# T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models

arXiv: https://arxiv.org/abs/2505.02417 · HTML: https://mlsanity.com/paper/2505.02417/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 32 of its 43 references that are in the map.
- First posted on arXiv 5 May 2025.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 30 of 32)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning](https://mlsanity.com/paper/2311.10709/) (2023)
- [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024)
- [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021)
- [Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers](https://mlsanity.com/paper/2405.05945/) (2024)
- [Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis](https://mlsanity.com/paper/2310.06119/) (2023)
- [VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2408.17253/) (2024)
- [Context is Key: A Benchmark for Forecasting with Essential Textual Information](https://mlsanity.com/paper/2410.18959/) (2024)
- [DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Models](https://mlsanity.com/paper/2301.13629/) (2023)
- [Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting](https://mlsanity.com/paper/2306.11025/) (2023)
- [A Survey on Diffusion Models for Time Series and Spatio-Temporal Data](https://mlsanity.com/paper/2404.18886/) (2024)
- [Vector Quantized Time Series Generation with a Bidirectional Prior Model](https://mlsanity.com/paper/2303.04743/) (2023)
- [Time Weaver: A Conditional Time Series Generation Model](https://mlsanity.com/paper/2403.02682/) (2024)
- [Towards Time Series Reasoning with LLMs](https://mlsanity.com/paper/2409.11376/) (2024)
- [Diffusion-based Conditional ECG Generation with Structured State Space Models](https://mlsanity.com/paper/2301.08227/) (2023)
- [TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model](https://mlsanity.com/paper/2409.02322/) (2024)
- [DiffuSETS: 12-lead ECG Generation Conditioned on Clinical Text Reports and Patient-Specific Information](https://mlsanity.com/paper/2501.05932/) (2025)
- [AstroM3: A self-supervised multimodal model for astronomy](https://mlsanity.com/paper/2411.08842/) (2024)
- [CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision](https://mlsanity.com/paper/2411.08397/) (2024)

## Built on by (most cited first, 20 of 20)

- [SciTS: Scientific Time Series Understanding and Generation with LLMs](https://mlsanity.com/paper/2510.03255/) (2025)
- [Overcoming the Modality Gap in Context-Aided Forecasting](https://mlsanity.com/paper/2603.12451/) (2026)
- [TimeSAF: Towards LLM-Guided Semantic Asynchronous Fusion for Time Series Forecasting](https://mlsanity.com/paper/2604.12648/) (2026)
- [EventTSF: Event-Aware Non-Stationary Time Series Forecasting](https://mlsanity.com/paper/2508.13434/) (2025)
- [Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations](https://mlsanity.com/paper/2601.13534/) (2026)
- [FaultDiffusion: Few-Shot Fault Time Series Generation with Diffusion Model](https://mlsanity.com/paper/2511.15174/) (2025)
- [UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting](https://mlsanity.com/paper/2512.07184/) (2025)
- [TF-CoDiT: Conditional Time Series Synthesis with Diffusion Transformers for Treasury Futures](https://mlsanity.com/paper/2601.11880/) (2026)
- [Spectral-Aware Text-to-Time Series Generation with Billion-Scale Multimodal Meteorological Data](https://mlsanity.com/paper/2603.27135/) (2026)
- [PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation](https://mlsanity.com/paper/2605.28867/) (2026)
- [Net-Ev2: A Generative Simulator for Network Event Evolution](https://mlsanity.com/paper/2606.12494/) (2026)
- [Parallel Complex Diffusion for Scalable Time Series Generation](https://mlsanity.com/paper/2602.17706/) (2026)
- [Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework](https://mlsanity.com/paper/2604.26762/) (2026)
- [UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation](https://mlsanity.com/paper/2606.10466/) (2026)
- [Represent, Then Generate: Multimodal-Conditioned Time-Series Generation under Irregular Missingness](https://mlsanity.com/paper/2608.12592/) (2026)
- [GALA: Generation-Aware Cross-Modal Alignment for Text-to-Time-Series Synthesis](https://mlsanity.com/paper/2608.13741/) (2026)
- [MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters](https://mlsanity.com/paper/2608.23473/) (2026)
- [CodeTS: Verifiable Text-to-Time Series Generation via Executable Code](https://mlsanity.com/paper/2609.15393/) (2026)
- [ShapeLex: Decoupling Local Shape Symbolization and Global Scale Modeling for Text-Controlled Time Series Generation](https://mlsanity.com/paper/2609.24003/) (2026)
- [LineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series Identification](https://mlsanity.com/paper/2610.01800/) (2026)

## Abstract (arXiv)

Text-to-Time Series generation holds significant potential to address challenges such as data sparsity, imbalance, and limited availability of multimodal time series datasets across domains. While diffusion models have achieved remarkable success in Text-to-X (e.g., vision and audio data) generation, their use in time series generation remains in its nascent stages. Existing approaches face two critical limitations: (1) the lack of systematic exploration of general-proposed time series captions, which are often domain-specific and struggle with generalization; and (2) the inability to generate time series of arbitrary lengths, limiting their applicability to real-world scenarios. In this work, we first categorize time series captions into three levels: point-level, fragment-level, and instance-level. Additionally, we introduce a new fragment-level dataset containing over 600,000 high-resolution time series-text pairs. Second, we propose Text-to-Series (T2S), a diffusion-based framework that bridges the gap between natural language and time series in a domain-agnostic manner. T2S employs a length-adaptive variational autoencoder to encode time series of varying lengths into consistent latent embeddings. On top of that, T2S effectively aligns textual representations with latent embeddings by utilizing Flow Matching and employing Diffusion Transformer as the denoiser. We train T2S in an interleaved paradigm across multiple lengths, allowing it to generate sequences of any desired length. Extensive evaluations demonstrate that T2S achieves state-of-the-art performance across 13 datasets spanning 12 domains.