Upcoming surveys will produce billions of galaxy images but comparatively few spectra, motivating models that learn cross-modal representations. We build a dataset of 134,533 galaxy images (HSC-PDR2) and spectra (DESI-DR1) and adapt a Multi-Modal Masked Autoencoder (MMAE) to embed both images and spectra in a shared representation. The MMAE is a transformer-based architecture, which we train by masking 75% of the data and reconstructing missing image and spectral tokens. We use this model to test three applications: spectral and image reconstruction from heavily masked data and redshift regression from images alone. It recovers key physical features, such as galaxy shapes, atomic emission line peaks, and broad continuum slopes, though it struggles with fine image details and line strengths. For redshift regression, the MMAE performs comparably or better than prior multi-modal models in terms of prediction scatter even when missing spectra in testing. These results highlight both the potential and limitations of masked autoencoders in astrophysics and motivate extensions to additional modalities, such as text, for foundation models.

We present a novel dataset of simulations of the photodissociation region (PDR) in the Orion Bar and provide benchmarks of emulators for the dataset. Numerical models of PDRs are computationally expensive since the modeling of these changing regions requires resolving the thermal balance and chemical composition along a line-of-sight into an interstellar cloud. This often makes it a bottleneck for 3D simulations of these regions. In this work, we provide a dataset of 8192 models with different initial conditions simulated with 3D-PDR.

We present a novel approach to reconstruct gas and dark matter projected density maps of galaxy clusters using score-based generative modeling. Our diffusion model takes in mock SZ and X-ray images as conditional observations, and generates realizations of corresponding gas and dark matter maps by sampling from a learned data posterior. We train and validate the performance of our model by using mock data from a hydrodynamical cosmological simulation. The model accurately reconstructs both the mean and spread of the radial density profiles in the spatial domain to within 5\%, indicating that the model is able to distinguish between clusters of different sizes. In the spectral domain, the model achieves close-to-unity values for the bias and cross-correlation coefficients, indicating that the model can accurately probe cluster structures on both large and small scales. Our experiments demonstrate the ability of score models to learn a strong, nonlinear, and unbiased mapping between input observables and fundamental density distributions of galaxy clusters. These diffusion models can be further fine-tuned and generalized to not only take in additional observables as inputs, but also real observations and predict unknown density distributions of galaxy clusters.

The specialized language and complex concepts in physics pose significant challenges for information extraction through Natural Language Processing (NLP). Central to effective NLP applications is the text embedding model, which converts text into dense vector representations for efficient information retrieval and semantic analysis. In this work, we introduce PhysBERT, the first physics-specific text embedding model. Pre-trained on a curated corpus of 1.2 million arXiv physics papers and fine-tuned with supervised data, PhysBERT outperforms leading general-purpose models on physics-specific tasks including the effectiveness in fine-tuning for specific physics subdomains.

In inference problems, we often have domain knowledge which allows us to define summary statistics that capture most of the information content in a dataset. In this paper, we present a hybrid approach, where such physics-based summaries are augmented by a set of compressed neural summary statistics that are optimised to extract the extra information that is not captured by the predefined summaries. The resulting statistics are very powerful inputs to simulation-based or implicit inference of model parameters. We apply this generalisation of Information Maximising Neural Networks (IMNNs) to parameter constraints from tomographic weak gravitational lensing convergence maps to find summary statistics that are explicitly optimised to complement angular power spectrum estimates. We study several dark matter simulation resolutions in low- and high-noise regimes. We show that i) the information-update formalism extracts at least $3\times$ and up to $8\times$ as much information as the angular power spectrum in all noise regimes, ii) the network summaries are highly complementary to existing 2-point summaries, and iii) our formalism allows for networks with smaller, physically-informed architectures to match much larger regression networks with far fewer simulations needed to obtain asymptotically optimal inference.

