Abstract: In this letter, we present a novel dual-task, closed-loop, visual servoing-based active vision framework in an eye-in-hand configuration. The proposed active vision framework continuously ...
CVPR 2026 opened Friday in Denver with a record 16,092 submissions and 4,089 accepted papers — a 42% jump — as ...
Xpeng's Dr. Xianming Liu explains VLA 2.0's vision-to-action approach, $300M/month R&D spend, and why the company sees itself as a Physical AI firm, not a car maker.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results