mlsanityData to 7 Oct 2026

UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence

arXiv 2605.09040 ↗First posted 9 May 2026cs.AI cs.IR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Modeling ultra-long user sequences involves a difficult trade-off between efficiency and effectiveness. While current paradigms rely on either item-specific search or item-agnostic compression, we propose UxSID, a framework exploring a third path: semantic-group shared interest memory. By utilizing Semantic IDs (SIDs) and a dual-level attention strategy, UxSID captures target-aware preferences without the heavy cost of item-specific models. This end-to-end architecture balances computational parsimony with semantic awareness, achieving state-of-the-art performance and a 0.337% revenue lift in large-scale advertising A/B test.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 45 references that are in the map. First posted on arXiv 9 May 2026.

Builds on

37 of 45 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2018Self-Attentive Sequential Recommendationcited by 1,169
  4. 2016Wide & Deep Learning for Recommender Systemscited by 745
  5. 2017Deep Interest Network for Click-Through Rate Predictioncited by 541
  6. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 425
  7. 2018Deep Interest Evolution Network for Click-Through Rate Predictioncited by 336
  8. 2023Recommender Systems with Generative Retrievalcited by 191
  9. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 184
  10. 2020Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Predictioncited by 176
  11. 2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 167
  12. 2019Behavior Sequence Transformer for E-commerce Recommendation in Alibabacited by 128
25 more
  1. 2019Practice on Long Sequential User Behavior Modeling for Click-Through Rate Predictioncited by 118
  2. 2019Multi-Interest Network with Dynamic Routing for Recommendation at Tmallcited by 113
  3. 2024Learnable Item Tokenization for Generative Recommendationcited by 106
  4. 2022KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systemscited by 94
  5. 2019Deep Session Interest Network for Click-Through Rate Predictioncited by 64
  6. 2022PinnerFormer: Sequence Modeling for User Representation at Pinterestcited by 57
  7. 2025MTGR: Industrial-Scale Generative Recommendation Framework in Meituancited by 47
  8. 2025LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenderscited by 46
  9. 2021End-to-End User Behavior Retrieval in Click-Through RatePrediction Modelcited by 45
  10. 2019Lifelong Sequential Modeling with Personalized Memorization for User Response Predictioncited by 41
  11. 2023TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishoucited by 40
  12. 2023TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterestcited by 35
  13. 2024TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishoucited by 30
  14. 2025OneRec-V2 Technical Reportcited by 28
  15. 2025PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendationscited by 27
  16. 2024QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishoucited by 26
  17. 2022Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Predictioncited by 24
  18. 2025DV365: Extremely Long User History Modeling at Instagramcited by 8
  19. 2025DAS: Dual-Aligned Semantic IDs Empowered Industrial Recommender Systemcited by 8
  20. 2024Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Predictioncited by 7
  21. 2026DOS: Dual-Flow Orthogonal Semantic IDs for Recommendation in Meituancited by 3
  22. 2026PIT: A Dynamic Personalized Item Tokenizer for End-to-End Generative Recommendationcited by 3
  23. 2024Multi-Grained Preference Enhanced Transformer for Multi-Behavior Sequential Recommendationcited by 2
  24. 2026QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modelingcited by 2
  25. 2026Farewell to Item IDs: Unlocking the Scaling Potential of Large Ranking Models via Semantic Tokenscited by 1

Built on by

Not cited yet.