What is LoRA? Why does it exist? Where does it appear in Fine-Tuning?
Draw or describe a visual model of LoRA. What does it look like conceptually?
Implement LoRA from scratch in Python. Keep it minimal — just enough to see it work.
How is LoRA different from related concepts in Fine-Tuning? What are the trade-offs?
Explain LoRA in plain language using an analogy. Could a non-expert follow it?