Subtracting the action-marginal mean from a world model's action-conditioned predictions yields a vector action channel that exactly cancels common-mode distraction and works post hoc on frozen predictors.
Proceedings of the 33rd International Conference on Machine Learning (ICML) , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dueling World Models: Advantage-Style Action Channels for Common-Mode Distractor Rejection
Subtracting the action-marginal mean from a world model's action-conditioned predictions yields a vector action channel that exactly cancels common-mode distraction and works post hoc on frozen predictors.