Sipeng Zheng

3
Papers
15
Total Citations

Papers (3)

VideoOrion: Tokenizing Object Dynamics in Videos

ICCV 2025arXiv
8
citations

Unified Multimodal Understanding via Byte-Pair Visual Encoding

ICCV 2025
7
citations

MotionCtrl: A Real-time Controllable Vision-Language-Motion Model

ICCV 2025
0
citations