arXiv Machine Learning August 13, 2026 By Cyrill B\"osch, Yigithan Gediz, Hakan T\"ureci

Unifying Physical Backpropagation

Read the original on arXiv Machine Learning →

arXiv:2608. 11585v1 Announce Type: cross Abstract: Physical computing systems exploit device dynamics for computation, but their gradient-based optimization is challenging: backpropagation through a digital twin suffers from model-reality gap.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 9

Perturbative Contrastive Physical Learning

arXiv:2606. 09756v1 Announce Type: new Abstract: Responses to perturbations are key to understanding physical systems.

By Kyungeun Kim, Amanuel Anteneh, Israel Klich, Olivier Pfister, J. M. Schwarz

agents

arXiv Machine Learning

Aug 5

Symplectic Neural Networks for Learning Non-Separable Hamiltonians

arXiv:2606. 27029v2 Announce Type: replace Abstract: Hamiltonian Neural Networks (HNNs) integrate physical priors into neural models by learning a system's Hamiltonian, improving generalization and sample efficiency.

By Harsh Choudhary, Vyacheslav Kungurtsev, Chandan Gupta, Melvin Leok, Georgios Korpas

arXiv Machine Learning

Jun 26

Symplectic Neural Networks for learning Generalized Hamiltonians

arXiv:2606. 27029v1 Announce Type: new Abstract: Hamiltonian Neural Networks (HNNs) integrate physical priors into neural models by learning a system's Hamiltonian, improving generalization and sample efficiency.

By Harsh Choudhary, Vyacheslav Kungurtsev, Chandan Gupta, Melvin Leok, Georgios Korpas

arXiv Machine Learning

Jul 20

Physics-enhanced reinforcement learning for real-time optimal control of dynamical systems

arXiv:2607. 16177v1 Announce Type: new Abstract: Reinforcement learning (RL) has recently emerged as a promising feedback control strategy for nonlinear and complex dynamical systems.

By Matteo Tomasetto, Nicol\`o Botteghi, Gabriele Bruni, Andrea Manzoni

agents reinforcement-learning benchmarks

arXiv Machine Learning

Jun 2

Graph Transfer Learning via Shared Latent Geometry: Theory and Applications

arXiv:2606. 00716v1 Announce Type: new Abstract: Inference and control in engineered physical systems pay a heavy physics cost at deployment: state estimators, inverse-problem solvers, model-predictive controllers, schedulers, and observers are often not closed-form and must re-solve a numerical optimization per instance, with the operator re-supplied each time.

By Tong Wu, Andrew Campbell, Anna Scaglione

fine-tuning efficiency multimodal

arXiv Machine Learning

Aug 26

Physics-Integrated Operator Learning via Gaussian Splatting Representations

arXiv:2608.24049v1 Announce Type: new Abstract: Neural operators provide efficient surrogates for spatiotemporal PDE systems, but purely data-driven formulations often accumulate substantial errors d...

By Jihao Zhang, Junyi Guo, Jian-Xun Wang

diffusion benchmarks

One email a morning, machine-written

Related stories

Perturbative Contrastive Physical Learning

Symplectic Neural Networks for Learning Non-Separable Hamiltonians

Symplectic Neural Networks for learning Generalized Hamiltonians

Physics-enhanced reinforcement learning for real-time optimal control of dynamical systems

Graph Transfer Learning via Shared Latent Geometry: Theory and Applications

Physics-Integrated Operator Learning via Gaussian Splatting Representations