UG-Separation framework disentangles user-side and item-side flows in TokenMixer dense-interaction models to enable reusable user computations, cutting inference latency up to 20% in ByteDance production scenarios.
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
Variations in user state embeddings for CMAB recommenders can improve performance more than changing the bandit algorithm, with no embedding or aggregation strategy dominating across datasets.
citing papers explorer
-
Compute Only Once: UG-Separation for Efficient Large Recommendation Models
UG-Separation framework disentangles user-side and item-side flows in TokenMixer dense-interaction models to enable reusable user computations, cutting inference latency up to 20% in ByteDance production scenarios.
-
The Bandit's Blind Spot: The Critical Role of User State Representation in Recommender Systems
Variations in user state embeddings for CMAB recommenders can improve performance more than changing the bandit algorithm, with no embedding or aggregation strategy dominating across datasets.