Top Finds

🧪 Test ONNX Runtime Execution Provider coverage with real-world operator support mappings for effective AI deployment insights.

Professional project by Gabriel Demetrios Lafis

💻🔒 A local-first full-stack app to analyze medical PDFs with an AI model (Apollo2-2B), ensuring privacy & patient-friendly insights — no external APIs or cloud involved.

🎨 Transform images into engaging, multilingual stories with expressive narration using AI-powered storytelling technology.

🤖 Analyze stock data with AI insights through an interactive dashboard, featuring technical indicators and sentiment scoring for informed decisions.

A structured multi-agent framework for coordinated AI collaboration

🤖 Access Google's Gemini AI effortlessly with Termai, a lightweight CLI tool for Termux and Linux, designed for smooth command line integration.

🔍 Enhance code quality with Argus MCP, an AI-driven code review server using a Zero-Trust model for safe and efficient development.

A Python AI agent with extensible function-calling, built as a Boot.dev guided project. 🤖

🤖 Simplify customer support with SmartSupport AI, a multi-agent platform that uses NLP and Voice AI for 24/7 automated assistance and faster response times.

GFlowNet-based therapeutic peptide design. Generates diverse, high-quality candidates (5.4x better diversity vs PPO/GRPO) to reduce correlated wet-lab failures. Published method with pre-trained models. Validated on FLIP & Propedia benchmarks.

The implementation of "NeuralCPA: A Deep Learning Perspective on Chosen-Plaintext Attacks".

Train a JEPA world model on a set of pre-collected trajectories from an environment involving an agent in two rooms.

Proyecto de análisis de datos para predecir las ventas de un supermercado. Utiliza Python (Pandas, Scikit-learn, etc.) para el procesamiento de datos y la construcción del modelo, y Power BI para un dashboard interactivo que muestra el rendimiento del modelo y explora los datos de ventas.

Kaggle LLM Classification Competition - Predicting human preferences between chatbot responses

little Python tools, mainly useful for tasks related to machine learning, etc.

🧭 Enhance navigation with VLN-YuanNav, a visual-language model using advanced memory and decision-making for effective exploration.

🎯 Predict your next Dota 2 win streak with 85% accuracy by analyzing match history and identifying optimal play times for maximum MMR gains.

A deep learning system that automatically designs optimal CNN architectures using Neural Architecture Search to classify lung - colon cancer from histopathology images. Achieves 99.72% accuracy across five cancer types with robust regularization. PyTorch-based solution ready for medical imaging deployment with exceptional generalization performane

🎤 Build a low-latency voice agent with real-time TTS and STT, powered by Murf and AssemblyAI for seamless conversational experiences.

👁 Detect suspicious activity in real-time with AI-powered night vision surveillance on Raspberry Pi for reliable low-light security monitoring.

🖐️ Control your mouse effortlessly with real-time hand gestures using AI and computer vision for a touchless, intuitive experience.

🛒 Simplify Pwnagotchi management with PwnStore, a lightweight CLI package manager for seamless plugin browsing, installing, and updating.

Tutorial materials for NUS IT1244: Artificial Intelligence - Technology and Impact (AY25/26 Sem 2)

An AI-driven content generation tool utilizing Natural Language Generation (NLG) to automate social media copy. Optimized for engagement through fine-tuned transformer models and promotional analysis.