Transformer
The neural network architecture behind virtually all modern AI, introduced by Google researchers in the 2017 paper Attention Is All You Need. Its key trick, self-attention, lets the model weigh how every word (or image patch) relates to every other one, capturing context brilliantly. Transformers power LLMs like Gemini and GPT, plus many image, video, and music models. For creators, the practical impact: transformers understand long, detailed prompts, so specificity pays off. When you write 'a corgi in a spacesuit, floating, Earth in the background', attention connects all those pieces into one coherent scene.