Preprint
Aug 2026
Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes
This study provides empirical clarity through a systematic exploration of multimodal pretraining and derives efficient pretraining recipes that achieve strong generative performance using only 5% of the compute budget.
Junlin Han, Shengbang Tong, David Fan et al.
· 0 citations