Xiongjie Chen

Papers

Total Citations

H-Index

About

Xiongjie Chen is a researcher specializing in sequential Bayesian inference, probabilistic state estimation, and the integration of deep learning with classical filtering methods. His work sits at a compelling intersection of machine learning and signal processing, with a particular focus on advancing particle filter methodologies for complex, real-world applications. Chen's most significant contribution lies in the development and formalization of differentiable particle filters — a framework that embeds neural networks into traditional particle filter architectures, enabling dynamic and measurement models to be learned end-to-end from data. His 2023 overview paper on differentiable particle filters for data-adaptive sequential Bayesian inference has rapidly garnered 27 citations, establishing itself as a key reference in the field. This work systematically surveys how differentiable implementations allow particle filters to scale effectively to large, non-linear estimation problems that classical approaches struggle to address. His 2021 paper on end-to-end semi-supervised learning for differentiable particle filters, with 15 citations, further demonstrates his commitment to practical applicability, reducing reliance on fully labeled datasets — a critical advantage in real-world deployments. Collectively, Chen's research is shaping how the probabilistic inference community thinks about combining principled Bayesian methods with modern machine learning flexibility.