Jiahe Chen
Jiahe Chen is a first-year PhD student at the OpenRobotLab of Shanghai AI Laboratory, jointly enrolled with the College of Computer Science and Technology at Zhejiang University, advised by Jiangmiao Pang and Dahua Lin. His research focuses on embodied AI, robot learning, and humanoid robot motion generation. He is best known as co-first author of Imagine2Real, a 2026 paper proposing video generation models as synthetic data sources for zero-shot humanoid-object interaction, and previously contributed to GRUtopia, a large-scale simulated robotic environment, and MGF (Mixed Gaussian Flow), accepted at NeurIPS 2024.
“Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors”
Source→“The primary bottleneck is the lack of high-fidelity 3D interaction data for humanoid robots, which prevents the learning of robust and versatile interaction policies.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.