Research map / Probabilistic and scientific modeling / Molecules and proteins
Cormorant: Covariant Molecular Neural Networks
Brandon Anderson, Truong Son Hy, Risi Kondor
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Cormorant instead of competing approaches | MD-17 molecular energy prediction · MD-17 Aspirin | MAE (kcal/mol): 0.120 -> 0.098 | Improved |
| Use Cormorant instead of competing approaches | MD-17 molecular energy prediction · MD-17 Benzene | MAE (kcal/mol): 0.065 -> 0.023 | Improved |
| Use Cormorant instead of competing approaches | MD-17 molecular energy prediction · MD-17 Ethanol | MAE (kcal/mol): 0.050 -> 0.027 | Improved |
| Use Cormorant instead of competing approaches | MD-17 molecular energy prediction · MD-17 Malonaldehyde | MAE (kcal/mol): 0.080 -> 0.041 | Improved |
| Use Cormorant instead of competing approaches | MD-17 molecular energy prediction · MD-17 Naphthalene | MAE (kcal/mol): 0.095 -> 0.029 | Improved |
| Use Cormorant instead of competing approaches | MD-17 molecular energy prediction · MD-17 Salicylic Acid | MAE (kcal/mol): 0.106 -> 0.066 | Improved |
| Use Cormorant instead of competing approaches | MD-17 molecular energy prediction · MD-17 Toluene | MAE (kcal/mol): 0.085 -> 0.034 | Improved |
| Use Cormorant instead of competing approaches | MD-17 molecular energy prediction · MD-17 Uracil | MAE (kcal/mol): 0.085 -> 0.023 | Improved |
| Use Cormorant instead of the strongest listed baseline | QM9 molecular-property prediction · QM9 α | MAE (bohr^3): 0.092 -> 0.085 | Improved |
| Use Cormorant instead of the strongest listed baseline | QM9 molecular-property prediction · QM9 Δε | MAE (eV): 0.063 -> 0.061 | Improved |
| Use Cormorant instead of the strongest listed baseline | QM9 molecular-property prediction · QM9 εLUMO | MAE (eV): 0.034 -> 0.038 | Hurt |
| Use Cormorant instead of the strongest listed baseline | QM9 molecular-property prediction · QM9 R2 | MAE (bohr^2): 0.073 -> 0.961 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- SchNet — SchNet: A continuous-filter convolutional neural network for modeling quantum interactions (NeurIPS 2017) · better on 5 of 11 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing (NeurIPS 2024 · similarity 0.87)
- Efficient and Scalable Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity (ICML 2025 · similarity 0.87)
- Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systems (ICLR 2025 · similarity 0.86)
- Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks (ICLR 2024 · similarity 0.86)
- Learning the Electronic Hamiltonian of Large Atomic Structures (ICML 2025 · similarity 0.86)
- $\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
