DINGO (PRL 2021 / ICLR 2022)
github.com/dingo-gw/dingoAmortized simulation-based inference for gravitational-wave Bayesian parameter estimation, training conditional normalizing flows on millions of simulated waveforms and detector-noise PSDs so posterior inference on real compact-binary coalescence events completes in ~1 minute versus ~a day of MCMC; introduces group-equivariant GNPE that exploits physical symmetries, asymptotically exact DINGO-IS neural importance-sampling correction, a transformer-based DINGO-T1 variant for flexible inference, and BNS extensions enabling sub-second inference for electromagnetic follow-up of neutron-star mergers (Max Planck Institute for Intelligent Systems & AEI Potsdam, 132+ stars, MIT License, actively maintained)
Sourced from
- GitHub — github.com/dingo-gw/dingo
- Awesome AI for Science — github.com/dingo-gw/dingo
Related resources
Fast and scalable MCMC toolkit for exoplanet characterization built on PyMC and Aesara/JAX, providing differentiable probabilistic models for transit light curves, radial velocities, and astrometry — enabling gradient-based inference (NUTS) and Hamiltonian Monte Carlo for robust parameter estimation, model comparison, and uncertainty quantification in time-domain astronomy (exoplanet-dev, JOSS 2021, 242+ stars, MIT License, actively maintained)
Cross-modal self-supervised foundation model for galaxies by Polymathic AI, jointly embedding multi-band galaxy imaging and optical spectra into a shared latent space to enable zero/few-shot redshift estimation, galaxy property prediction, morphology classification, and cross-modal similarity search (MNRAS Letters 2024)
Polymathic AI's large omnimodal foundation model for astronomical surveys, seamlessly integrating 39 distinct data modalities including imaging, spectra, photometry, and catalog entries for similarity search, property prediction, and generative modeling across legacy surveys (MIT)
PyTorch library for training neural networks on gravitational-wave physics, providing differentiable PSD estimation, whitening, SNR calculation, interferometer response projection, waveform simulation, and streaming data loaders; the shared back end of the NSF A3D3/ML4GW pipelines deployed for real-time detection of compact-binary coalescences in LIGO–Virgo–KAGRA observing runs (35+ stars, GPL-3.0, 2022-2026)