AI Dynamics

Global AI News Aggregator

About

Causal prediction alone enables strong visual learning

A new mind-blowing finding:
causal prediction alone is sufficient for strong visual learning, no need for any fancy reconstruction, masking, or contrastive loss In this paper NEPA, instead of reconstructing pixels, they train a vision model to autoregressively predict the next

→ View original post on X — @askalphaxiv