Bingyi Kang(@bingyikang):3D has always felt essential for visual intelligence that truly works in the real world. The challenge is making it useful in a simple and scalable way. Cambrian-P shows a surprisingly strong signal: adding pose grounding to video understanding substantially improves spatial reasoning, recognition, and even general video QA.

Bingyi Kang

@bingyikang

growing alongside @amilabs, prev: created and led the Depth Anything series

加入 December 2019

409 正在關注 3.5K 粉絲

Bingyi Kang@bingyikang

2026.05.27 05:14

3D has always felt essential for visual intelligence that truly works in the real world. The challenge is making it useful in a simple and scalable way. Cambrian-P shows a surprisingly strong signal: adding pose grounding to video understanding substantially improves spatial reasoning, recognition, and even general video QA.