Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
2
Instead of rebuilding the entire recommendation stack from scratch, LIGE-GR generalizes the existing pointwise recommendation system into a listwise generation system, which allows mature recommender systems to benefit from listwise optimization while preserving compatibility with existing models, value functions, and serving infrastructure.
Sequence recommendation models can achieve near-perfect scaling efficiency in distributed training, slashing wasted GPU cycles by up to 90%.
