What Should World Models Forget? Stratified Retention for Continual Adaptation
[Uczenie maszynowe] Autorzy: Nishit Anand, Ramani Duraiswami, Dinesh Manocha
Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary prediction target, where a correct label remains correct indefinitely. World models do not satisfy this condition. Their prediction target is the environment, which changes, so knowledge that was accurate when acquired may later become false, and discarding it is required behavior rather than a defect. Non-stationary ground truth is well studied in the concept drift literature and in the temporal factuality of language models, but has not been formulated for world models, which are distinctive in that they also encode knowledge that must never be revised. We argue that continual world models require retention stratified by invariance timescale, separating invariants such as physics and object permanence, which must never be revised, from instance-l…
- Kategoria arxiv
- cs.LG
- Kategoria
- Uczenie maszynowe