XPENG releases TuringViT for smart driving and humanoid robots

XPENG released TuringViT, a vision encoder for vision-language and vision-language-action models, with two variants: TuringViT-18L and TuringViT-24L. At 1536x1536 resolution, the company claims TuringViT-18L reached 3.04 on an unspecified benchmark.