AI RESEARCH
An Invariant Compiler for Neural ODEs in AI-Accelerated Scientific Simulation
arXiv CS.LG
•
ArXi:2603.23861v1 Announce Type: new Neural ODEs are increasingly used as continuous-time models for scientific and sensor data, but unconstrained neural ODEs can drift and violate domain invariants (e.g., conservation laws), yielding physically implausible solutions. In turn, this can compound error in long-horizon prediction and surrogate simulation. Existing solutions typically aim to enforce invariance by soft penalties or other forms of regularization, which can reduce overall error but do not guarantee that trajectories will not leave the constraint manifold. We.