Dynamic Focus

What is Dynamic Focus? Why does it exist? Where does it appear in Attention?

Draw or describe a visual model of Dynamic Focus. What does it look like conceptually?

Work through a concrete manual example of Dynamic Focus with real numbers or pseudocode.

Implement Dynamic Focus from scratch in Python. Keep it minimal — just enough to see it work.

Try Dynamic Focus on a real example. Vary the inputs and observe what changes.

How is Dynamic Focus different from related concepts in Attention? What are the trade-offs?

Explain Dynamic Focus in plain language using an analogy. Could a non-expert follow it?

Build a small project or demo that uses Dynamic Focus as a core component.