Probabilistic Graphical Models (Pengtao Xie)

Basics

• Lecture 1: Introduction to Probabilistic Graphical Models
• Lecture 2: Review of Probabilities and Statistics

Beyesian Network

• Lecture 3: Introduction to Bayesian Network
• Lecture 4: Basics of Large Language Models

Markov Random Field

• Lecture 5: Introduction to Markov Random Field
• Lecture 6: Energy Based Models

Inference

• Lecture 7: Variational Inference and Variational Autoencoder (I)
• Lecture 8: Variational Inference and Variational Autoencoder (II)
• Lecture 9: MCMC Sampling (I)
• Lecture 10: MCMC Sampling (II)

Parameter Learning

• Lecture 11: Maximum Likelihood and EM Algorithm

Advanced Topics of LLMs

• Lecture 12: Multi-modal LLMs
• Lecture 13: Parameter-Efficient Finetuning of LLMs
• Lecture 14: LLM Reasoning
• Lecture 15: LLM Watermarking

Diffusion Models

• Lecture 16: Basics of Diffusion Models
• Lecture 17: Advanced Topics of Diffusion Models (I)
• Lecture 18: Advanced Topics of Diffusion Models (II)

Course Project Presentations

• Lecture 19: Course Project Presentation (I)
• Lecture 20: Course Project Presentation (II)