Wenshuo Wang

Papers

Total Citations

H-Index

About

Wenshuo Wang is a leading researcher at the intersection of machine learning and robotics, with a primary focus on neural processes, neurosymbolic AI, and autonomous disassembly systems. His most impactful work, "Recurrent Attentive Neural Process for Sequential Data" (2019, 23 citations), introduced a novel framework that extends Attentive Neural Processes (ANPs) by incorporating recurrent mechanisms to model sequential dependencies. This contribution significantly advanced the ability to predict distributions over functions from sparse context sets, enabling more robust adaptation in dynamic environments—a critical capability for autonomous systems. Wang's research has direct implications for improving prediction accuracy in stochastic processes, particularly in robotics applications where uncertainty is high. More recently, his work "Learning Symbolic Operators: A Neurosymbolic Solution for Autonomous Disassembly of Electric Vehicle Battery" (2022, 2 citations) tackles the pressing challenge of sustainable recycling. By combining symbolic reasoning with neural learning, Wang proposes a framework to automate the disassembly of EV batteries, a task currently reliant on human labor due to unstructured conditions. This neurosymbolic approach promises to enhance robotic autonomy in complex, uncertain environments, positioning Wang as a key innovator in both theoretical machine learning and applied robotics for sustainability.