Booth 21-25 | AI Data Management Zone | Tokyo Big Sight
There’s a quiet result from Cheng et al. (Renmin University and Microsoft Research, 2026) that I keep coming back to. They gave large language models access to a minimal sandbox
Imagine if every time a human hand reached into a dark shelf or pinched a small component, the robot’s vision system simply guessed where the fingers went. This is the current reality of robotic development. We’ve spent years perfecting single-view pose estimation only to hit a persistent technical ceiling: the
