Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes Paper • 2608.05000 • Published Aug 6 • 64
Small Vision-Language Models are Smart Compressors for Long Video Understanding Paper • 2604.08120 • Published Apr 9 • 20
OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory Paper • 2512.07802 • Published Dec 8, 2025 • 47