BranchIP: Learning Adaptive Equivariant Computation for Interatomic Potentials
cs.LG, physics.app-ph, physics.chem-ph, physics.comp-ph
Submitted: 2026-10-01
Updated: 2026-10-01
Sources
- ADMP-GNN: Adaptive Depth Message Passing GNN
- An Efficient Sparse Kernel Generator for O(3)-Equivariant Deep Networks
- Six Open Questions in Machine-Learned Interatomic Potential Foundation Models
- Early-Exit Graph Neural Networks
- Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials
- Training Compute-Optimal Large Language Models
- Scaling Laws for Neural Language Models
- Fast and Accurate Foundation Models for Equivariant Machine-Learned Interatomic Potentials
- Scaling Machine Learning Interatomic Potentials with Mixtures of Experts
- Mixture of Experts Framework in Machine Learning Interatomic Potentials for Atomistic Simulations
- Surface roughening in nanoparticle catalysts
- Revealing the proton slingshot mechanism in solid acid electrolytes through machine learning molecular dynamics
- UMA: A Family of Universal Models for Atoms
- DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks