MirahLabs Engineering Blog

Technical insights, tutorials, and architectures written by our design and backend engineers.

Active Filters: Tag: deep-learning Clear All
Artificial Intelligence June 13, 2026

Diffusion Models Explained: DALL-E 3 and Stable Diffusion Mechanics

Understand the math and mechanics behind modern generative image models: forward diffusion, reverse denoising U-Nets, and classifier-free guidance.

⏱️ 20 min read Read Article
Artificial Intelligence May 22, 2026

Computer Vision with YOLO and PyTorch: From Training to Edge Deployment

Object detection with YOLO achieves real-time performance even on edge devices. Learn how to train custom YOLO models with PyTorch and deploy them to edge hardware using TensorRT and ONNX.

⏱️ 22 min read Read Article
Artificial Intelligence May 22, 2026

Graph Neural Networks (GNNs): Concepts and Practical Applications

Graph Neural Networks (GNNs) extend deep learning to non-Euclidean domains. Explore graph convolutions, message passing, and real-world applications in recommendation systems.

⏱️ 20 min read Read Article
Artificial Intelligence May 20, 2026

Understanding Transformer Architecture: Attention Is All You Need

A deep-dive into the Transformer model that revolutionized natural language processing—from self-attention heads to positional encoding and multi-head parallelism.

⏱️ 19 min read Read Article
Artificial Intelligence May 03, 2026

Self-Attention vs. State Space Models (Mamba): The Battle for Sequence Modeling

Transformers struggle with O(N^2) context scaling. Discover how State Space Models (SSMs) like Mamba offer linear O(N) scaling for long context windows.

⏱️ 21 min read Read Article
Artificial Intelligence March 23, 2026

Fine-Tuning LLMs with LoRA: A Practical Guide

Low-Rank Adaptation (LoRA) lets you fine-tune large language models efficiently with minimal GPU memory. Learn how to apply LoRA to domain-specific AI tasks step by step.

⏱️ 22 min read Read Article