← Search

Zijing Xu

2 accepted papers

2025

DemoSpeedup: Accelerating Visuomotor Policies via Entropy-Guided Demonstration Acceleration

CoRL 2025oral

Imitation learning has shown great promise in robotic manipulation, but the policy’s execution is often unsatisfactorily slow due to commonly tardy demonstrations collected by human operators. In this work, we present DemoSpeedup, a self-supervised method to accelerate visuomotor policy execution vi…

Cited by 0SourceScholar
2024

Exploring the Low-Pass Filtering Behavior in Image Super-Resolution

ICML 2024poster

Deep neural networks for image super-resolution (ISR) have shown significant advantages over traditional approaches like the interpolation. However, they are often criticized as 'black boxes' compared to traditional approaches with solid mathematical foundations. In this paper, we attempt to interpr…