Search papers, labs, and topics across Lattice.
Polytechnic University of Bari
7
0
10
A unified taxonomy reveals how agentic architectures can transform recommender systems into more autonomous and interactive entities.
ORM-based verification outperforms traditional heuristic methods in Text-to-SQL tasks, achieving significant accuracy gains and scalability.
Visual evidence sources in movie recommendations are not interchangeable; the choice of modality can drastically alter ranking accuracy and diversity.
FlowLet can generate high-fidelity 3D brain MRIs with fewer sampling steps, enhancing brain age prediction for underrepresented demographics.
Stop rewriting your recommender systems for production: WarpRec lets you seamlessly transition from local experimentation to distributed training with 50+ algorithms and built-in energy tracking.
Ditch the data drop: training-free graph imputation lets multimodal recommender systems handle missing data better than ever, boosting performance without retraining.
Key contribution not extracted.