Search papers, labs, and topics across Lattice.
5
3
8
5
TGR revolutionizes industrial recommendation systems by achieving a staggering 477.8% boost in cold-start new-user engagement through innovative generative techniques.
CCFormer delivers a 3.57% increase in click-through rates and a 1.71% boost in advertising revenue, all while cutting model training time by over 2x.
BARGE not only restores item-level structure in recommendations but also achieves a 1.70% increase in total reading time on a major platform, showcasing its industrial relevance.
LLM safety can be significantly bolstered against harmful fine-tuning attacks by strategically projecting models back into safe parameter space using a relevance- and diversity-aware curated dataset.
Recommendation agents can achieve state-of-the-art performance by personalizing not just user memory, but also the reasoning process itself through self-evolving, user-specific policy skills.
