# TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

arXiv: https://arxiv.org/abs/2605.01418 · HTML: https://mlsanity.com/paper/2605.01418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 2 May 2026.

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

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Professor Forcing: A New Algorithm for Training Recurrent Networks](https://mlsanity.com/paper/1610.09038/) (2016)
- [Timer: Generative Pre-trained Transformers Are Large Time Series Models](https://mlsanity.com/paper/2402.02368/) (2024)
- [Chronos-2: From Univariate to Universal Forecasting](https://mlsanity.com/paper/2510.15821/) (2025)
- [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024)
- [FlexTok: Resampling Images into 1D Token Sequences of Flexible Length](https://mlsanity.com/paper/2502.13967/) (2025)
- [FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching](https://mlsanity.com/paper/2412.15205/) (2024)
- [Vector Quantized Time Series Generation with a Bidirectional Prior Model](https://mlsanity.com/paper/2303.04743/) (2023)
- [Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series](https://mlsanity.com/paper/2410.19538/) (2024)
- [TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis](https://mlsanity.com/paper/2402.16412/) (2024)
- [MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process](https://mlsanity.com/paper/2403.05751/) (2024)
- [Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization](https://mlsanity.com/paper/2412.05244/) (2024)
- [TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts](https://mlsanity.com/paper/2501.05403/) (2025)
- [Population Aware Diffusion for Time Series Generation](https://mlsanity.com/paper/2501.00910/) (2025)
- [Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach](https://mlsanity.com/paper/2505.20446/) (2025)
- [Learning Soft Sparse Shapes for Efficient Time-Series Classification](https://mlsanity.com/paper/2505.06892/) (2025)
- [DeepVol: Volatility Forecasting from High-Frequency Data with Dilated Causal Convolutions](https://mlsanity.com/paper/2210.04797/) (2022)
- [Diffusion Transformers for Tabular Data Time Series Generation](https://mlsanity.com/paper/2504.07566/) (2025)
- [TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph Perspective](https://mlsanity.com/paper/2511.12174/) (2025)
- [TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation](https://mlsanity.com/paper/2505.09955/) (2025)

## Abstract (arXiv)

Time-series data are inherently multiscale, spanning diverse temporal granularities from coarse trends to fine-scale dynamics. However, existing time-series generative models provide limited control over the temporal granularity of both inputs and outputs, restricting their ability to condition on user-provided coarse sketches and generate samples at a desired target granularity. To address this, we introduce TimeTok, a unified framework for Granularity-Controllable Time-Series Generation (GC-TSG), which generates time series at any target granularity from any coarser input (e.g., rough sketches) or without conditioning. At the core of TimeTok is a hierarchical tokenization strategy that maps time series into an ordered sequence of tokens, from coarse to fine temporal granularity. Our autoregressive generation process operates across these granularity levels, producing token blocks that are decoded back into continuous time series. This design naturally enables GC-TSG within a single framework, where controlling the number of token blocks provides explicit control over output detail. Experiments show that TimeTok excels at GC-TSG tasks while achieving state-of-the-art performance in standard generation. Furthermore, we showcase TimeTok's potential as a foundational tokenizer by training on multiple datasets with heterogeneous temporal granularities, verifying strong transferability that consistently outperforms models trained on individual datasets. To our knowledge, this is the first unified framework that covers the full generative spectrum for time series, offering a valuable foundation for models that benefit from diverse temporal granularities.