Caltech's DynaTokens teaches dynamics to camera-controlled video models at test time, NeurIPS accepted

georgiagkioxari · x · 2026-09-30

Caltech researchers Ziqi Ma, Hongqiao Chen and Georgia Gkioxari introduce DynaTokens, a NeurIPS-accepted fix for camera-controlled video models that nail camera motion but fail at scene dynamics:

Project page, paper and code are public.

Original post →

More from Multimodal

Multimodal channel →