Top Finds

A Python toolkit designed to construct deep learning-ready datasets from Google Earth Engine

📚 Learn from diverse sources with OmniLearnAI, an intelligent platform that combines documents, videos, and more, all with reliable citations.

📊 Detect market regimes by clustering probability distributions using Wasserstein K-means for more accurate financial analysis and insights.

🤖 Automate job applications with a multi-agent system that uses Kafka for seamless data ingestion and efficient document preparation.

Data Science project - python-deep-learning-cv

Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias" (ICLR 2025 Oral)

👤 Utilize AI for secure face recognition with "bio_face_auth," a fast and efficient system driven by deep learning embeddings.

🔍 Solve N-dimensional coupled spring-mass systems using a Physics-Informed Neural Network in PyTorch, without needing ground-truth data.

Nlp Sentiment Analysis Pipeline - Professional Python project

🧠 Build an AI-powered blog recommendation system with Django and Elasticsearch, featuring smart search and fast content suggestions through advanced technology.

Minor Project on the topic of "AI Weather Prediction Model for Extreme Weather Events." Version 3.1.0

🫀 基于深度学习的ECG心电身份识别系统 | Deep Learning ECG Biometric Identification System (98.44% Accuracy)

🎤 Generate realistic Vietnamese speech with VieNeu-TTS, an advanced on-device Text-to-Speech model featuring instant voice cloning and real-time synthesis.

Corrected weather model with higher accuracy using 11 model-ensemble and XGBoost.

🏥 Streamline healthcare management with our AI-powered platform for appointment scheduling, patient records, and Google Calendar integration.

Evaluate multimodal agents on complex, realistic visual tasks involving multi-step workflows in dynamic environments.

🧑⚖️ Evaluate AI skill and agent performance with configurable scores and dual-mode operation on Claude Code and Cowork platforms.

SignatureNetDB is a deep-learning signature verification system using Siamese and Triplet networks. It includes a custom database that stores users, their multiple signature images, and averaged embedding vectors. The system supports user enrollment, signature lookup, identity verification, and model-switching between Siamese and Triplet backbones.

get images from LaTeX

Análise de Segmentação de Clientes usando Machine Learning.

🖼️ Recover plaintext from pixelized screenshots using this proof of concept, designed for images processed with a linear box filter.

Detect stress and burnout in real time using facial emotion recognition and hybrid deep learning models for better mental health insights.

🤖 Transform ideas into videos with openOii, an AI-powered platform that uses collaboration among agents to create engaging comics and animated stories.

🧠 Detect Alzheimer's disease using MRI scans with transfer learning, deep learning, and ensemble methods for accurate stage classification and progression prediction.

This is a high-performance, FastAPI-based microservice and WebSocket worker dedicated to generating text embeddings using the state-of-the-art BAAI/bge-m3 model.