NTU's PACT Adapts Time-Series Foundation Models Without Forgetting Old Conditions

NanyangTechnologicalUniversity · hf · 2026-11-19

Researchers from NTU, ASTAR, and Khalifa University propose PACT (Piecewise Adaptation via Chart Transport) for adapting pretrained time-series foundation models to new operating conditions. Key insight: embedding spaces shift non-uniformly under condition drift, so global adaptation unnecessarily moves already-correct embeddings. PACT partitions the frozen embedding space into local charts and learns gated residual transports, achieving high macro-F1 with limited labeled calibration data and no condition identity at test time.

Original post →

More from Research

Research channel →