2 papers
cs.LG2025
Denoising-based Contractive Imitation Learning
Macheng Shen, Jishen Peng, Zefang Huang
A fundamental challenge in imitation learning is the \emph{covariate shift} problem. Existing methods to mitigate covariate shift often require additional expert interactions, acce…
cs.LG2025
Neural SDEs as a Unified Approach to Continuous-Domain Sequence Modeling
Macheng Shen, Chen Cheng
Inspired by the ubiquitous use of differential equations to model continuous dynamics across diverse scientific and engineering domains, we propose a novel and intuitive approach t…