Multimodal AI

Vision-language, image generation, speech (STT/TTS), and multimodal RAG. The converging edge.

1. 1Image representation: pixels to patches3 q
2. 2Vision-language models: one shared space3 q
3. 3Image generation: denoising step by step3 q
4. 4Speech: STT and TTS concepts3 q
5. 5Multimodal RAG: retrieving over mixed media3 q
6. 6Putting multimodal together: a tiny assistant3 q