An iERF-centric framework unifies local, global, and mechanistic interpretability in vision models via SRD for saliency, CAFE for concept anchoring, and ICAT for interlayer attribution.
Intriguing properties of neural networks
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
Hypernetwork-conditioned RL policies improve robustness to actuator failures in fixed-wing aircraft control and generalize to time-varying failure modes not seen during training.
citing papers explorer
-
From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models
An iERF-centric framework unifies local, global, and mechanistic interpretability in vision models via SRD for saliency, CAFE for concept anchoring, and ICAT for interlayer attribution.
-
Hypernetwork-Conditioned Reinforcement Learning for Robust Control of Fixed-Wing Aircraft under Actuator Failures
Hypernetwork-conditioned RL policies improve robustness to actuator failures in fixed-wing aircraft control and generalize to time-varying failure modes not seen during training.