large language models

Mathematical Resolution of Thermal and Electromagnetic Deadlock in Space-Based AI Computing (Ⅰ, Ⅱ, Ⅲ)

Confirmed date obtained2026.09.19 Saturday Around pm11:00 First acquisition2026.09.20 Sunday Around am05:30 Second acquisition The Orchestrated Breakout: Infrastructure Lockdown AbstractThis paper presents a definitive mathematical and structural demolition of the contemporary narrative surrounding autonomous artificia...

R8: An Exploratory Lexical Framework for Approximating Cognitive Manipulation Risk in Text

R8 (Cognitive Risk Analyzer): An Exploratory Lexical Framework for Approximating Cognitive Manipulation Risk in Japanese Text R8 is an exploratory, dictionary-based framework that approximates cognitive manipulation risk in Japanese-language text across 12 theoretically grounded categories, producing a single composite...

The role of AI in academic library reference services: A bibliometric analysis

The integration of artificial intelligence (AI) into academic library reference services has emerged as a significant area of scholarly interest. Using bibliometrix in R and VOSviewer, this study examines publication trends, identifies leading journals, countries, and authors, maps thematic clusters through keyword co-...

Specification Before Generation: A Pre-Registered, Five-Model Paired Evaluation of a Specification Frame for LLM-Generated Code in Money, Time, Idempotency, and Access Tasks

Code generated by large language models passes security checks at a rate that has barely moved in four years. In regulated backends, the defect classes that matter most are money arithmetic, time handling, retry safety, and access control. Teams answer with instruction files, yet the largest controlled study of instruc...

Clinical quality, safety and stability of ChatGPT and DeepSeek patient information on pancreatic intraductal papillary mucinous neoplasms

This deposit contains the data and analysis code for a study evaluating the clinical quality, safety and stability of patient-facing advice generated by two large language models about pancreatic intraductal papillary mucinous neoplasms (IPMN).

Zero-Copy In-Place Compaction and Idempotent Associative Routing of Dynamic Key-Value Cache Tensors in Deep Learning Accelerators

The serving of autoregressive Large Language Models (LLMs) is severely constrained by the computational and memory capacity limits of the Key-Value (KV) cache, commonly referred to as the Memory Wall. While dynamic context pruning algorithms mitigate memory expansion by discarding tokens of low attention mass, conventi...

CTT Algorithm

CTT Project - Hwang Joon This paper was written using GPT-5.6sol,GPT-6 Astra model of OpenAI. Abstract CTT is a computational research framework developed for large-scale hierarchical computation and structure-aware analysis across multiple scientific and engineering domains. The numerical CTT implementation has been e...

DS@GT ARC at Touché: Large Language Models for Retrieval-Augmented Debate

David vs. Goliath in Next Activity Prediction: Argmax vs. LSTM, Transformer, and LLM

LLM Compression with Jointly Optimizing Architectural and Quantization Choices

The Promise and Perils of Smart (City) Bots as Educational Tools

Written from an educator’s perspective, the paper aims to examine the increasing use of chatbot technology capable of answering user queries in various fields such as commerce, public service delivery, urban areas, higher education etc. by simulating human conversation through text messages or voice commands. We analys...

The Cell, Not the Call: A Preregisterable Audit Protocol for Repeated-Call Behavioral Experiments With Large Language Models

Abstract. When a hosted large language model answers the same prompt many times, the resulting completions can estimate that model's response distribution for that one prompt. They cannot, on their own, stand in for a sample of scenarios, participants, or models, and treating them as if they could undermines the claims...