Zhongang Cai
Zhongang Cai is a Staff Research Scientist at SenseTime Research and a core contributor to SenseNova, where he works on multimodal models and spatial intelligence. He received his Ph.D. from MMLab at Nanyang Technological University, advised by Prof. Ziwei Liu and Prof. Chen Change Loy. He is best known for his research on visual reasoning, spatial intelligence, and virtual humans, including leading the development of SenseNova-SI and co-authoring works such as VBVR-Pro and Scaling Spatial Intelligence with Multimodal Foundation Models.
“GPT-6-Astra outperforms existing methods by substantial margins, including recent agentic approaches that also build on GPT-6-Astra.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.