arXiv Machine Learning
Learning Graph Energies for Finite-Time Generation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 2
Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation
arXiv:2603. 23398v3 Announce Type: replace-cross Abstract: Generative modeling of discrete data, such as graphs, underpins many scientific and industrial applications, including molecular discovery and materials design.
arXiv Machine Learning
Jul 20
Neural Non-Equilibrium Hamiltonian Monte Carlo for Corrected Boltzmann Sampling
arXiv:2607. 15682v1 Announce Type: new Abstract: Sampling from an unnormalized Boltzmann density requires proposals that move probability mass globally while retaining enough path-probability information for statistical correction.
arXiv Machine Learning
Aug 4
Sampling Decisions: Exact Path-Space Control for Physics-Informed Generative Sampling
arXiv:2503. 14549v4 Announce Type: replace Abstract: Scientific generative models must turn tractable local decisions into globally correlated samples that respect physical constraints.
arXiv AI
Jul 28
Sampling Decisions: Exact Path-Space Correction, Prior Cancellation and Local-Boltzmann Guidance
arXiv:2503. 14549v3 Announce Type: replace-cross Abstract: How can a cheap but biased sequential, finite-horizon sampler over a discrete space be corrected so that its terminal output follows a prescribed Gibbs distribution?
arXiv Machine Learning
Oct 8
Physics-Aligned Electronic Ground-State Learning Improves Generalization
The paper introduces Physics‑Aligned Electronic Ground‑State Models (GSMs) that sit between machine‑learned interatomic potentials and Kohn‑Sham density functional theory in terms of computational cost and accuracy. By aligning GSM learning objectives with KS‑DFT equations and enforcing physical constraints, the authors develop new training techniques—OrthoNormal‑Loss (ON‑Loss), Grassmann Restricted Occupied‑Orbital Training (GROOT), and Residual Optimal‑gauge Conditioning‑aware KS‑Eq. Training (ROCKET)—which dramatically reduce energy and force errors in size‑extrapolation tests from QM9 to QM40. The models also achieve near‑chemical‑accuracy predictions on reactive chemistry benchmarks and demonstrate efficient label‑free self‑consistency fine‑tuning. whyItMatters":"The work advances the cost‑accuracy frontier for electronic structure predictions, enabling more reliable out‑of‑distribution generalization in drug and material discovery."
Hugging Face Trending Papers
Oct 7
Physics-Aligned Electronic Ground-State Learning Improves Generalization
Machine-learned interatomic potentials (MLIPs) excel at in-distribution tasks, accelerating drug and material development, yet they struggle to generalize out-of-distribution. We propose to push the c...