Categories: AI/ML Research

A Gentle Introduction to Multi-Head Attention and Grouped-Query Attention

This post is divided into three parts; they are: • Why Attention is Needed • The Attention Operation • Multi-Head Attention (MHA) • Grouped-Query Attention (GQA) and Multi-Query Attention (MQA) Traditional neural networks struggle with long-range dependencies in sequences.

A Gentle Introduction to Multi-Head Latent Attention (MLA)

This post is divided into three parts; they are: • Low-Rank Approximation of Matrices • Multi-head Latent Attention (MLA) • PyTorch Implementation Multi-Head Attention (MHA) and Grouped-Query Attention (GQA) are the attention mechanisms used in almost all transformer models.

June 24, 2025

In "AI/ML Research"

Advanced Techniques to Build Your RAG System

This post is divided into three parts; they are: • Query Expansion and Reformulation • Hybrid Retrieval: Dense and Sparse Methods • Multi-Stage Retrieval with Re-ranking One of the challenges in RAG systems is that the user's query might not match the terminology used in the knowledge base.

April 27, 2025

In "AI/ML Research"

A Gentle Introduction to Attention Masking in Transformer Models

This post is divided into four parts; they are: • Why Attention Masking is Needed • Implementation of Attention Masks • Mask Creation • Using PyTorch's Built-in Attention In the

June 27, 2025

In "AI/ML Research"

AI Generated Robotic Content