Search papers, labs, and topics across Lattice.
2
0
2
2
This work shows that robust preference alignment benefits from addressing different noise types with targeted interventions rather than uniform regularization, and proposes wDPO, a robust LLM alignment approach with hierarchical winsorization.
PrismRec revolutionizes micro-video recommendation by treating video content as a core driver of user preferences, achieving a remarkable 22.65% improvement over existing methods.
