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

TL;DR

TimeTok introduces a hierarchical tokenization framework for controllable time-series generation at any temporal granularity, enabling flexible, user-driven synthesis and transferability across datasets.

Contribution

The paper presents the first unified hierarchical tokenization approach for controllable and transferable time-series generation across multiple granularities.

Findings

TimeTok achieves state-of-the-art performance in granularity-controllable generation.

It can generate time series at any specified level of detail from coarse inputs or from scratch.

TimeTok demonstrates strong transferability across datasets with different temporal granularities.

Abstract

Time-series generative models often lack control over temporal granularity, forcing users to accept whatever granularity the model produces. To enable truly user-driven generation, 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 from scratch. 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 - including standard generation - 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.