocol for LLM-Based Supply-Chain Risk Intelligence”

This dataset contains the reproducibility materials supporting the study “From Extraction Accuracy to Analytical Admissibility: A Human–AI Division of Labor Protocol for LLM-Based Supply-Chain Risk Intelligence.” The package supports an offline benchmark of four open-weight large language models—DeepSeek-V3.2, Qwen3.8-...

Bibliographic References Repository - Triaxial Evaluation of Large Language Models in Code Generation: A Structural and Semantic Approach.

This repository provides the bibliographic dataset and methodological documentation supporting the research article *"Triaxial Evaluation of Large Language Models in Code Generation: A Structural and Semantic Approach"*. The dataset consists of a comprehensive BibTeX (`.bib`) file containing a hybrid corpus of scientif...

A User-Centered Approach to Customizing, Validating, and Evaluating a Large Language Model for Empowering Healthcare Providers with Up-to-Date Information on Adolescent and Child Health

Healthcare professionals (HCPs) in Kenya face critical challenges in accessing reliable, context-specific information on adolescent and child health, which hampers clinical decision-making and compromises patient outcomes. Large Language Models (LLMs) offer a promising solution by delivering context-aware, localized kn...

From Multi-Agent Systems to AI Ecosystems in Tourism and Hospitality: A Scoping Review Protocol

This scoping review will map how interactions between computational agents are designed, coordinated, evaluated, and governed in tourism and hospitality. It will cover traditional multi-agent systems and architectures based on large language models, identifying applications, agent roles, coordination mechanisms, evalua...

Provenance-Aware Evaluation of Cloud and Local Large Language Models for Cybersecurity Workloads

LeakAgent: a multi-agent system for leak detection using multi-modal large language model coordination in water distribution network

Water distribution networks (WDNs) suffer from severe leakage, yet pinpointing the leaks remains difficult. Data-driven detection is typically split into disconnected stages of hydraulic modelling, partitioning, sensor planning and analysis, and it treats the questions of whether a leak exists and where it lies as sepa...

**The Earth That Heard** is a 30-chapter bilingual essay (Hebrew and English) that traces a continuous textual architecture from the murder of Abel in Genesis to Joshua's altar on Mount Ebal.

# Zenodo Description — v15 ## Title Bound by Design: The Earth That Heard — Sukkot 2026 Edition (v15) ## Description **The Earth That Heard** is a 30-chapter bilingual essay (Hebrew and English) that traces a continuous textual architecture from the murder of Abel in Genesis to Joshua's altar on Mount Ebal. The author...

InventOR: A Human-Reviewed, Prompt-Configured Large Language Model Decision Support System for Material-Level Inventory Control

Confidentiality-screened public release: analysis code, anonymized variable schema, aggregate evaluation results (Run 1, Run 2, Run 3), manuscript sources, and integrity manifest for InventOR, a prompt-configured LLM workflow that generates material-level (r,Q) inventory policies without project-specific model training...