Course Calendar
The planned course schedule is provided below.
Week 1
- Jan 05
- BackgroundCourse Introduction & Overview of Foundation Models
- Lecture Material:
- Recording:
- Lecture Material:
- Jan 07
- BackgroundIntroduction to LLMs
- Lecture Material:
- Suggested Reading:
- Monitoring AI-Modified Content at Scale
- Scaling Instruction-Finetuned Language Models
- Training Language Models to Follow Instructions
- Using ChatGPT to Facilitate Truly Informed Medical Consent
- Recording:
- Lecture Material:
Week 2
- Jan 12
- BackgroundAgentic Systems
- Lecture Material:
- Recording:
- Lecture Material:
- Jan 14
- BackgroundEvaluation of LLMs and Agents, MedArena (Eric Wu)
- Lecture Material:
- Recording:
- Lecture Material:
Week 3
- Jan 19
- No Class - MLK Day
- Jan 21
- BackgroundEvaluation of LLMs (Pt. 2)
- Lecture Material:
- Suggested Reading:
- The Leaderboard Illusion
- MedVAL: Toward Expert-Level Medical Text Validation with Language Models
- A Survey on LLM-as-a-Judge
- Recording:
- Lecture Material:
Week 4
- Jan 26
- BackgroundRetrieval Augmented Generation, Mixture of Experts
- Lecture Material:
- Suggested Reading:
- Recording:
- Lecture Material:
- Jan 28
- BackgroundInference Scaling and Reasoning
- Lecture Material:
- Suggested Reading:
- Recording:
- Lecture Material:
Week 5
- Feb 02
- BackgroundVision-Language Models (Maya Varma)
- Lecture Material:
- Suggested Reading:
- Learning Transferable Visual Models From Natural Language Supervision
- Sigmoid Loss for Language Image Pre-Training
- Domino: Discovering Systematic Errors with Cross-Modal Embeddings
- Recording:
- Lecture Material:
- Feb 04
- BackgroundMechanistic Interpretability of VLMs (Robbie Holland)
- Lecture Material:
- Recording:
- Lecture Material:
Week 6
- Feb 09
- BackgroundGenerative VLMs for Vision
- Lecture Material:
- Suggested Reading:
- High-Resolution Image Synthesis with Latent Diffusion Models
- MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoders
- A vision–language foundation model for the generation of realistic chest X-ray images
- Recording:
- Lecture Material:
- Feb 11
- BackgroundGenerative VLMs for Text
- Lecture Material:
- Suggested Reading:
- Visual Instruction Tuning
- xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
- A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation
- Recording:
- Lecture Material:
Week 7
- Feb 16
- No Class - Presidents’ Day
- Feb 18
- BackgroundFoundation Models for Segmentation
- Lecture Material:
- Recording:
- Lecture Material:
Week 8
- Feb 23
- ApplicationsRegulation and Deployment: EchoNet Case Study
- Recording:
- Feb 25
- ApplicationsSleepFM: Multimodal Foundation Model of Sleep
Week 9
- Mar 02
- BackgroundAdvanced Architectures
- Mar 04
- BackgroundEMR Foundation Models (Jason Fries)
Week 10
- Mar 09
- OpportunitiesEthics of Foundation Models (Roxana Daneshjou)
- Mar 11
- Project Presentations DueFinal Presentations