Zhongang Cai @CVPR'26's banner
Zhongang Cai @CVPR'26's profile picture

Zhongang Cai @CVPR'26

@caizhongang • 1,321 subscribers

Staff Research Scientist, SenseTime Research. Multimodal, Video Reasoning, Spatial Intelligence, Virtual Humans. Ph.D., S-Lab/MMLab@NTU.

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

Video might be the next intelligence substrate. Strikingly, video models are beginning to exhibit the same emergent reasoning behaviors first observed in LLMs—multi-path search, self-correction, and layer specialization. We demystify video reasoning and show it doesn’t happen frame-by-frame, but along diffusion steps. 🔗 📄 So, what's next? ;)
1:19
caizhongang's profile picture

Video might be the next intelligence substrate. Strikingly, video models are beginning to exhibit the same emergent reasoning behaviors first observed in LLMs—multi-path search, self-correction, and layer specialization. We demystify video reasoning and show it doesn’t happen frame-by-frame, but along diffusion steps. 🔗 📄 So, what's next? ;)

Zhongang Cai @CVPR'26

70,629 Aufrufe • vor 4 Monaten

Keine weiteren Inhalte verfügbar