The paper introduces a graph-recurrent neural network (GRNN) that learns emergent collective dynamics directly from trajectory data, without requiring explicit microscopic equations of motion. The GRNN combines gated recurrent memory with graph message passing, allowing local hidden states to capture information beyond instantaneous observables and to propagate spatially. The authors validate the approach on the semiclassical Holstein model, successfully reproducing temporal and spatial correlations and dynamical scaling during domain coarsening of charge-density-wave order.
arXiv:2609.37392v1 Announce Type: new Abstract: Modeling the temporal evolution of macroscopic properties of complex systems is an important scientific task. To predict this evolution without full mi...
The paper introduces a physics-inspired neural framework that combines graph neural networks with statistical‑mechanics principles to solve large‑scale graph coloring problems. By using a planting‑based supervised signal, symmetry‑breaking regularization, and iterative noise‑annealed neural dynamics, the model navigates complex solution landscapes and scales quadratically with graph size. It generalizes from small training graphs to instances up to 20 times larger, demonstrating that neural architectures can learn scalable algorithmic strategies effective in hard connectivity regions.
arXiv:2607. 10285v1 Announce Type: new Abstract: We study how unsupervised autoencoders trained on microscopic spin configurations from the Ising model learn macroscopic, theory-relevant variables underlying the data-generating process.
The paper investigates whether machine learning models can uncover physical patterns in atomistic data without relying on traditional physics-based inductive biases such as geometric locality or graph structures. By training a general-purpose architecture on molecular simulation data, the authors demonstrate that the model autonomously learns interatomic interaction strengths resembling classical electrostatics and identifies interaction cutoffs aligned with established physical models. The study also reports predictable neural scaling behavior and competitive accuracy on certain metrics compared to physics-informed architectures, suggesting that explicit priors may only be necessary when empirically justified.
arXiv:2607. 28537v1 Announce Type: cross Abstract: Metallic magnets exhibit complex spin dynamics governed by electronically generated interactions.
arXiv:2607. 29158v1 Announce Type: cross Abstract: We introduce implicit machine learning force fields (I-MLFFs), which replace explicit stacks of neural network layers with self-consistent fixed-point equations.
TetrisCNN is a convolutional neural network that uses parallel branches of differently shaped filters to learn sparse, interpretable latent representations directly from spin correlators. Applied to experimental snapshots of two-dimensional Ising and XY quantum simulators, it detects phase transitions and crossovers while expressing its decision boundaries as symbolic formulas built from measurable spin correlators. This approach bridges the gap between black‑box neural networks and physically interpretable models, enabling automated discovery of new phases of matter from realistic, noisy experimental data.
The paper explores how information propagates in Deep Graph Networks (DGNs) for both static and dynamic graphs, treating DGNs as dynamical systems. It presents new architectures that better preserve long‑term node dependencies and learn complex spatio‑temporal patterns from irregular, sparsely sampled dynamic graphs. The work combines theoretical analysis with empirical results to demonstrate the effectiveness of these designs.
arXiv:2607. 03039v1 Announce Type: new Abstract: Neural networks are increasingly used to infer hidden physical structure from dynamical observations, yet it remains unclear whether their out-of-distribution performance reflects transferable physical rule learning.
arXiv:2606. 09432v1 Announce Type: new Abstract: Modeling interacting dynamical systems requires capturing spatial interactions alongside long-range temporal dependencies.
TetrisCNN is a convolutional neural network that uses parallel branches of differently shaped filters to learn sparse, interpretable latent representations directly in terms of spin correlators. Applied to experimental snapshots from two-dimensional Ising and XY quantum simulators measured in multiple bases, the network detects phase transitions and crossovers while expressing its decision boundaries as symbolic formulas built from experimentally measurable spin correlators. This approach bridges the gap between black‑box neural network methods and physically interpretable models, enabling automated detection of phases of matter from realistic, noisy experimental data.
The paper introduces ONDA, a graph learning framework that uses operator‑valued information waves to enable effective long‑range propagation in graph neural networks. ONDA evolves stalk‑valued representations through second‑order dynamics governed by learned sheaf transport operators, combining wave‑like propagation with expressive local geometry. Experiments on challenging benchmarks show that ONDA consistently outperforms scalar wave propagation, diffusive sheaf baselines, and state‑of‑the‑art models, demonstrating the advantage of coupling wave dynamics with matrix‑valued transport.