Last year has witnessed the re-flourishment of tag-aware recommender systems supported
by the LLM-enriched tags. Unfortunately, though large efforts have been made, current …

Learning representations of words in a continuous space is perhaps the most fundamental
task in NLP, however words interact in ways much richer than vector dot product similarity …

A major factor contributing to the success of modern representation learning is the ease of
performing various vector operations. Recently, objects with geometric structures (eg …

The rapid penetration of electric vehicles (EVs) provides notable opportunities for the EV
charging industry. However, the frequent occurrence of EV overstay results in the …

Embedding-based methods are a cornerstone of modern approaches to modeling graph
data. Geometric embeddings, which represent elements using objects with richer geometric …

Sets are fundamental to human knowledge representation and reasoning, most explicitly as
the axiomatic cornerstone on which all of modern mathematics is built, but also more …

Vector word embeddings are powerful tools, but they do not naturally express uncertainty
about the target concept. Furthermore, they do not naturally model asymmetric relations …