Gregorio F. Azevedo
3 papers · Latest:
Information Retrieval
The Bandit's Blind Spot: The Critical Role of User State Representation in Recommender Systems
User state representation in CMAB recommender systems is more critical than the bandit algorithm itself, often yielding greater performance improvements.
2604.26651
Information RetrievalLearning Behaviorally Grounded Item Embeddings via Personalized Temporal Contexts
TAI2Vec learns item embeddings by integrating personalized temporal contexts, distinguishing short-term and long-term user preferences for better recommendations.
2604.15581
Information RetrievalCollaborative Filtering Through Weighted Similarities of User and Item Embeddings
This paper introduces an efficient ensemble method for collaborative filtering, unifying user-item and item-item recommendations with shared embeddings.
2604.15573
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.