Instructors

Georgia Gkioxari

Pietro Perona

Advisors

Yang Song

Giovanni Paolini

TAs

Neehar Kondapaneni

Laure Delisle

Suzanne Stathatos

Zihui Wu

Rogério Guimarães


Guest Speakers

Yejin Choi

Björn Ommer

Jack Hessel

Ross Girshick

Saining Xie


Syllabus

Date

Topic

Lecturers

Materials

04/04/23

  Intro to Large Language & Vision Models

  • What is AI and why pursue it
  • Weak vs Strong AI
  • Intro to Large Models for vision and language
  • AI4Science applications
  • Current LLVMs and failures
  • Class overview, homeworks, grading policy
Pietro
Georgia
  • Slides - Part A by Pietro: pdf
  • Slides - Part B by Georgia: pdf
04/06/23

  Brief Recap on MLPs

  • Definition of MLPs
  • Backpropagation
  • Stochastic Gradient Descent
  • Momentum (paper)
  • Adam (paper)
Pietro
04/11/23

  Brief Recap on CNNs

Pietro
  • Pietro's slides: pdf
04/13/23

  Transformers - Part A

Georgia
  • Georgia's slides: pdf
04/18/23

  Transformers - Part B

Georgia
  • Georgia's slides: pdf
04/20/23

  Self-Supervised Learning

Elijah Cole
04/25/23

  Object Recognition at Scale

Georgia
  • Georgia's slides: pdf
04/27/23

  Large Vision Models for Segmentation

Ross Girshick
05/02/23

  Generative Models I

  • Intro to Generative Models & Autoregressive Models
  • GPT (GPT, GPT2, GPT3)
  • PixelCNN (paper)
  • WaveNet (paper)
Georgia
  • Georgia's slides: pdf
05/04/23

  Generative Models II

  • Variational Autoencoders
  • Tutorial on VAEs (paper)
  • VQ-VAE (paper)
Georgia
  • Georgia's slides: pdf
  • Assignment 3: 🤖 nanoGPT -- main & code.
05/09/23

  Generative Models III

  • Diffusion Models
  • DDPMs (paper)
  • Denoising Score Matching (paper)
Georgia
  • Georgia's slides: pdf
05/11/23

  Generative Models III-1/2

  • More on Diffusion Models
  • Latent Diffusion (paper)
  • Classifier-free Guidance (paper)
Georgia
  • Georgia's slides: pdf
05/16/23

  Scalable Vision Foundation Models

Saining Xie
  • Saining's slides: pdf
05/18/23

  Common Sense: The Dark Matter of Language Intelligence

Yejin
Jack
  • Yejin's slides: pdf
  • Jack's slides: pdf
05/23/23

  GANs & Unified Vision and Language Models

Pietro
Georgia
  • Pietro's slides: pdf
  • Georgia's slides: pdf
  • Assignment 4: Diffusion 🎨 -- main & code
05/25/23

  Stable Diffusion & Image Generation

Björn Ommer
05/30/23

  Ethics in AI

Pietro
06/01/23

  Alignment

  • Intro to RL
  • REINFORCE, PPO
  • InstructGPT (paper)
Giovanni Paolini
  • Giovanni's slides: pdf