Learning Aligned Stability in Neural ODEs Reconciling Accuracy with Robustness

ArXi:2509.21879v2 Announce Type: replace Despite Neural Ordinary Differential Equations (Neural ODEs) exhibiting intrinsic robustness, existing methods often impose Lyapuno stability for formal guarantees. However, these methods still face a fundamental accuracy-robustness trade-off, which stems from a core limitation: their applied stability conditions are rigid and inappropriate, creating a mismatch between the model's regions of attraction (RoAs) and its decision boundaries. To resolve this, we propose Zubo-Net, a novel framework that unifies dynamics and decision-making.