arXiv Machine Learning
Aug 21
Deep neural networks as lattice gauge theories
arXiv:2608. 19331v1 Announce Type: cross Abstract: We modify the NN/QFT duality [1] to incorporate the layerwise permutation symmetry of the network, resulting in a $(0\!
Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories
arXiv:2607. 07127v1 Announce Type: cross Abstract: Lattice field theory is the workhorse of non-perturbative physics, used to simulate phenomena from the strong nuclear force to critical phenomena in materials.
Related stories
arXiv Machine Learning
Jul 27
Explainable quantum-compressed machine learning for complex fluid flows
arXiv:2607. 21688v1 Announce Type: cross Abstract: Machine-learning surrogates of physical systems face a paradox: explainable models facing the challenge of expressivity to capture complex nonlinear flows, whereas expressive deep surrogates match high-fidelity simulations only through massive parameterisations that turn the learned dynamics into a black box.
arXiv Machine Learning
Sep 1
Operator-Guided Model Reduction for Generative Sampling in Lattice Field Theory
arXiv:2605.11199v2 Announce Type: replace-cross Abstract: Neural generative samplers for lattice field theory can be costly to train and evaluate. When they miss modes or assign them incorrect relati...
arXiv AI
Jul 3
Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts
arXiv:2605. 29283v2 Announce Type: replace-cross Abstract: Recent physics foundation models claim general spatiotemporal forecasting ability, yet their evaluations often collapse performance into a single average score under a fixed training distribution.
arXiv Machine Learning
Jun 30
Factorizable Normalizing Flows for parameter-dependent density morphing
arXiv:2606. 30489v1 Announce Type: cross Abstract: Normalizing Flows excel at modeling a single fixed density, yet many problems across the sciences, such as high energy physics, instead require modeling how that density deforms as a function of continuous parameters: the strength of a physical effect, a calibration constant, or a source of systematic uncertainty.
arXiv Machine Learning
Jul 31
Emulating Cosmic Structure Formation with a Lagrangian Neural Cellular Automaton
arXiv:2607. 27320v1 Announce Type: cross Abstract: Field-level inference of cosmological initial conditions from galaxy surveys requires a forward model that is simultaneously accurate in the non-linear regime, computationally efficient, and fully differentiable.
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.
arXiv Machine Learning
Sep 10
Latent-MoE: Domain-Aware Mixture-of-Experts for PDEs with Multi-Regime Physics
arXiv:2609.07814v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) struggle on PDEs whose governing physics varies across the domain. We trace this to a structural property of s...
arXiv Machine Learning
Sep 10
PhysSAE: Mechanistic Interpretability with Sparse Autoencoders
arXiv:2609.07061v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) embed PDE residuals into neural network training, but their internal representations remain opaque: it is unkn...
Hugging Face Trending Papers
Jun 10
Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics
Generative AI emulators are increasingly used in scientific domains where we already have strong theory, benchmarks, and physical intuition. This raises a central evaluation and interpretability question: when a foundation-style model can reproduce known continuum dynamics, what internal mechanism supports that behavior, is the internal behaviour consistent with known physics, and how does it relate to where the emulator succeeds or fails?
arXiv Machine Learning
Sep 15
PhysSAE: Mechanistic Interpretability of PINNs with Sparse Autoencoders
arXiv:2609.07061v2 Announce Type: replace Abstract: Physics-Informed Neural Networks (PINNs) embed PDE residuals into neural network training, but their internal representations remain opaque: it is...
arXiv AI
Jul 3
Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders
arXiv:2607. 01336v1 Announce Type: cross Abstract: Neural Quantum States (NQS) are a remarkably expressive class of variational ans\"atze for quantum many-body wavefunctions, yet little is understood about their internal mechanisms: trained on variational objectives alone, how do NQS accurately capture physical observables that they have never been explicitly optimized for?