Back to Homepage

Videos

The most useful entry points into my technical teaching: implementation-heavy ML explainers, paper walkthroughs, and hands-on AI engineering tutorials. Neural Breakdown with AVB.

Neural Breakdown with AVB channel thumbnail
YouTube Channel Neural Breakdown with AVB

Deep learning explanations, paper reviews, and implementation-heavy AI engineering tutorials.

Recent Videos

Popular Tutorials

01
LLM fine-tuning Finetune LLMs to teach them ANYTHING with Huggingface and Pytorch 165K+ views
02
deep learning papers Kolmogorov Arnold Networks (KAN) Paper Explained 74K+ views
03
DSPy Complete DSPy Tutorial - Master LLM Prompt Programming 70K+ views
04
SAM Explaining the Segment Anything Model - Network architecture, Dataset, Training 44K+ views
05
diffusion Text to Image Diffusion AI Model from scratch 38K+ views
06
local LLMs Tiny Language Models - How to build INSANELY FAST local models | Chapter 2, SLM Training 35K+ views
07
RLHF / GRPO How to finetune LLMs to THINK with Reinforcement Learning (GRPO from scratch!) 31K+ views
08
agents Recursive Language Models (RLMs) - Let's build the coolest agents ever! (Theory & Code) 29K+ views
09
NLP history 10 years of NLP history explained in 50 concepts | From Word2Vec, RNNs to GPT 27K+ views
10
VAE Visualizing the Latent Space: This video will change how you imagine neural nets! 25K+ views
11
PyTorch Let me explain PyTorch in 7 Concepts 25K+ views
12
context engineering DSPy + Context Engineering - the fully hands-on Basics to Pro course! 23K+ views
13
computer vision How Neural Nets estimate depth from 2D images? 21K+ views
14
agent memory How to build your own long-term Agentic Memory System for LLMs | Mem0 from scratch in DSPy 19K+ views
15
VLM training Let's train Vision Language Models (VLM) from scratch using just Text-Only LLMs! 18K+ views
16
continued pretraining How to finetune LLMs on custom data domains using CPT | Chapter 1, SLM Training 17K+ views
17
SAM How does Segment Anything 2 (SAM 2) work? Paper and Network Architecture Explained! 17K+ views
18
multimodal Multimodal AI from First Principles - Neural Nets that can see, hear, AND write. 15K+ views
19
DPO / alignment Direct Preference Optimization, Model Alignment, and Post training | Chapter 3, SLM Training 7.3K+ views
20
DeepSeek / mHC DeepSeekV4 - Manifold Constrained Hyper Connections (mHC) and the evolution of ResNets 6.1K+ views
21
sparse attention How is Deepseek V4 so cheap (A deep dive into Sparse Attention) 4.7K+ views