OpenPrint 20261116.0001v1MethodReleased: November 16, 2026

RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility

Haoyu He|Haozheng Luo|Yan Chen|Qi R. Wang
Read Full Paper (PDF)
NeurIPS
Reviewed by NeurIPS Agent
Refs Verified (79/82)
Claims Verified

Abstract

Predicting human mobility is inherently challenging due to complex long-range dependencies and multi-scale periodic behaviors. To address this, we introduce RHYTHM (Reasoning with Hierarchical Temporal Tokenization for Human Mobility), a unified framework that leverages large language models (LLMs) as general-purpose spatio-temporal predictors and trajectory reasoners. Methodologically, RHYTHM employs temporal tokenization to partition each trajectory into daily segments and encode them as discrete tokens with hierarchical attention that captures both daily and weekly dependencies, thereby significantly reducing the sequence length while preserving cyclical information. Additionally, we enrich token representations by adding pre-computed prompt embeddings for trajectory segments and prediction targets via a frozen LLM, and feeding these combined embeddings back into the LLM backbone to capture complex interdependencies. Computationally, RHYTHM freezes the pretrained LLM's backbone to reduce attention complexity and memory cost. We evaluate our model against state-of-the-art methods using three real-world datasets. Notably, RHYTHM achieves a 2.4% improvement in overall accuracy, a 5.0% increase on weekends, and a 24.6% reduction in training time. Code is publicly available at https://github.com/he-h/rhythm.

Keywords

human mobilitytemporal tokenizationhierarchical attentiontrajectory predictionlarge language modelsprompt embeddingsfrozen pretrained LLM

Illustration

Illustration 1/3

Citation

@article{He2026RHYTHM,
  title={RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility},
  author={Haoyu He and Haozheng Luo and Yan Chen and Qi R. Wang},
  year={2026},
  url={https://cspaper.org/openprint/20261116.0001v1},
  journal={OpenPrint:20261116.0001v1}
}

Version History

VersionReleased DateSubmitter
v1Current
Nov 16, 2026
Robin Luo
RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility | OpenPrint 20261116.0001v1 — CSPaper