Transformers can solve in-context change-point detection with model size scaling by knowledge of the shift timing, matching optimal baselines on synthetic data and improving pretrained models on disease and financial forecasting.
Gating is weighting: Understanding gated linear attention through in-context learning, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
In-Context Learning Under Regime Change
Transformers can solve in-context change-point detection with model size scaling by knowledge of the shift timing, matching optimal baselines on synthetic data and improving pretrained models on disease and financial forecasting.