We present a comprehensive evaluation of proprietary and open-weights large language models using the first astronomy-specific benchmarking dataset. This dataset comprises 4,425 multiple-choice questions curated from the Annual Review of Astronomy and Astrophysics, covering a broad range of astrophysical topics. Our analysis examines model performance across various astronomical subfields and assesses response calibration, crucial for potential deployment in research environments. Claude-3.5-Sonnet outperforms competitors by up to 4.6 percentage points, achieving 85.0% accuracy. For proprietary models, we observed a universal reduction in cost every 3-to-12 months to achieve similar score in this particular astronomy benchmark. Open-source models have rapidly improved, with LLaMA-3-70b (80.6%) and Qwen-2-72b (77.7%) now competing with some of the best proprietary models. We identify performance variations across topics, with non-English-focused models generally struggling more in exoplanet-related fields, stellar astrophysics, and instrumentation related questions. These challenges likely stem from less abundant training data, limited historical context, and rapid recent developments in these areas. This pattern is observed across both open-weights and proprietary models, with regional dependencies evident, highlighting the impact of training data diversity on model performance in specialized scientific domains. Top-performing models demonstrate well-calibrated confidence, with correlations above 0.9 between confidence and correctness, though they tend to be slightly underconfident. The development for fast, low-cost inference of open-weights models presents new opportunities for affordable deployment in astronomy. The rapid progress observed suggests that LLM-driven research in astronomy may become feasible in the near future.

It's a problem that will be repeated in other places over the coming decade. As astronomers construct giant cameras to image the entire sky and launch infrared telescopes to hunt for distant planets, they will collect data on unprecedented scales. "We really are not ready for that, and we should all be freaking out," says Cecilia Garraffo, a computational astrophysicist at the Harvard-Smithsonian Center for Astrophysics. "When you have too much data and you don't have the technology to process it, it's like having no data." In preparation for the information deluge, astronomers are turning to AI for assistance, optimizing algorithms to pick out patterns in large and notoriously finicky data sets.

Artificial intelligence technology has been widely used in astronomy, and new artificial intelligence technologies and application scenarios are constantly emerging. There have been a large number of papers reviewing the application of artificial intelligence technology in astronomy. However, relevant articles seldom mention telescope intelligence separately, and it is difficult to understand the current development status and research hotspots of telescope intelligence from these papers. This paper combines the development history of artificial intelligence technology and the difficulties of critical technologies of telescopes, comprehensively introduces the development and research hotspots of telescope intelligence, then conducts statistical analysis on various research directions of telescope intelligence and defines the research directions' merits. All kinds of research directions are evaluated, and the research trend of each telescope's intelligence is pointed out. Finally, according to the advantages of artificial intelligence technology and the development trend of telescopes, future research hotspots of telescope intelligence are given.

Characterizing the interior structure of exoplanets is essential for understanding their diversity, formation, and evolution. As the interior of exoplanets is inaccessible to observations, an inverse problem must be solved, where numerical structure models need to conform to observable parameters such as mass and radius. This is a highly degenerate problem whose solution often relies on computationally-expensive and time-consuming inference methods such as Markov Chain Monte Carlo. We present ExoMDN, a machine-learning model for the interior characterization of exoplanets based on Mixture Density Networks (MDN). The model is trained on a large dataset of more than 5.6 million synthetic planets below 25 Earth masses consisting of an iron core, a silicate mantle, a water and high-pressure ice layer, and a H/He atmosphere. We employ log-ratio transformations to convert the interior structure data into a form that the MDN can easily handle. Given mass, radius, and equilibrium temperature, we show that ExoMDN can deliver a full posterior distribution of mass fractions and thicknesses of each planetary layer in under a second on a standard Intel i5 CPU. Observational uncertainties can be easily accounted for through repeated predictions from within the uncertainties. We use ExoMDN to characterize the interior of 22 confirmed exoplanets with mass and radius uncertainties below 10% and 5% respectively, including the well studied GJ 1214 b, GJ 486 b, and the TRAPPIST-1 planets. We discuss the inclusion of the fluid Love number $k_2$ as an additional (potential) observable, showing how it can significantly reduce the degeneracy of interior structures. Utilizing the fast predictions of ExoMDN, we show that measuring $k_2$ with an accuracy of 10% can constrain the thickness of core and mantle of an Earth analog to $\approx13\%$ of the true values.

Coronal Mass Ejections (CMEs) correspond to dramatic expulsions of plasma and magnetic field from the solar corona into the heliosphere. CMEs are scientifically relevant because they are involved in the physical mechanisms characterizing the active Sun. However, more recently CMEs have attracted attention for their impact on space weather, as they are correlated to geomagnetic storms and may induce the generation of Solar Energetic Particles streams. In this space weather framework, the present paper introduces a physics-driven artificial intelligence (AI) approach to the prediction of CMEs travel time, in which the deterministic drag-based model is exploited to improve the training phase of a cascade of two neural networks fed with both remote sensing and in-situ data. This study shows that the use of physical information in the AI architecture significantly improves both the accuracy and the robustness of the travel time prediction.