// PERSON
Zijian Zhu
ROLE RESEARCHERAT SYNTHOID.AIMENTIONS 1LAST SEEN JUNE 2, 2026
// BIO
Zijian Zhu is a researcher affiliated with Synthoid.ai and a co-author of RDGen, a sim-to-real reinforcement learning framework for generating high-quality robot demonstrations to train Vision-Language-Action models. The paper, co-authored with Menglin Zou and others, was published on arXiv in May 2026. He is best known for this work on using RL-generated trajectories as an alternative to human teleoperation for robot policy learning.
// RECENT MENTIONS
// SIGNALS
1 SIGNAL
01
product·arXiv Physical AI·JUNE 2, 2026
“RDGen leverages trained RL policies as a structured trajectory generator... Successful rollouts are then harvested as clean, high-quality demonstrations for downstream VLA training.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.