Lei Zhang
Corresponding author of GTA-VLA and head of the research group at IDEA.
“GTA-VLA introduces a third input channel — sparse visual cues like a click (affordance point), a drawn box, or a sketched path — that directly conditions the robot's reasoning chain before action is generated.”
Source→“Lei Zhang | IDEA (International Digital Economy Academy) | Corresponding author; head of the research group producing GTA-VLA | leizhang@idea.edu.cn; previously associated with foundational work on T-Rex2 [15] and Rex-Omni [14] for interactive detection”
Source→“previously associated with foundational work on T-Rex2 [15] and Rex-Omni [14] for interactive detection — this group has a consistent research thread on interactive visual grounding now extended to robotics”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.