Search papers, labs, and topics across Lattice.
Technical University of Denmark
4
0
4
Achieving near-state-of-the-art performance without training, ZoRRO revolutionizes the speed and efficiency of personalized news recommendations.
NAILS aligns recommender systems with normative objectives without retraining, balancing user engagement with fairness and diversity.
Jeffrey guidance can significantly improve diffusion model outputs while ensuring fairness across attributes, challenging the limitations of standard sampling techniques.
Latent diffusion models can handle missing data far more robustly than pixel-space diffusion, maintaining high sample quality even with 50% data missing.
