🩺 Enable real-time segmentation of multimodal biomedical images with the light-weight CFPNet-M network for improved medical analysis and diagnostics.

🔍 Discover your architecture automatically with this AI-powered system designed for educational purposes and portfolio showcasing.

🩺 Segment lungs from COVID-19 X-ray images using advanced deep learning techniques like U-Net and MobileNet-U-Net for improved accuracy and efficiency.

🗓️ Build responsive web applications with ease using React, HTML, CSS, and JavaScript, focusing on user-centered design and performance optimization.

🌍 Discover advancements in 3D scene understanding with LiDAR techniques for semantic and panoptic segmentation, plus occupancy prediction.

📂 Extract, embed, cluster, and securely store Korean text from documents using BERT, enhancing research efficiency and organization.

🌍 Segment drone images in the Baylands using a U-Net model for precise multi-class identification of paths and roads.

🧠 Implement U-Net in PyTorch for effective binary image segmentation, focusing on brain tumor detection with a complete pipeline from data prep to evaluation.

🧠 Enhance your AI projects with Deep Think API, offering OpenAI-compatible interfaces for deep and ultra reasoning modes.

End-to-end UNet3D stack for volumetric medical segmentation: training utilities, FastAPI inference API, Streamlit review UI, Docker deployment, and a model card. Upload NIfTI volumes, get masks back, and visualize slices/IoU plots from experiments. Built for reproducible research and production-grade serving

Via high-fidelity CARLA vehicle simulator & deep semantic segmentation, data from RGBA cameras and LiDAR sensors are combined to achieve comprehensive environmental awareness

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Few-shot semantic segmentation on OpenEarthMap using segmentation models

[IEEE GRSL 2025] PHDMamba: Progressive Hybrid Mamba for Hyperspectral Image Classification

Open source Python library for building bioimage analysis pipelines

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

myGym enables fast prototyping of RL in the area of robotic manipulation and navigation.You can train different robots, in several environments on various tasks. There is automatic evaluation and benchmark tool. From version 2.1 there is support for multi-step tasks, multi-reward training and multi-network architectures.

This repository provides the companion Jupyter Notebooks for the book Context-Engineering for Multi-Agent Systems. It technically details the progressive construction of a Context Engine moving from simple prompts to foundational concepts to a production-ready system semantic blueprint. The code is a guide to building Multi-Agent Systems (MAS)

Neural Network Compression Framework for enhanced OpenVINO™ inference