Zaijin Wang

Beijing Institute for General Artificial Intelligence, Beijing Academy of Artificial Intelligence

Papers

Total Citations

H-Index

About

Zaijin Wang is a rising researcher at the forefront of embodied AI and robotics, with a focus on bridging the gap between simulation and real-world mobile manipulation. Wang’s work centers on enabling robots to understand and interact with complex 3D environments through a combination of diffusion-based planning and part-level scene understanding. In their highly cited work, "M² Diffuser" (2025, 9 citations), Wang pioneered a diffusion-based trajectory optimization method that coordinates both navigation and manipulation—a long-standing challenge in robotics. This was preceded by a foundational contribution in "Part-level Scene Reconstruction Affords Robot Interaction" (2023, 8 citations), which introduced a novel approach to reconstructing interactive scenes at the part level, allowing robots to interact with objects more naturally without relying on limited CAD model databases. Wang also led the development of PR2 (2025, 2 citations), a physics- and photo-realistic humanoid testbed designed to accelerate collaborative research between embodied AI and robotics. With a growing citation footprint and a focus on practical, deployable solutions, Zaijin Wang is shaping the next generation of intelligent, mobile robotic agents.