Outlier Courses

Diffusion Models - PyTorch Implementation

1 review

Learn to implement and train diffusion models in PyTorch, covering unconditional and conditional versions, classifier-free guidance, and exponential moving average. Gain hands-on experience with state-of-the-art generative AI techniques.

• YouTube
• 22 minutes
• On-Demand
• Free Video

Diffusion Models - Paper Explanation - Math Explained

Comprehensive explanation of diffusion models, covering theory, architecture, math derivation, algorithms, improvements, and results. Includes comparisons to other methods and references to state-of-the-art applications.

• YouTube
• 33 minutes
• On-Demand
• Free Video

VQ-GAN - PyTorch Implementation

Implement Vector Quantized Generative Adversarial Networks (VQGAN) using PyTorch, covering encoder, decoder, codebook, discriminator, and transformer stages for high-resolution image synthesis.

• YouTube
• 38 minutes
• On-Demand
• Free Video

Diffusion Models and Score-Based Generative Models Explained - From Scratch

Explore score-based generative models and their connection to diffusion models. Gain intuition on DDPM, DDIM, and EDM through mathematical explanations and visualizations.

• YouTube
• 38 minutes
• On-Demand
• Free Video

Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO) - Math Explained

Dive into the mathematical foundations of PPO and GRPO reinforcement learning methods used in LLM alignment, covering derivations from intuitive concepts to final objectives.

• YouTube
• 25 minutes
• On-Demand
• Free Video

RoPE - Rotary Positional Embeddings Explanation and PyTorch Implementation

Discover how RoPE (Rotary Positional Embeddings) teaches Transformers about data positions in text, images, and videos with clear explanations and PyTorch code implementation.

• YouTube
• 20 minutes
• On-Demand
• Free Video

Flow Matching - Intuitive Explanation and PyTorch Implementation

Dive into Flow Matching's simplified approach to diffusion models through intuitive explanations, mathematical derivations, and hands-on PyTorch implementation for advanced AI image generation.

• YouTube
• 22 minutes
• On-Demand
• Free Video

Direct Preference Optimization - Paper Explained

Discover how Direct Preference Optimization streamlines LLM training without reward functions, using only preference data for more efficient tuning than PPO methods.

• YouTube
• 17 minutes
• On-Demand
• Free Video