article published yes Frederik Skovbo Moller author 43cbcc83-0564-11f0-a935-e37325525859 Gabriel Fernández-Fernández author Thomas Schweigler author Paulin De Schoulepnikoff author Jörg Schmiedmayer author Gorka Muñoz-Gil author EdHa department Analog quantum simulators provide access to many-body dynamics beyond the reach of classical computation. However, extracting physical insights from experimental data is often hindered by measurement noise, limited observables, and incomplete knowledge of the underlying microscopic model. Here, we develop a machine learning approach based on a variational autoencoder (VAE) to analyze interference measurements of tunnel-coupled one-dimensional Bose gases, which realize the sine-Gordon quantum field theory. Trained in an unsupervised manner, the VAE learns a minimal latent representation that strongly correlates with the equilibrium control parameter of the system. Applied to nonequilibrium protocols, the latent space uncovers signatures of frozen-in solitons following rapid cooling, and reveals anomalous postquench dynamics not captured by conventional correlation-based methods. These results demonstrate that generative models can extract physically interpretable variables directly from noisy and sparse experimental data, providing complementary probes of equilibrium and nonequilibrium physics in quantum simulators. More broadly, our work highlights how machine learning can supplement established field-theoretical techniques, paving the way for scalable, data-driven discovery in quantum many-body systems. https://research-explorer.ista.ac.at/download/21847/21852/2026_PhysicalReviewResearch_Moller.pdf application/pdfno American Physical Society2026 eng 2643-1564 2509.1382110.1103/r7pj-gl7r 82 Moller, F. S., Fernández-Fernández, G., Schweigler, T., De Schoulepnikoff, P., Schmiedmayer, J., &#38; Muñoz-Gil, G. (2026). Learning minimal representations of many-body physics from snapshots of a quantum simulator. <i>Physical Review Research</i>. American Physical Society. <a href="https://doi.org/10.1103/r7pj-gl7r">https://doi.org/10.1103/r7pj-gl7r</a> F. S. Moller, G. Fernández-Fernández, T. Schweigler, P. De Schoulepnikoff, J. Schmiedmayer, and G. Muñoz-Gil, “Learning minimal representations of many-body physics from snapshots of a quantum simulator,” <i>Physical Review Research</i>, vol. 8, no. 2. American Physical Society, 2026. Moller, Frederik Skovbo, Gabriel Fernández-Fernández, Thomas Schweigler, Paulin De Schoulepnikoff, Jörg Schmiedmayer, and Gorka Muñoz-Gil. “Learning Minimal Representations of Many-Body Physics from Snapshots of a Quantum Simulator.” <i>Physical Review Research</i>. American Physical Society, 2026. <a href="https://doi.org/10.1103/r7pj-gl7r">https://doi.org/10.1103/r7pj-gl7r</a>. Moller FS, Fernández-Fernández G, Schweigler T, De Schoulepnikoff P, Schmiedmayer J, Muñoz-Gil G. 2026. Learning minimal representations of many-body physics from snapshots of a quantum simulator. Physical Review Research. 8(2), 023094. F.S. Moller, G. Fernández-Fernández, T. Schweigler, P. De Schoulepnikoff, J. Schmiedmayer, G. Muñoz-Gil, Physical Review Research 8 (2026). Moller, Frederik Skovbo, et al. “Learning Minimal Representations of Many-Body Physics from Snapshots of a Quantum Simulator.” <i>Physical Review Research</i>, vol. 8, no. 2, 023094, American Physical Society, 2026, doi:<a href="https://doi.org/10.1103/r7pj-gl7r">10.1103/r7pj-gl7r</a>. Moller FS, Fernández-Fernández G, Schweigler T, De Schoulepnikoff P, Schmiedmayer J, Muñoz-Gil G. Learning minimal representations of many-body physics from snapshots of a quantum simulator. <i>Physical Review Research</i>. 2026;8(2). doi:<a href="https://doi.org/10.1103/r7pj-gl7r">10.1103/r7pj-gl7r</a> 218472026-05-10T22:02:15Z2026-05-11T06:58:56Z