However, these results lack reliable uncertainty estimates.

Anomaly detection in time series data is fundamental to the design, deployment, and evaluation of industrial control systems.

The number of features is comparable to the sample size and errors may be heavy-tailed.

This work was done during the internship at Microsoft Research Asia.

Specifically, we propose a multi-view masking strategy for addressing the challenges of endoscopic videos.

The recently introduced Consistency models pose an efficient alternative to diffusion algorithms, enabling rapid and good quality image synthesis.

Video understanding relies on accurate action detection for temporal analysis.