AI Dynamics

Global AI News Aggregator

About

Why Frontier VLMs Lag Behind LLMs and Vision Models

Frontier LLM have superhuman text-based world knowledge. Frontier image / video models have superhuman vision-based world knowledge (e.g. Genie). But current frontier VLMs are still absolutely clown shoes. Why? Relative scarcity of image:text pairs (while there is plenty of text

→ View original post on X — @fchollet