# BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models

arXiv: https://arxiv.org/abs/2505.17871 · HTML: https://mlsanity.com/paper/2505.17871/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 44 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [Monash Time Series Forecasting Archive](https://mlsanity.com/paper/2105.06643/) (2021)
- [Timer: Generative Pre-trained Transformers Are Large Time Series Models](https://mlsanity.com/paper/2402.02368/) (2024)
- [ForecastPFN: Synthetically-Trained Zero-Shot Forecasting](https://mlsanity.com/paper/2311.01933/) (2023)
- [TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment](https://mlsanity.com/paper/2406.01638/) (2024)
- [ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data](https://mlsanity.com/paper/2412.11376/) (2024)
- [Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts](https://mlsanity.com/paper/2410.10469/) (2024)
- [VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2408.17253/) (2024)
- [Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer](https://mlsanity.com/paper/2405.17478/) (2024)
- [Balanced Data Sampling for Language Model Training with Clustering](https://mlsanity.com/paper/2402.14526/) (2024)
- [Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation](https://mlsanity.com/paper/2505.02138/) (2025)
- [Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting](https://mlsanity.com/paper/2401.11929/) (2024)

## Built on by (most cited first, 16 of 16)

- [TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding](https://mlsanity.com/paper/2509.19406/) (2025)
- [Distilling Time Series Foundation Models for Efficient Forecasting](https://mlsanity.com/paper/2601.12785/) (2026)
- [ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecasting](https://mlsanity.com/paper/2510.09734/) (2025)
- [Selective Learning for Deep Time Series Forecasting](https://mlsanity.com/paper/2510.25207/) (2025)
- [TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning](https://mlsanity.com/paper/2605.00015/) (2026)
- [Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Models](https://mlsanity.com/paper/2601.12083/) (2026)
- [CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2601.20318/) (2026)
- [Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis](https://mlsanity.com/paper/2607.01918/) (2026)
- [ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecasting](https://mlsanity.com/paper/2509.06060/) (2025)
- [APT: Affine Prototype-Timestamp For Time Series Forecasting Under Distribution Shift](https://mlsanity.com/paper/2511.12945/) (2025)
- [Tabby: An Open Pretraining Recipe for Time Series Foundation Models](https://mlsanity.com/paper/2609.13956/) (2026)
- [Integrating Time Series into LLMs via Multi-layer Steerable Embedding Fusion for Enhanced Forecasting](https://mlsanity.com/paper/2508.16059/) (2025)
- [KAIROS: Unified Training for Universal Non-Autoregressive Time Series Forecasting](https://mlsanity.com/paper/2510.02084/) (2025)
- [Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy Denoising](https://mlsanity.com/paper/2510.05589/) (2025)
- [Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Training](https://mlsanity.com/paper/2602.19113/) (2026)
- [QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization](https://mlsanity.com/paper/2609.20156/) (2026)

## Abstract (arXiv)

The advent of universal time series forecasting models has revolutionized zero-shot forecasting across diverse domains, yet the critical role of data diversity in training these models remains underexplored. Existing large-scale time series datasets often suffer from inherent biases and imbalanced distributions, leading to suboptimal model performance and generalization. To address this gap, we introduce BLAST, a novel pre-training corpus designed to enhance data diversity through a balanced sampling strategy. First, BLAST incorporates 321 billion observations from publicly available datasets and employs a comprehensive suite of statistical metrics to characterize time series patterns. Then, to facilitate pattern-oriented sampling, the data is implicitly clustered using grid-based partitioning. Furthermore, by integrating grid sampling and grid mixup techniques, BLAST ensures a balanced and representative coverage of diverse patterns. Experimental results demonstrate that models pre-trained on BLAST achieve state-of-the-art performance with a fraction of the computational resources and training tokens required by existing methods. Our findings highlight the pivotal role of data diversity in improving both training efficiency and model performance for the universal forecasting task.