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
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IR 4years
2026 4roles
background 1polarities
background 1representative citing papers
MoS applies theme-aware routing to extract multi-scale theme-specific subsequences from noisy long user sequences, achieving state-of-the-art recommendation performance with fewer FLOPs than comparable MoE models.
SpecTran applies a spectral-aware transformer adapter with learnable position encoding to aggregate informative components across the full spectrum of LLM embeddings, yielding 9.17% average gains on sequential recommendation tasks.
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.
-
Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation
MoS applies theme-aware routing to extract multi-scale theme-specific subsequences from noisy long user sequences, achieving state-of-the-art recommendation performance with fewer FLOPs than comparable MoE models.
-
SpecTran: Spectral-Aware Transformer-based Adapter for LLM-Enhanced Sequential Recommendation
SpecTran applies a spectral-aware transformer adapter with learnable position encoding to aggregate informative components across the full spectrum of LLM embeddings, yielding 9.17% average gains on sequential recommendation tasks.
- BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models