SUIN improves CTR prediction by augmenting target user sequences with similar users' behaviors via embedding-based retrieval, user-specific position encoding, and user-aware target attention.
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 10roles
background 1polarities
background 1representative citing papers
IAT compresses each historical interaction instance into a unified embedding token via temporal-order or user-order schemes, allowing standard sequence models to learn long-range preferences with better performance and transferability.
NSGR is a tree-structured generative reranker that progressively generates optimal lists via next-scale expansion and multi-scale neighbor loss to balance perspectives and align training signals.
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.
MTServe achieves up to 3.1x speedup for generative recommendation model serving by using hierarchical caches with host RAM and system optimizations while keeping cache hit ratios above 98.5%.
MBGR is a new generative recommendation framework using business-aware semantic IDs, multi-business prediction, and label dynamic routing to handle multiple businesses without seesaw effects or representation confusion, validated by experiments and deployed at Meituan.
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.
SIF encodes entire historical raw samples as tokens via hierarchical group-adaptive quantization and token/sample-level mixing to overcome partial encoding and feature heterogeneity limits in scaled recommender models.
LLM-EDT improves cross-domain sequential recommendation by using LLMs for transferable item augmentation, dual-phase training to handle domain transitions, and domain-aware profiling to build user profiles.
A2Gen models temporal user action sequences with context-aware attention and autoregressive generation to improve short video recommendation accuracy, showing gains in watch time and retention on large-scale tests.
citing papers explorer
-
Similar Users-Augmented Interest Network
SUIN improves CTR prediction by augmenting target user sequences with similar users' behaviors via embedding-based retrieval, user-specific position encoding, and user-aware target attention.
-
IAT: Instance-As-Token Compression for Historical User Sequence Modeling in Industrial Recommender Systems
IAT compresses each historical interaction instance into a unified embedding token via temporal-order or user-order schemes, allowing standard sequence models to learn long-range preferences with better performance and transferability.
-
Next-Scale Generative Reranking: A Tree-based Generative Rerank Method at Meituan
NSGR is a tree-structured generative reranker that progressively generates optimal lists via next-scale expansion and multi-scale neighbor loss to balance perspectives and align training signals.
-
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.
-
MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches
MTServe achieves up to 3.1x speedup for generative recommendation model serving by using hierarchical caches with host RAM and system optimizations while keeping cache hit ratios above 98.5%.
-
MBGR: Multi-Business Prediction for Generative Recommendation at Meituan
MBGR is a new generative recommendation framework using business-aware semantic IDs, multi-business prediction, and label dynamic routing to handle multiple businesses without seesaw effects or representation confusion, validated by experiments and deployed at Meituan.
-
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.
-
Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models
SIF encodes entire historical raw samples as tokens via hierarchical group-adaptive quantization and token/sample-level mixing to overcome partial encoding and feature heterogeneity limits in scaled recommender models.
-
LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Training
LLM-EDT improves cross-domain sequential recommendation by using LLMs for transferable item augmentation, dual-phase training to handle domain transitions, and domain-aware profiling to build user profiles.
-
Action-Aware Generative Sequence Modeling for Short Video Recommendation
A2Gen models temporal user action sequences with context-aware attention and autoregressive generation to improve short video recommendation accuracy, showing gains in watch time and retention on large-scale tests.