SCRIPT presents a scalable diffusion policy with JAST-DiT architecture, nonlinear history conditioning, and RLHR post-training that claims to outperform prior methods on text alignment, motion quality, and physical realism while scaling on a 1200-hour dataset.
ACM Transactions on Graphics (ToG) , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
AnyAct generates editable human reenactments from character videos via conditional motion generation from transferable sparse local 2D articulated cues, with designs for human-only supervision and global-local decoupling.