Overview

Sequence modeling asks how information in an ordered stream—such as words, sensor readings, user actions, or DNA—can be used to predict what comes next or interpret the sequence as a whole. Common approaches include recurrent networks such as LSTMs, Transformer attention, state-space models such as Mamba, and Markov or hidden Markov models; hybrids and diffusion methods are also used for long or structured sequences. Applications range from language and time-series forecasting to recommendation, biological analysis, and action recognition, with evaluation often testing prediction quality, long-range recall, and generalization to new lengths or domains. A central tension is balancing expressive memory and reliable long-context behavior against computation, latency, and memory costs, while ensuring benchmarks measure genuine sequence understanding rather than leakage or repetition.

Latest papers

CardsList

268 papers18 papers in the last four weeks, down 31% on the four weeks before. 0.1% of all new papers.

  1. Halting in Recurrent Sequence Models

    Nov 16, 2026Simon DrägerRecurrent Neural NetworksSequence Modeling

  2. Deep Sequence Model for Genome Wide Discovery of Coding and Regulatory Element Signatures

    Nov 15, 2026Rayhaneh Shabani Nia, Ali KarkehabadiGenomicsSequence Modeling

  3. FlexCast: Flexible Context Learning for Time Series Foundation Models

    Nov 13, 2026Zuyang Shen, Luqi Gong, Fanda Fan +6Time-Series Foundation ModelsTime Series Forecasting

  4. Riordan Arrays as Structured Operators for Artificial Intelligence

    Nov 11, 2026Dennis Davenport, Dewayne A. Dixon, Moussa DoumbiaSequence Modeling

  5. INTENT: Out-of-Sample, Out-of-Time, and Cold-Start Evaluation on User Event Sequences

    Nov 9, 2026Mattias Kvist, Erik Lidman Hillbom, Edoardo de Cal +3Sequential RecommendationRecommender Systems

  6. Implicit Bias in State Space Models and Linear Autoregressive Training

    Nov 6, 2026Gal Katzhendler, Gilad Yehudai, Gal VardiImplicit BiasState Space Models

  7. Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout

    Nov 5, 2026Tushaar Gangavarapu, Gil Tabak, Clemens JS SchaeferDelta-Rule Linear AttentionSequence Modeling

  8. MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene Regulation

    Nov 5, 2026Kangjie Zheng, Amirhossein Vahidi, Liying Jin +7GenomicsSingle-Cell Transcriptomics

  9. Control Foundation Models across Changing Block Diagrams: Generalizing Time-Series Prediction to Dynamic Graphs

    Nov 2, 2026Yuji Okamoto, Kenta Hoshino, Masaki InoueTime-Series Foundation ModelsNeural Network Control

  10. CoGSeq-LTV: Scalable Missing-Aware Graph-Sequence Modeling for Multi-Business Transaction Analytics

    Nov 1, 2026Ziyang Su, Yao Zhou, Kelin Liu +2Sequence Modeling

  11. When can Optimally Trained Transformers Achieve Near-Lossless Token Prediction for non-Markovian Data?

    Oct 29, 2026Kağan Akman, Jake Feldman Starosta, Naci Saldi +1Autoregressive TransformerSequence Modeling

  12. Observability-Aligned Evidential Masked Pretraining for Reliable VRU Motion Prediction

    Oct 29, 2026Shang Gao, Franz Götz-Hahn, Konrad Doll +1Uncertainty QuantificationMasked Autoencoders

  13. DES-JEPA: Learning a Shared Vocabulary for High-Dimensional Discrete Event Sequences

    Oct 28, 2026Hugo Math, Maximilian Forstenhäusler, Christos AnagnostopoulosSequence ModelingJoint-Embedding Predictive Architecture

  14. GTFormer: A Syntax-Free Graph Network Alternative to Transformers for 8192×\times Length Extrapolation in Linear Time

    Oct 27, 2026Elisabeth FinkLong-Context ModelingSequence Modeling

  15. TRIDENT-Seq: Profile-Matched Prefix-Future Contrast for Label-Efficient Payment Risk Modeling

    Oct 27, 2026Weiyu Han, Haoyu Jiang, Jie Sheng +7Financial Fraud DetectionContrastive Learning

  16. LEAP: a Latent Embedding Anomaly Patch-Transformer for time-series anomaly detection

    Oct 26, 2026Cristhian Moya-Mota, Ignacio Aguilera-Martos, Diego García-Gil +1Time-Series Anomaly DetectionUnsupervised Anomaly Detection

  17. Empirical Boundaries of Reservoir Computing for Few-Shot Sequence Pattern Tasks

    Oct 14, 2026Mario Mallea, Angela Nebot, Franscisco MugicaSequence-to-Sequence ModelsReservoir Computing

  18. Learning Source Structure: Bayesian Prediction with Transformers

    Oct 13, 2026Meir Feder, Ruediger UrbankeTransformerSequence Modeling

  19. The Language of Looking: Motion Tokens Reveal Domain-Dependent Local Structure in Gaze Sequences

    Oct 12, 2026Virmarie Maquiling, Enkelejda KasneciDomain GeneralizationSequence Modeling

  20. FON: A Draft-Revise Dual-Organ Language Model without Sequence-Level Quadratic Attention

    Oct 12, 2026Helong Hu, Hongdan Pan, Shuiqing HuLanguage ModelingSequence Modeling

  21. What DNA Foundation Models Learn Beyond Sequence Composition

    Oct 11, 2026Vincenzo Yuto Civale, Andrew David Bagdanov, Alberto MagiGenomic Foundation ModelsMolecular Foundation Models

  22. The RNN Homunculus: Learning to Gate Long-Term Memory

    Oct 9, 2026Zeyu Fan, Alexandru-Dragos Manolache, Jan van GemertLong-Range Dependency ModelingRecurrent Neural Networks

  23. Understanding Mamba-3 Through Oscillatory Dynamics

    Oct 9, 2026Shutian Liang, Yue SongSequence ModelingSelective SSMs

  24. Double-Take: Improving Capacity, Binding, and Selectivity In Long-Context Within Bidirectional Memory

    Oct 9, 2026Vakul Raghavan, Utkarsh Grover, Mingyang Mao +2Long-Context ModelingMemory-Augmented Neural Networks

  25. Time Delay System for Sequence Modeling

    Oct 9, 2026Youshan Zhang, Jialu LiSequence ModelingTemporal Attention

  26. TraceRelay: Attention-Aligned Recurrence over Rolling Traces

    Oct 8, 2026Sungwoo Goo, Hwi-yeol Yun, Sangkeun JungSequence ModelingPersistent Memory for Language Models