# MARS: Multi-resolution Adaptive Routing for Sequential Recommendation

arXiv: https://arxiv.org/abs/2610.07505 · HTML: https://mlsanity.com/paper/2610.07505/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 47 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 30 of 30)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Gated Linear Attention Transformers with Hardware-Efficient Training](https://mlsanity.com/paper/2312.06635/) (2023)
- [Deep Interest Evolution Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1809.03672/) (2018)
- [Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations](https://mlsanity.com/paper/2402.17152/) (2024)
- [Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction](https://mlsanity.com/paper/2006.05639/) (2020)
- [A Clockwork RNN](https://mlsanity.com/paper/1402.3511/) (2014)
- [Can recurrent neural networks warp time?](https://mlsanity.com/paper/1804.11188/) (2018)
- [LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders](https://mlsanity.com/paper/2505.04421/) (2025)
- [Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers](https://mlsanity.com/paper/2407.09941/) (2024)
- [TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou](https://mlsanity.com/paper/2302.02352/) (2023)
- [MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs](https://mlsanity.com/paper/2508.18264/) (2025)
- [Mamba4Rec: Towards Efficient Sequential Recommendation with Selective State Space Models](https://mlsanity.com/paper/2403.03900/) (2024)
- [A Comprehensive Review of Recommender Systems: Transitioning from Theory to Practice](https://mlsanity.com/paper/2407.13699/) (2024)
- [Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos](https://mlsanity.com/paper/2303.12370/) (2023)
- [Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative Recommenders](https://mlsanity.com/paper/2510.22049/) (2025)
- [Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction](https://mlsanity.com/paper/2411.15005/) (2024)
- [ms-Mamba: Multi-scale Mamba for Time-Series Forecasting](https://mlsanity.com/paper/2504.07654/) (2025)
- [Rethinking Large-scale Pre-ranking System: Entire-chain Cross-domain Models](https://mlsanity.com/paper/2310.08039/) (2023)
- [Hi-SAM: A Hierarchical Structure-Aware Multi-modal Framework for Large-Scale Recommendation](https://mlsanity.com/paper/2602.11799/) (2026)
- [When History Misleads: Asymmetric Margin Supervision for Instruction-Guided LLM Generative Recommendation](https://mlsanity.com/paper/2610.02600/) (2026)

## Abstract (arXiv)

Long-history recommenders often compress each user's history into a compact, candidate-independent memory that is cached and reused to score large candidate pools. We show that real user histories exhibit multi-scale semantic structure, with short-lived intent, medium-term interests, and long-term preferences coexisting in one sequence, and that monolithic cached memories preserve these scales unevenly: linear probes recover recent and mid-range content far worse than long-range content. We call this failure mode textittemporal aliasing. We propose MARS, a multi-resolution user memory that writes the full history into recurrent state tracks anchored to different half-lives, and a sparse routing reader that materializes compact seed memories by selecting the relevant temporal resolutions for each seed, preserving fixed-size candidate scoring. MARS outperforms strong baselines on three public datasets, with gains that grow with history length. Component-matched ablations with paired tests show that temporal diversity and selective routing each contribute beyond what hard-window memories or added capacity provide. The advantage of MARS over its interface-matched baseline also widens after within-user behavioral shifts, at about 1.02× that baseline's warm-cache serving latency for 1,000 candidates per user.