Image-text contrastive models such as CLIP are useful for a variety of
d...
Few-shot classification (FSC) entails learning novel classes given only ...
Breaking down a document or a conversation into multiple contiguous segm...
Existing meta-learners primarily focus on improving the average task acc...
Intent classification (IC) and slot filling (SF) are two fundamental tas...
Influence functions approximate the effect of training samples in test-t...
We consider membership inference attacks, one of the main privacy issues...
With the rapid adoption of machine learning systems in sensitive
applica...
With the increasing adoption of AI, inherent security and privacy
vulner...