Skip to content
All tags

#clip

2 posts
ai deep-dive Reading Stanford CS336

CS336 Lecture 17: Multimodal Models Turn Images into Tokens, Then Reconcile Semantics with Detail

Lecture 17 organizes CLIP/SigLIP, LLaVA, Qwen-VL, and Chameleon into three paths: contrastive encoders learn semantics, vision-encoder/projector/LM stacks provide understanding, and discrete image tokens enable generation. Resolution, token budgets, and modality balance constrain them all.

#cs336#multimodal#vision-language-model#clip#qwen-vl
ai guide The RAG Techniques Compendium

Multimodal RAG: Bringing Images into the Knowledge Base

Climbing routes carry a ton of visual information (topos, wall photos) that text-only RAG misses entirely. Multimodal RAG makes images searchable and understandable.

#rag#multimodal#vision#image-embedding#clip