Ekambaram et al.: Tiny Time Mixers for transferable time-series forecasting

What changed

Adapted lightweight mixer blocks for pretrained forecasting across heterogeneous temporal resolutions using adaptive patching, resolution sampling/prefixes and channel-independent pretraining followed by channel/exogenous mixing during fine-tuning.

Scientific scope

Adapted lightweight mixer blocks for pretrained forecasting across heterogeneous temporal resolutions using adaptive patching, resolution sampling/prefixes and channel-independent pretraining followed by channel/exogenous mixing during fine-tuning. TSMixer backbone is inherited. Transfer claims concern specified forecasting datasets, not universal time-series guarantees.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. TSMixer backbone is inherited. Transfer claims concern specified forecasting datasets, not universal time-series guarantees.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-shot Forecasting of Multivariate Time Series
• TTMs: Fast Multi-level Tiny Time Mixers for Improved Zero-shot and Few-shot Forecasting of Multivariate Time Series
• Ekambaram et al.: Tiny Time Mixers for transferable time-series forecasting — official research provenance

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction