Search papers, labs, and topics across Lattice.
Affiliation:
6
0
6
1
SWIM redefines list evaluation by modeling user engagement as a survival process, leading to substantial gains in recommendation effectiveness.
UAME transforms the way we handle user satisfaction in video recommendations by incorporating uncertainty directly into the optimization process, yielding superior alignment with actual user preferences.
A2Gen transforms short video recommendations by treating user actions as dynamic sequences, resulting in substantial improvements in user engagement metrics.
Reranking in recommender systems can be revolutionized by shifting from local indices to generating global identifiers, enhancing robustness and user satisfaction.
SVD-Attention slashes the quadratic cost of attention to linear for recommendation tasks by exploiting the inherent low-rank structure of user behavior sequences, without sacrificing softmax.
FlashEvaluator slashes the computational cost of evaluating multiple sequences in Generator-Evaluator frameworks while boosting accuracy by enabling direct cross-sequence comparisons.
