arXiv AI June 18, 2026 By Till Richter, Niki Kilbertus

OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems

arXiv:2606. 19145v1 Announce Type: cross Abstract: Dynamical systems are fundamental to modeling the natural world, yet modeling them involves a persistent trade-off: manually prescribed mechanistic models are interpretable by design but often overly simplistic and misspecified; in contrast, flexible data-driven neural methods lack physical insight.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

benchmarks

arXiv AI

Aug 6

SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors

arXiv:2608. 04060v1 Announce Type: cross Abstract: Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models are typically opaque neural maps.

By Yongchao Huang

rag

arXiv Machine Learning

Aug 10

Mathematical Principles and Experimental Discoveries of the Emergence of Symbolic Patterns in Artificial Neural Networks

arXiv:2608. 06839v1 Announce Type: new Abstract: Artificial Neural networks (ANNs) are often treated as black-box models, making explainability a central challenge in deep learning.

By Quanshi Zhang, Qihan Ren, Siyu Lou

arXiv Machine Learning

Jun 30

Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization

arXiv:2606. 29951v1 Announce Type: new Abstract: Interpretable Mesomorphic Neural Networks (IMNs) offer a promising framework that combines the predictive power of deep neural networks with the interpretability of linear models.

By Hugo L. Hammer, Vajira Thambawita, Kristoffer Herland Hellton, P{\aa}l Halvorsen

benchmarks safety

arXiv Machine Learning

Jul 22

Hierarchical Physics-Embedded Learning for Partially Known Spatiotemporal Dynamics

arXiv:2510. 25306v3 Announce Type: replace Abstract: Partial physical knowledge--governing structures known, constitutive relations or their combinations not--pervades spatiotemporal systems.

By Xizhe Wang, Xiaobin Song, Hongbo Zhao, Qingshan Jia, Qianchuan Zhao, Hao Sun, Benben Jiang

rag benchmarks

arXiv Machine Learning

Aug 10

Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data

arXiv:2511. 09432v2 Announce Type: replace Abstract: Machine learning (ML) models achieve remarkable performance but remain hard to interpret due to their scale and complexity.

By Ege Erdogan, Ana Lucic

safety

arXiv Machine Learning

Jul 17

RTS Smoother-Guided Learning of Physics-Based Neural Differential Models

arXiv:2607. 15180v1 Announce Type: new Abstract: Ordinary differential equations (ODEs) are widely used to model dynamical systems in physics, biology, neuroscience, and physiology, but in many applications some equations of the dynamics are unknown and only a subset of the state variables are measured.

By Ahmet Demirkaya, Georgios Stratis, Tales Imbiriba, Zachary D. Danziger, Deniz Erdogmus

benchmarks

Related stories

SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors

Mathematical Principles and Experimental Discoveries of the Emergence of Symbolic Patterns in Artificial Neural Networks

Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization

Hierarchical Physics-Embedded Learning for Partially Known Spatiotemporal Dynamics

Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data

RTS Smoother-Guided Learning of Physics-Based Neural Differential Models