Weiyu Guo

Event-VLA achieves robust robotic manipulation even in near-dark conditions by effectively integrating motion-sensitive event streams with traditional RGB inputs.

Robots can now "remember" and manipulate objects they can't currently see, thanks to a spatial memory system that lets them reason beyond their immediate field of view.

Q-Gate dynamically optimizes keyframe selection by intelligently routing attention based on query intent, outperforming traditional methods that struggle with modality noise.