9 citations · 12 across the 5 of their papers we have counts for
3 papers · 1 filter
Beyond I-Con: Exploring New Dimension of Distance Measures in Representation Learning
Jasmine Shone, Zhening Li, Shaden Alshammari +2
The Information Contrastive (I-Con) framework revealed that over 23 representation learning methods implicitly minimize KL divergence between data and learned distributions that en…
I-Con: A Unifying Framework for Representation Learning
Shaden Alshammari, John Hershey, Axel Feldmann +2
As the field of representation learning grows, there has been a proliferation of different loss functions to solve different classes of problems. We introduce a single information-…
Vision-Language Models Do Not Understand Negation
Kumail Alhamoud, Shaden Alshammari, Yonglong Tian +4
Many practical vision-language applications require models that understand negation, e.g., when using natural language to retrieve images which contain certain objects but not othe…