Yunbo Wang

Shanghai Jiao Tong University, University of California, Los Angeles

Papers

Total Citations

H-Index

About

Yunbo Wang is a leading researcher in predictive learning and robotic manipulation, with a focus on building world models that can adapt to changing environments. His work addresses the fundamental challenge of continual predictive learning from videos, where he develops models capable of sequentially learning from different physical environments without catastrophic forgetting—a critical step toward more robust and generalizable AI systems. His 2022 paper on this topic has already garnered significant attention, laying the groundwork for future advances in lifelong learning for video prediction. In parallel, Wang has made notable contributions to robotics, particularly in vision and force-based autonomous coating with rollers. His 2020 work introduces a cost-effective method for general-purpose robots to perform structural painting tasks, integrating visual and tactile feedback for precise, adaptive control. This research bridges the gap between high-level predictive models and real-world robotic applications. With a growing citation impact, Wang’s work is shaping the future of both continual learning and autonomous manipulation, offering practical solutions for adaptive, intelligent systems.