nextbigthing.my

Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling

Tech Business·2 min read·via ArXivOriginal source →

Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling

arXiv:2603.04791v1 Announce Type: new Abstract: We introduce Timer-S1, a strong Mixture-of-Experts (MoE) time series foundation model with 8.3B total parameters, 0.75B activated parameters for each token, and a context length of 11.5K. To overcome the scalability bottleneck in existing pre-trained time series foundation models, we perform Serial Scaling in three dimensions: model architecture, dataset, and training pipeline. Timer-S1 integrates sparse TimeMoE blocks and generic TimeSTP blocks f

More Stories

The Worst Acquisition in History, Again

The Worst Acquisition in History, Again

3 min read
TSA leaves passenger needing surgery after illegally forcing her through scanner

TSA leaves passenger needing surgery after illegally forcing her through scanner

2 min read
Show HN: Reconstruct any image using primitive shapes, runs in-browser via WASM

Show HN: Reconstruct any image using primitive shapes, runs in-browser via WASM

2 min read
How Cursor is evolving through its Composer coding models built on Chinese open models, as coding agents like Claude Code threaten to make code editors obsolete

How Cursor is evolving through its Composer coding models built on Chinese open models, as coding agents like Claude Code threaten to make code editors obsolete

3 min read