Zanxin Chen

Robotics Research (United States), Shenzhen Academy of Robotics, Shenzhen University

Papers

Total Citations

H-Index

About

Zanxin Chen is an emerging researcher at the forefront of robotics and embodied artificial intelligence, with a focused body of work addressing some of the most pressing challenges in autonomous robotic manipulation. His research centers on dual-arm robot coordination, generative digital twins, and pose-aware object manipulation — areas critical to advancing next-generation autonomous systems. Chen's most notable contribution is the **RoboTwin** benchmark, a dual-arm robot evaluation framework leveraging generative digital twins to produce diverse, high-quality demonstration data that bridges the gap between simulation and real-world deployment. Published across multiple iterations in 2024–2025, this work has rapidly accumulated nearly 30 cumulative citations, signaling strong community interest and uptake. By tackling the persistent scarcity of realistic training benchmarks, RoboTwin represents a meaningful infrastructure contribution to the robotics research ecosystem. Complementing this, his work on **G3Flow** introduces a generative 3D semantic flow framework that integrates geometric precision with semantic understanding for generalizable manipulation policies — pushing imitation learning closer to human-level dexterity. Together, Chen's publications reflect a coherent and ambitious research vision: making robot learning more data-rich, realistic, and generalizable, with growing influence evidenced by his citation trajectory in just his early career stage.