Prerequisites: CS 228, EE 228, EE 242A, CS 224; graduate standing; or consent of instructor
Description: Explores key concepts in foundation models and recent advances in AI. Covers model architectures such as attention, transformers, and state space models; training pipelines including pretraining, fine-tuning, and reinforcement learning from human feedback; data acquisition strategies; tool augmentations; multimodal models; and techniques for efficient training and inference.