Shusheng Yang(@shushengyang):Check out Cambrian-P, a must-read if you work on video/3D MLLMs or spatial understanding. Key takeaway: camera pose, which naturally describe the relationships between isolated frames, turns out to be highly effective for enhancing video understanding and spatial intelligence!

Shusheng Yang

@shushengyang

Ph.D. @NYU_Courant advised by Prof. @sainingxie

加入 December 2020

1.1K 正在關注 930 粉絲

Shusheng Yang@shushengyang

2026.05.26 23:26

Check out Cambrian-P, a must-read if you work on video/3D MLLMs or spatial understanding. Key takeaway: camera pose, which naturally describe the relationships between isolated frames, turns out to be highly effective for enhancing video understanding and spatial intelligence!