DateTopicsVideo from playlist
April 3rd, 2026[slides] Lecture 1: Diffusion
• Background on vision
• Motivation behind diffusion
• Diffusion in DDPM
• Training derivation, ELBO
• Inference
• Faster sampling with DDIM 		Lecture 1
1:46:26
April 10th, 2026[slides] Lecture 2: Score matching
• Motivation behind score matching
• Score estimation
• Denoising score matching
• SDE formulation
• Training, inference
• Probability flows
• Parallel with diffusion 		Lecture 2
1:48:48
April 17th, 2026[slides] Lecture 3: Flow matching
• Motivation behind flows
• History on flows
• Conditional flow matching
• Training, inference
• Rectified flow
• Parallel with diffusion and score matching 		Lecture 3
1:47:34
April 24th, 2026[slides] Lecture 4: Latent space and guidance
• Variational autoencoders
• Latent diffusion models
• Text representation
• Image representation
• Contrastive learning, CLIP, SigLIP
• Guidance (classifier-based, classifier-free) 		Lecture 4
1:40:58
May 1st, 2026Midterm
[exam] [solutions]
May 8th, 2026[slides] Lecture 5: Image generation architectures
• Convolutions
• U-Net
• Attention mechanism
• Diffusion Transformers
• Multimodal DiT
• Optimizations 		Lecture 5
1:46:26
May 15th, 2026Lecture 6: Model training
• Training lifecycle
• Pretraining, curriculum learning
• Supervised finetuning
• Preference tuning with Diffusion-DPO, Flow-GRPO
• Tuning with textual inversion, DreamBooth
• Distillation 		Lecture 6 - YouTube
Coming soon, stay tuned!
May 22nd, 2026Lecture 7: Evaluation
• Human ratings
• Confidence metrics (IS)
• Similarity metrics (FID, SSIM, LPIPS)
• Reconstruction metrics (MSE, PSNR)
• Multimodal LLMs
• MLLM-as-a-Judge 		Lecture 7 - YouTube
Coming soon, stay tuned!
May 29th, 2026Lecture 8: Trending topics
• Class recap
• State-of-the-art models
• Extension from image to video
• Alternatives to generation
• Parallel with the text world
• Conclusion 		Lecture 8 - YouTube
Coming soon, stay tuned!
June 8th, 2026Final