Neural decompositionality is defined via decision-boundary semantic preservation, and language transformers largely satisfy it under SAVED while vision models often do not.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
diffRL enables verification of symbolic properties over input ranges for DRL agents in adaptive video streaming, wireless resource management, and congestion control by decomposing them into tractable sub-properties for existing DNN verifiers.
citing papers explorer
-
On the Decompositionality of Neural Networks
Neural decompositionality is defined via decision-boundary semantic preservation, and language transformers largely satisfy it under SAVED while vision models often do not.
-
Analyzing Symbolic Properties for DRL Agents in Systems and Networking
diffRL enables verification of symbolic properties over input ranges for DRL agents in adaptive video streaming, wireless resource management, and congestion control by decomposing them into tractable sub-properties for existing DNN verifiers.