Pre-trained foundation models are making time-series forecasting more accessible and available, unlocking its benefits for smaller organizations with limited resources. Over the last year, we’ve seen ...
Recent advances in AI, such as foundation models, make it possible for smaller companies to build custom models to make predictions, reduce uncertainty, and gain business advantage. Time series ...
H2O.ai, the trusted Sovereign AI Platform with the software and expertise to run predictive, generative, and agentic AI in ...
What if you could predict the future—not just in abstract terms, but with actionable precision? From forecasting energy demand to anticipating retail trends, the ability to make accurate predictions ...
NVIDIA announced Kumo Forecast on October 21, 2026, an open multivariate time-series forecasting model that combines a pretrained MOMENT-1-large Transformer backbone with optional retrieval over ...
Official code and reproducibility suite for cross-channel dependency, predictive utility, and functional reliance in multivariate time-series forecasting. - dearyonghoon/rethinking-cross-channel ...
Mistral AI Releases Timestral: A 209M Forecasting Model Family That Outperforms Google’s TimesFM-3
Mistral Timestral is a time series foundation model family, 5M to 209M parameters, forecasting zero-shot on a CPU.
A new Gaussian process framework learns sparse, ordered dependency graphs from irregular electronic health records while ...
New research reveals that "foundation models" trained on vast, general time-series data may be able to forecast river flows accurately, even in regions with little or no local hydrological records.
I tested Sarashina3.2 mini thinking (hereinafter Sarashina3.2), released on October 29, 2026, by re-measuring official ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results