Ninghan Zhong

Ninghan Zhong is a Robotics PhD student at the Georgia Institute of Technology, where he is advised by Prof. Sriram Vishwanath and collaborates with Prof. Glen Chou. His research focuses on the intersection of robot learning and planning, with ongoing work on latent world models that plan from vision and touch. He is best known for GT-VLA, a steerable Vision-Language-Action framework that translates high-level VLM guidance into 2D visual traces to steer low-level VLA execution on unseen tasks and configurations.