# Multimodal Architecture Mathematics: Vision Encoder → Projection → LLM — 3 Connection Strategies

> Source: https://sukruyusufkaya.com/en/learn/llm-muhendisligi/multimodal-mimari-matematik-vision-llm-baglama
> Updated: 2026-05-13T13:00:31.526Z
> Category: LLM Mühendisliği
> Module: Module 19: Multimodal Models — Image + Audio + Video
**TLDR:** Internal architectural mathematics of multimodal LLMs: 3 strategies for Vision encoder (ViT/CLIP/SigLIP) → projection → LLM binding. (1) Linear projection (LLaVA style, simple), (2) Q-Former (BLIP-2 style, learnable queries), (3) Cross-attention (Flamingo/Llama-3.2 style, deep integration). Image token budget management, resolution problem, vision-text alignment. LLaVA-style multimodal architecture in PyTorch from scratch. Image-text alignment for Turkish.