RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models

• URL: http://arxiv.org/abs/2607.06504v1
• Date: Tue, 07 Jul 2026 17:04:44 GMT
• Title: RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models
• Abstract summary: We establish a large-scale, high-quality, real-world, and multivariate time series archive that contains around 200 datasets and 142 billion time points.<n> Experimental results show that incorporating real-world multivariate data predominantly improves the generalization performance.
• Score: 11.251202834387682
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent years have witnessed the emergence of multivariate modeling using time series foundation models (TSFMs), which achieve advanced zero-shot generalization. Modern multivariate TSFMs are predominantly pretrained on multivariate synthetic data, which is easier to scale but may fail to capture the complex temporal dynamics and cross-variable relationships present in real-world time series. This raises a key question: Whether and to what extent the leading TSFMs trained with the real-world corpus perform better than those trained with synthetic data? To answer this, we establish the RMISC corpus, a considerably large-scale, high-quality, openly accessible, real-world, and multivariate time series archive that contains around 200 datasets and 142 billion time points across diverse domains. Furthermore, we pretrain four advanced TSFMs on univariate, synthetic multivariate, and real-world multivariate data and evaluate their zero-shot generalization capabilities on standard in-distribution and out-of-distribution benchmarks. Experimental results show that incorporating real-world multivariate data predominantly improves the generalization performance for both univariate and multivariate TSFMs. These results provide a deeper understanding of how real-world multivariate data contributes to the development of stronger TSFMs.

Related papers

• FreSH: Frequency-Segmented Hierarchical Multi-Expert Framework for Multivariate Time Series Classification [15.396551583872009]
  We present FreSH, a Frequency-Segmented Hierarchical Multi-Expert Framework designed to address these challenges.<n>FreSH introduces a new perspective for MTSC by enabling adaptive, multi-scale analysis of temporal signals.<n>It consistently outperforms state-of-the-art methods in classification accuracy, while substantially reducing model size and efficiency.
  arXiv  Detail & Related papers  (2026-08-08T16:05:17Z)
• MULTISEISMO: A Multimodal Seismic Dataset and Model for Cross-Modal Seismic Understanding [1.0407464689506312]
  In seismology, understanding earthquake phenomena requires the synthesis of timeseries waveform data, geographical imagery, and contextual metadata.<n>We present MultiSeismo, a large scale structured multimodal dataset spanning over 16K seismic events spanning 13 years (2010 to 2023) across diverse geographical regions.<n>Each event data integrates waveform recordings from global station networks, intensity maps, population exposure visualizations, and a comprehensive textual format.<n>We leverage finetune an existing multimodal model (Unified IO 2) enhanced with a specialized timeseries encoder, which yields SeisModal, the first domain specific multimodal model for comprehensive seismic analysis.
  arXiv  Detail & Related papers  (2026-05-25T20:35:48Z)
• Universal Redundancies in Time Series Foundation Models [3.8551402560229806]
  Time Series Foundation Models (TSFMs) leverage extensive pretraining to accurately predict unseen time series during inference.<n>We introduce a set of tools for mechanistic interpretability of TSFMs, including ablations of specific components and direct logit attribution on the residual stream.
  arXiv  Detail & Related papers  (2026-02-02T03:53:46Z)
• UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting [90.47915032778366]
  We propose UniDiff, a unified diffusion framework for multimodal time series forecasting.<n>At its core lies a unified and parallel fusion module, where a single cross-attention mechanism integrates structural information from timestamps and semantic context from texts.<n>Experiments on real-world benchmark datasets across eight domains demonstrate that the proposed UniDiff model achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-08T05:36:14Z)
• Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Models [50.877082340479085]
  We study how different Time Series Foundational Models (TSFMs) exhibit specialized performance profiles across various forecasting settings.<n>We propose Synapse, a novel arbitration framework for TSFMs.<n>Results demonstrate that Synapse consistently outperforms other popular ensembling techniques as well as individual TSFMs.
  arXiv  Detail & Related papers  (2025-11-07T18:01:51Z)
• Chronos-2: From Univariate to Universal Forecasting [52.753731922908905]
  Chronos-2 is a pretrained model capable of handling univariate, multivariate, and covariate-informed forecasting tasks in a zero-shot manner.<n>It delivers state-of-the-art performance across three comprehensive benchmarks: fev-bench, GIFT-Eval, and Chronos Benchmark II.<n>The in-context learning capabilities of Chronos-2 establish it as a general-purpose forecasting model that can be used "as is" in real-world forecasting pipelines.
  arXiv  Detail & Related papers  (2025-10-17T17:00:53Z)
• MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification [18.142252811096643]
  We propose a novel Multiscale Periodic Time Series Network (MPTSNet)<n>MPTSNet integrates multiscale local patterns and global correlations to fully exploit the inherent information in time series.<n>The experiments on UEA benchmark datasets demonstrate that the proposed MPTSNet outperforms 21 existing advanced baselines in the MTSC tasks.
  arXiv  Detail & Related papers  (2025-03-07T17:07:51Z)
• mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data [71.352883755806]
  Multimodal embedding models have gained significant attention for their ability to map data from different modalities, such as text and images, into a unified representation space.<n>However, the limited labeled multimodal data often hinders embedding performance.<n>Recent approaches have leveraged data synthesis to address this problem, yet the quality of synthetic data remains a critical bottleneck.
  arXiv  Detail & Related papers  (2025-02-12T15:03:33Z)
• TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting [35.505530132151]
  Time Series Forecasting (TSF) is key functionality in numerous fields, such as financial investment, weather services, and energy management.<n>Many TSF methods require domain-specific data collection and model training and do not generalize well when applied in other domains.<n>Time Series Foundation Models (TSFMs) that are pre-trained on massive heterogeneous time series data aim to overcome these limitations.
  arXiv  Detail & Related papers  (2024-10-15T17:23:49Z)
• MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild [81.32127423981426]
  Multimodal emotion recognition based on audio and video data is important for real-world applications. Recent methods have focused on exploiting advances of self-supervised learning (SSL) for pre-training of strong multimodal encoders. We propose a different perspective on the problem and investigate the advancement of multimodal DFER performance by adapting SSL-pre-trained disjoint unimodal encoders.
  arXiv  Detail & Related papers  (2024-04-13T13:39:26Z)
• Multi-scale Attention Flow for Probabilistic Time Series Forecasting [68.20798558048678]
  We propose a novel non-autoregressive deep learning model, called Multi-scale Attention Normalizing Flow(MANF) Our model avoids the influence of cumulative error and does not increase the time complexity. Our model achieves state-of-the-art performance on many popular multivariate datasets.
  arXiv  Detail & Related papers  (2022-05-16T07:53:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.