FaVeX accelerates verified explanations for neural networks via dynamic batch-sequential processing and query reuse while introducing verifier-optimal robust explanations that incorporate verifier incompleteness.
In: Majumdar, R., Kuncak, V
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Physical admissibility is defined as a prediction-control interface using kinematic, dynamic, and composed-horizon conditions to reject invalid dynamics proposals, with AUC 0.957 on LeRobot PushT and 87-89% prevention of invalid actions in interventions.
An experience report from Heriot-Watt's LAIV lab on successes and language-related difficulties when incorporating neural network verification into AI MSc programs.
citing papers explorer
-
Faster Verified Explanations for Neural Networks
FaVeX accelerates verified explanations for neural networks via dynamic batch-sequential processing and query reuse while introducing verifier-optimal robust explanations that incorporate verifier incompleteness.
-
Can Predicted Dynamics Exist in the Physical World?
Physical admissibility is defined as a prediction-control interface using kinematic, dynamic, and composed-horizon conditions to reject invalid dynamics proposals, with AUC 0.957 on LeRobot PushT and 87-89% prevention of invalid actions in interventions.
-
Neural Network Verification for the Masses (of AI graduates)
An experience report from Heriot-Watt's LAIV lab on successes and language-related difficulties when incorporating neural network verification into AI MSc programs.