During the CL of VLMs, we need not only to prevent the catastrophic forgetting on incrementally learned knowledge but also to preserve the zero-shot ability of VLMs.

This paper presents the first benchmark of uncertainty disentanglement.

Work done while doing an internship at NA VER Cloud.

This also makes the outputs more amenable for training species classifiers on prediction crops, if species are known.

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

MMSite is a two-stage ("First Align, Then Fuse") Understanding these sites is essential for elucidating enzyme mechanisms, designing inhibitors, and developing novel drugs. MNER, high-quality datasets for multi-modal active sites identification are less abundant.