CVPR 2026: NVIDIA, Tesla, and Waymo hear Xpeng present physical AI

CVPR 2026，英伟达特斯拉Waymo一块听中国公司讲物理AI

Xpeng presented its world-model stack at CVPR 2026, covering X-World, X-Foresight, and X-Cache; the article says X-Cache cuts about 70% of repeated computation, the second-generation VLA used over 4 trillion training tokens, and the in-car stack reduced inference latency to 80 ms.

Why it matters: HKR-H comes from the CVPR stage contrast, HKR-K has X-Cache, 4T+ tokens, and 80 ms latency, and HKR-R fits autonomy competition. It is still a company tech showcase, below the 85 must-write band.