Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
LLMs outperform specialized TSFMs and regression baselines in intervention-aware time series forecasting, yet all models exhibit a stark performance degradation when predicting responses to novel, unseen covariate futures.
Static train-test splits are out: Impermanent offers a live, continuously updating benchmark to truly test temporal generalization in time series forecasting.
Matching open-source projects to the right foundation can be quantitatively determined using sociotechnical profiles, unlocking better sustainability outcomes.