Standard attention collapses on additively mixed signals because it is memoryless with respect to explained evidence, but adding multiplicative depletion with an attention bias prevents collapse and enables multi-source inference.
Advances in Neural Information Processing Systems , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A decoupling strategy optimizes object slots for holistic class identity during training and composes them at inference to achieve better generalization to unseen concepts in continual few-shot settings.
citing papers explorer
-
When Attention Collapses: Residual Evidence Modeling for Compositional Inference
Standard attention collapses on additively mixed signals because it is memoryless with respect to explained evidence, but adding multiplicative depletion with an attention bias prevents collapse and enables multi-source inference.
-
Unlocking Compositional Generalization in Continual Few-Shot Learning
A decoupling strategy optimizes object slots for holistic class identity during training and composes them at inference to achieve better generalization to unseen concepts in continual few-shot settings.