Search papers, labs, and topics across Lattice.
3
0
4
UniPolicy is proposed, an objective-aware multi-policy alignment framework that supports parallel, business-customizable multi-policy beam search, flexibly allocating candidate quotas across objectives under a fixed retrieval budget and outperforming single-objective reinforcement learning and naive reward-fusion baselines.
Treating historical behavior and current requests as homogeneous context units, UniCon achieves a 3.09% lift in revenue and 2.07% in CTR, outperforming traditional models.
SA-RSQ achieves a remarkable balance between compact storage and high-quality representation, leading to significant performance boosts in real-world recommender systems.
