📄 Paper, code, and dataset are available here:
🔗 Paper: https://doi.org/10.1016/j.cma.2025.117785
🔗 GitHub Repository: https://github.com/eshaghi-ms/VINO
We extensively compared VINO with existing methods, and the results show superior performance—especially as mesh size increases, where our method remains highly reliable, unlike other approaches.
Additionally, we validated VINO on challenging problems, such as plates with arbitrary voids, further demonstrating its robustness.
Looking forward to discussions and feedback!
#AI #MachineLearning #ScientificMachineLearning #NeuralOperators #LeibnizUniversität #UniHannover
