mlsanityData to 7 Oct 2026

MoE for recommender systems

41 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: recommendation, user, item, sequential recommendation, sequential

Key facts. MoE for recommender systems: 41 papers on arXiv since 2020 (data through 7 Oct 2026). 5 of its 41 mapped papers (12%) cite “M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework” (2024, arXiv 2404.18465). 5 of its 41 mapped papers (12%) cite “Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendation” (2025, arXiv 2501.14269). 3 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

3 new since 17 Sep

  1. RouteRec: Behavior-Guided Sparse Routing for Sequential Recommendation
  2. EvoSkillRec: Skill-Genome Evolution for Recommender Architecture Discovery
  3. OneTrans-V2: Unifying Retrieval, Pre-rank, and Fine-rank with One Transformer in Industrial Recommender

Foundations

Most cited by papers here

  1. M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework2024cited by 5 here
  2. Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendation2025cited by 5 here
  3. Sequence-level Semantic Representation Fusion for Recommender Systems2024cited by 3 here
  4. HiNet: Novel Multi-Scenario & Multi-Task Learning with Hierarchical Information Extraction2023cited by 1 here
  5. Facet-Aware Multi-Head Mixture-of-Experts Model for Sequential Recommendation2024cited by 1 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 7 here
  2. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 5 here
  3. 2022Mixture-of-Experts with Expert Choice Routingcited by 2 here
  4. 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Modelscited by 4 here
  5. 2025ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restorationcited by 2 here
19 more it builds on, not in this chain
  1. 2018Deep Mixture of Experts via Shallow Embeddingcited by 1 here
  2. 2020Adversarial Mixture Of Experts with Category Hierarchy Soft Constraintcited by 1 here
  3. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 7 here
  4. 2021DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learningcited by 2 here
  5. 2021Scaling Vision with Sparse Mixture of Expertscited by 1 here
  6. 2021MoEfication: Transformer Feed-forward Layers are Mixtures of Expertscited by 1 here
  7. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 5 here
  8. 2022DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scalecited by 1 here
  9. 2022ST-MoE: Designing Stable and Transferable Sparse Expert Modelscited by 3 here
  10. 2022On the Representation Collapse of Sparse Mixture of Expertscited by 3 here
  11. 2022MegaBlocks: Efficient Sparse Training with Mixture-of-Expertscited by 1 here
  12. 2023HiNet: Novel Multi-Scenario & Multi-Task Learning with Hierarchical Information Extractioncited by 1 here
  13. 2023From Sparse to Soft Mixtures of Expertscited by 1 here
  14. 2023Merging Experts into One: Improving Computational Efficiency of Mixture of Expertscited by 1 here
  15. 2023Mixture of Tokens: Continuous MoE through Cross-Example Aggregationcited by 1 here
  16. 2023Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuningcited by 1 here
  17. 2024Sequence-level Semantic Representation Fusion for Recommender Systemscited by 3 here
  18. 2024M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Frameworkcited by 5 here
  19. 2025Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendationcited by 5 here

The 24 most cited of 40.

Browse

30 of 41, ranked 6–35

  1. 6TokenMixer-Large: Scaling Up Large Ranking Models in Industrial Recommenders20261
  2. 7SMES: Towards Scalable Multi-Task Recommendation via Expert Sparsity20261
  3. 8Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation20261
  4. 9MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization20251
  5. 10Hierarchical LoRA MoE for Efficient CTR Model Scaling20251
  6. 11Facet-Aware Multi-Head Mixture-of-Experts Model with Text-Enhanced Pre-training for Sequential Recommendation20260
  7. 12Give Users the Wheel: Towards Promptable Recommendation Paradigm20260
  8. 13CAMMSR: Category-Guided Attentive Mixture of Experts for Multimodal Sequential Recommendation20260
  9. 14Lightweight Fairness for LLM-Based Recommendations via Kernelized Projection and Gated Adapters20260
  10. 15Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE20260
All 30
  1. 16Heterogeneous Ranking in Industrial-Scale Recommender Systems: A Case Study20260
  2. 17UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models20260
  3. 18Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts20260
  4. 19Beyond Modality Harmony: Orthogonal Purification and Topology-Guided MoE for Conflict-Aware Multimodal Recommendation20260
  5. 20STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation20250
  6. 21Divide-and-Conquer: Cold-Start Bundle Recommendation via Mixture of Diffusion Experts20250
  7. 22Enhancing CTR Prediction with De-correlated Expert Networks20250
  8. 23An Audio-centric Multi-task Learning Framework for Streaming Ads Targeting on Spotify20250
  9. 24M^2VAE: Multi-Modal Multi-View Variational Autoencoder for Cold-start Item Recommendation20250
  10. 25Efficient Multimodal Streaming Recommendation via Expandable Side Mixture-of-Experts20250
  11. 26Multi-modal Adaptive Mixture of Experts for Cold-start Recommendation20250
  12. 27A Self-Supervised Mixture-of-Experts Framework for Multi-behavior Recommendation20250
  13. 28MTmixAtt: Integrating Mixture-of-Experts with Multi-Mix Attention for Large-Scale Recommendation20250
  14. 29Revisiting scalable sequential recommendation with Multi-Embedding Approach and Mixture-of-Experts20250
  15. 30HyMoERec: Hybrid Mixture-of-Experts for Sequential Recommendation20250
  16. 31Tokenize Once, Recommend Anywhere: Unified Item Tokenization for Multi-domain LLM-based Recommendation20250
  17. 32Distillation-based Scenario-Adaptive Mixture-of-Experts for the Matching Stage of Multi-scenario Recommendation20250
  18. 33Automated Information Flow Selection for Multi-scenario Multi-task Recommendation20250
  19. 34HMDN: Hierarchical Multi-Distribution Network for Click-Through Rate Prediction20240
  20. 35Customizing Language Models with Instance-wise LoRA for Sequential Recommendation20240