From DDPM to Latent Diffusion and DiT
Notes connecting forward noise, reverse denoising, latent space, and a transformer backbone.
Read noteBlog Category
Separate learning paths for discriminative AI, vision, and generative models.
2026-08-01 · AI · Deep Learning · Computer Vision · 2025 Generative Models Intensive 5
Notes connecting forward noise, reverse denoising, latent space, and a transformer backbone.
Read note →2026-08-01 · AI · Deep Learning · Computer Vision · 2025 Generative Models Intensive 4
Notes connecting alternating generator and discriminator updates with Pix2Pix conditioning and L1 loss.
Read note →2026-08-01 · AI · Deep Learning · Computer Vision · 2025 Generative Models Intensive 3
Notes on why the encoder predicts a mean and variance and how reconstruction and KL losses interact.
Read note →2026-08-01 · AI · Deep Learning · Computer Vision · 2025 Generative Models Intensive 2
Notes connecting joint-probability factorization, teacher forcing, log-likelihood, and cross entropy.
Read note →2026-08-01 · AI · Deep Learning · Computer Vision · 2025 Generative Models Intensive 1
My notes comparing discriminative and generative models before checking tensor shapes and visualizing data.
Read note →