First-principles AI engineering from 21 foundational research
papers.
Foundations
How models work: generative models, transformers, pretraining,
fine-tuning, alignment.
Generative Adversarial Nets
Summary · Course
Auto-Encoding Variational
Bayes
Summary · Course
Attention Is All You Need
Summary · Course
Improving
Language Understanding by Generative Pre-Training
Summary · Course
Summary · Course
Scaling Laws for Neural
Language Models
Summary · Course
Training
Language Models to Follow Instructions with Human Feedback
Summary · Course
Summary · Course
Learning
Transferable Visual Models From Natural Language Supervision
Summary · Course
Retrieval-Augmented
Generation for Knowledge-Intensive NLP Tasks
Summary · Course
Denoising Diffusion
Probabilistic Models
Summary · Course
Parameter-Efficient
Transfer Learning for NLP
Summary · Course
LoRA:
Low-Rank Adaptation of Large Language Models
Summary · Course
Prompt Engineering
How to instruct models: chain-of-thought, reasoning+acting,
self-improvement.
Chain-of-Thought
Prompting Elicits Reasoning in Large Language Models
Summary · Course
ReAct:
Synergizing Reasoning and Acting in Language Models
Summary · Course
Self-Refine:
Iterative Refinement with Self-Feedback
Summary · Course
Context Engineering
How to manage what models see: retrieval, position effects,
memory.
Lost
in the Middle: How Language Models Use Long Contexts
Summary · Course
MemGPT: Towards LLMs
as Operating Systems
Summary · Course
Inference
How to run models smartly: sampling strategies, search over
reasoning, speculative decoding.
Self-Consistency
Improves Chain of Thought Reasoning in Language Models
Summary · Course
Tree
of Thoughts: Deliberate Problem Solving with Large Language Models
Summary · Course
Summary · Course
Future Tracks
- Computer vision – ResNet, AlexNet, VGG
- Reinforcement learning – AlphaGo, PPO, MuZero
- Optimization – Adam, BatchNorm, Dropout