QUELL — reproducibility package (v4.0). This repository accompanies the paper “QUELL: An On-Device Benchmark of Quantized Edge LLMs versus Classical Machine Learning for IoT Intrusion Detection.” QUELL fine-tunes decoder-only LLMs (GPT-2-medium, Qwen2.5-0.5B/1.5B, Llama-3.2-1B) on network-flow records serialized as text, quantizes the Qwen2.5-1.5B detector, deploys it on an NVIDIA Jetson Orin Nano Super (GGUF/llama.cpp), and compares it with random-forest and XGBoost detectors on Edge-IIoTset, CICIoT2023 and N-BaIoT under a leakage-controlled, multi-seed protocol. Axes: detection quality, on-device latency/energy/memory, quantization retentio
Şüyun, Süleyman Burçin, Aktürk, Fatih
Reproducibility package accompanying the manuscript “FMEA-Based Decision Intelligence for Supply Chain Risk Assessment: A Parameterized Simulation and Leakage-Audited Empirical Framework.” This Version 2 package contains the source code, deterministic 120-scenario simulation, leakage-audited DataCo evaluation scripts, machine-learning baselines, live GPT-4o pilot logs, repeated-call stability evidence, and supporting result files used in the revised manuscript. The package includes the complete 10 × 5 repeated-call stability outcomes supporting the reported 84% mean majority agreement. Documentation and terminology were updated during peer re
Donapati, Nikhil
Vigilancia bibliográfica: descubre en qué revistas se publica un tema, sigue las elegidas y muestra sus artículos nuevos, todos reales, de OpenAlex y PubMed. Varios radares, marca de novedades, exportación a Zotero y resumen opcional con IA. Funciona sin clave. Novedades de la versión 2.0 Ya no inventa artículos. La versión 1 pedía a GPT registros bibliográficos «realistas» (con DOI falsos) cuando había pocos resultados y los mezclaba con los reales. Al migrar un radar antiguo, esos artículos se eliminan y se avisa. Las revistas elegidas filtran de verdad : en OpenAlex por su identificador y en PubMed por su ISSN. Antes se ignoraban. Si un ar
Borrás Rocher, Fernando
Updated for https://ph-ai.me Public Health & AI Workshop at University of Arizona, June 8-11, 2026
Tyson L. Swetnam, Claude, Jeffrey K Gillan, Carlos Lizarraga-Celaya, Greg T. Chism, Enrique Noriega, Eric R. Scott
Comparing LLM based approaches for predicting Mg dissolution modulators. There is a Readme with brief instructions. Copyright (c) 2025 Busch et al. If you have any questions please contact us at , or . For further details refer to our publication ( https://doi.org/10.1016/j.corsci.2025.113080 ). Please cite this work if you use any of the code or ideas provided.
Busch, Matthias, Tacke, Marius, Lamaka, Sviatlana, Zheludkevich, Mikhail, Linka, Kevin, Cyron, Christian Johannes, Feiler, Christian, Aydin, Roland C.
Ferdi Iskandar Mind & Memory — Initial Archive <table width="100%"> <tr> <td width="36%" align="center" valign="middle"> <img src="https://i.postimg.cc/Y2Z6CBzh/Chat-GPT-Image-Jun-6-2026-11-43-05-PM.png" alt="dr. Ferdi Iskandar" width="250"> <br /> <sub><b>dr codieverse</b> · Proud Public Servant</sub> </td> <td width="64%" valign="middle"> This repository is designed as a living knowledge foundation that captures Dr. Ferdi Iskandar's way of thinking, decision-making process, lessons learned, vision, and values across leadership, healthcare, artificial intelligence, governance, innovation, and human-centered system building. Purpose To preser
codieverse
First public release of aialib — a reproducible pipeline and annotated threat library for AI-generated code vulnerabilities. Ships a deterministic generator–detector–annotator pipeline (Bandit, Semgrep, AI-aware risk detector) that turns one YAML prompt manifest into a CSV / SQLite / SARIF dataset. Dataset: 504 annotated findings drawn from 2,144 generated Python samples across four LLM providers (OpenAI gpt-4o-mini, gpt-4.1; Anthropic claude-sonnet-4-20250514; MBZUAI-IFM K2-Think-v2). Each entry carries CWE, OWASP, AI-cause, propagation vector, human–AI factor, and MITRE ATLAS technique labels, plus token and AST fingerprints for deduplicati
Aljaberi, Ali
This repository provides the manuscript code for the research work: “Sentiment-aware Image Captioning with Visually Consistent Sentiment Calibration (VCSC)”. The implementation presents a unified multimodal pipeline for generating sentiment-aware image captions. It integrates Vision Transformer (ViT) for visual feature extraction and a GPT-2-based decoder for caption generation (Vision–GPT framework). The framework further includes a comprehensive five-class sentiment classification module using: - TextBlob-based weak supervision - Classical machine learning baselines (TF-IDF with SVM, Random Forest, Decision Tree, Naive Bayes) - Deep learnin
Khan, Dr. Sajid Ullah
Replication package - Prioritizing Feature Requests Based on Mobile App User Reviews Using Deep Learning FOLDER DESCRIPTION 1- App reviews preprocessing and classification 1- CLAP dataset 2- Feature request classification CLAP-BERT (code and model) 3- Feature request classification CLAP-GPT (code) 4- Kaggle dataset 5- Text preprocessing code 6- Feature request type classification (code and model). 2- The app reviews clustering and topic modeling 1- Feature names extraction + Clustering + Topic modeling , (code and outputs). 3- Prioritization factors (estimation/measurement) 1- Sentiment analysis (code and model) + sensitivity analysis 2- Prio
Mansour, Albidah
This Zenodo archive contains the code accompanying the manuscript “Sentiment-aware image captioning with visually consistent sentiment calibration.” The repository provides a consolidated and reproducible implementation of the proposed multimodal approach for generating sentiment-aware image captions. The framework integrates Vision Transformer (ViT) for visual feature extraction, a GPT-2–based decoder for caption generation, and multiple sentiment classification models including LSTM, GRU, CNN, Transformer, and fine-tuned BERT. In addition, the archive implements the proposed Visually Consistent Sentiment Calibration (VCSC) mechanism, which
Khan, Sajid Ullah
autoresearch-mlx v1.0.0 Apple Silicon MLX port of karpathy/autoresearch for running autonomous AI pretraining research natively on M-series Macs. Highlights Full GPT model with RoPE, value embeddings (ResFormer), sliding window attention, softcap, and squared ReLU AdamW optimizer with 6 parameter groups and dimension-scaled learning rates Linear weight decay schedule for 2-5% BPB improvement over the reference fork NaN loss detection, proper eval batch sizing for 16GB machines, and __main__ guard for agent workflows Tunable --time-budget flag (default 5 min) MFU calculation, FLOP estimation, and detailed config logging Benchmark (M1 Pro 16GB,
Goyal, Naman
This work introduces the first absolute theoretical reference frame for Complexity Science. Instead of prediction, optimization, or model fitting, it establishes regime invariance as the fundamental organizing principle of all complex systems. The framework applies uniformly across physics, biology, economics, artificial intelligence, social systems, and civilizations, providing a permanent structural lens comparable in role to relativity in physics. Included are: a formal theoretical framework, a one-page universal regime manifesto, and an executable demonstrator validating regime stability across nonlinear systems. This is not a domain-spec
Nguyễn, Quốc Trường
