Introduces versioned late materialization to eliminate data redundancy in ultra-long sequence training for DLRMs by storing histories once and reconstructing via pointers at training time.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
IID-Nav enables progressive retrieval in large-scale recommenders by treating it as iterative goal-driven graph traversal with recursive state evolution supporting unlimited depth without rising inference cost.
citing papers explorer
-
Versioned Late Materialization for Ultra-Long Sequence Training in Recommendation Systems at Scale
Introduces versioned late materialization to eliminate data redundancy in ultra-long sequence training for DLRMs by storing histories once and reconstructing via pointers at training time.
-
From Extraction to Navigation: Progressive Retrieval with Indirectly Infinite Depth
IID-Nav enables progressive retrieval in large-scale recommenders by treating it as iterative goal-driven graph traversal with recursive state evolution supporting unlimited depth without rising inference cost.