TT-VidT: temporal-decoupled video pretraining accepted at NeurIPS

CMHungSteven · x · 2026-09-29

KBlueleaf (Spellbrush) announced that TT-VidT, a video pretraining method, has been accepted at NeurIPS. The approach decouples temporal information to extract real motion cues from video, achieving high-quality results with only small-scale training. Collaborators include NVIDIA and Spellbrush.

Original post →

More from Research

Research channel →