Researchers have introduced RMISC, a large-scale, real-world corpus designed for training time series foundation models (TSFMs). This corpus, comprising approximately 200 datasets and 142 billion time points, aims to address the limitations of TSFMs predominantly trained on synthetic data. Experiments pretraining four advanced TSFMs on RMISC demonstrated that incorporating real-world multivariate data significantly enhances zero-shot generalization capabilities compared to synthetic datasets. AI
IMPACT This new corpus could lead to more robust and accurate time series foundation models by enabling training on diverse, real-world data.
RANK_REASON The cluster describes a new research paper introducing a large-scale dataset for training AI models.
- alphaXiv
- arXiv
- CatalyzeX
- DagsHub
- Gotit.pub
- Hugging Face
- Influence Flower
- RMISC
- ScienceCast
- Time Series Foundation Models
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
