% Key papers for Physics-inspired GNNs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2020_discovering_59712,
  title = {{Discovering Symbolic Models from Deep Learning with Inductive Biases}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18671},
}

@inproceedings{neurips2020_multipole_60373,
  title = {{Multipole Graph Neural Operator for Parametric Partial Differential Equations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17297},
}

@inproceedings{neurips2019_universal_59146,
  title = {{Universal Invariant and Equivariant Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13805},
}

@inproceedings{neurips2019_hyperbolic_58381,
  title = {{Hyperbolic Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13892},
}

@inproceedings{icml2019_circuit_37218,
  title = {{Circuit-GNN: Graph Neural Networks for Distributed Circuit Design}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4281},
}

@inproceedings{cvpr2018_surface_13628,
  title = {{Surface Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Kostrikov_Surface_Networks_CVPR_2018_paper.html},
}

@inproceedings{icml2020_continuous_38044,
  title = {{Continuous Graph Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6441},
}

@inproceedings{icml2023_reducing_42239,
  title = {{Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24515},
}

@inproceedings{neurips2022_neural_66313,
  title = {{Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54308},
}

@inproceedings{neurips2022_physics_64238,
  title = {{Physics-Embedded Neural Networks: Graph Neural PDE Solvers with Mixed Boundary Conditions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54479},
}

@inproceedings{icml2019_graph_37405,
  title = {{Graph Element Networks: adaptive, structured computation and memory}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3979},
}

@inproceedings{icml2022_learning_40779,
  title = {{Learning to Solve PDE-constrained Inverse Problems with Graph Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16565},
}

@inproceedings{neurips2022_on_63635,
  title = {{On the Robustness of Graph Neural Diffusion to Topology Perturbations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53396},
}

@inproceedings{neurips2022_unravelling_66223,
  title = {{Unravelling the Performance of Physics-informed Graph Neural Networks for Dynamical Systems}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55670},
}

@inproceedings{iclr2023_contranorm_32605,
  title = {{ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11036},
}

@inproceedings{iclr2022_towards_30804,
  title = {{Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6800},
}

@inproceedings{icml2022_graph_40639,
  title = {{Graph-Coupled Oscillator Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17241},
}

@inproceedings{iclr2023_learning_32372,
  title = {{Learning rigid dynamics with face interaction graph networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10983},
}

@inproceedings{icml2023_faenet_41959,
  title = {{FAENet: Frame Averaging Equivariant GNN for Materials Modeling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/23593},
}

@inproceedings{neurips2023_transfer_67441,
  title = {{Transfer learning for atomistic simulations using GNNs and kernel mean embeddings}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72292},
}

@inproceedings{iclr2024_graph_35252,
  title = {{Graph Neural Networks for Learning Equivariant Representations of Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17821},
}

@inproceedings{icml2024_neural_44338,
  title = {{Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34114},
}

@inproceedings{neurips2024_neural_73828,
  title = {{Neural P\$^3\$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93679},
}

@inproceedings{aaai2025_dynamics_8856,
  title = {{Dynamics-Based Feature Augmentation of Graph Neural Networks for Variant Emergence Prediction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34995},
}

@inproceedings{iclr2024_energy_35439,
  title = {{Energy-conserving equivariant GNN for elasticity of lattice architected metamaterials}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17634},
}

@inproceedings{icml2024_quantum_44026,
  title = {{Quantum Positional Encodings for Graph Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34426},
}

@inproceedings{icml2024_graph_44594,
  title = {{Graph Neural PDE Solvers with Conservation and Similarity-Equivariance}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33858},
}

@inproceedings{neurips2024_compositional_72752,
  title = {{Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94640},
}

@inproceedings{neurips2024_distributed_73574,
  title = {{Distributed-Order Fractional Graph Operating Network}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93910},
}

@inproceedings{neurips2025_universally_77526,
  title = {{Universally Invariant Learning in Equivariant GNNs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Uu7UGn5i2A},
}

@inproceedings{iclr2025_phympgn_82925,
  title = {{PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28878},
}

@inproceedings{iclr2026_rapid_84419,
  title = {{Rapid Training of Hamiltonian Graph Networks Using Random Features}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=2T4KxtDquV},
}

@inproceedings{aaai2026_pb4u_104112,
  title = {{Pb4U-GNet: Resolution-Adaptive Garment Simulation via Propagation-before-Update Graph Network}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37641},
}

@inproceedings{aaai2026_sheaf_106841,
  title = {{Sheaf Graph Neural Networks via PAC-Bayes Spectral Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39193},
}

@inproceedings{iclr2024_neural_33903,
  title = {{Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19172},
}

@inproceedings{iclr2024_unleashing_35587,
  title = {{Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17486},
}

@inproceedings{icml2024_predicting_43582,
  title = {{Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34870},
}

@inproceedings{icml2025_topology_46284,
  title = {{Topology-aware Neural Flux Prediction Guided by Physics}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46276},
}

@inproceedings{icml2025_graph_47461,
  title = {{Graph Adaptive Autoregressive Moving Average Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45132},
}

@inproceedings{icml2025_learning_47569,
  title = {{Learning the Electronic Hamiltonian of Large Atomic Structures}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45027},
}