The paper argues that imitation learning generalization is governed by representation compression and encoder-data dependence, and that high conditional entropy in actions tightens the bound, but the key new bound is asserted without proof.
Correlation information bottleneck: Towards adapting pretrained multimodal models for robust visual question answering
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generalization Capability for Imitation Learning
The paper argues that imitation learning generalization is governed by representation compression and encoder-data dependence, and that high conditional entropy in actions tightens the bound, but the key new bound is asserted without proof.