Smith42 / astroddpm
A denoising diffusion probabilistic model synthesises galaxies that are qualitatively and physically indistinguishable from the real thing.
☆48Updated 2 years ago
Related projects: ⓘ
- Multimodal contrastive pretraining for astronomical data☆69Updated 2 months ago
- A repository to store state of the art score model architectures☆38Updated last week
- Semantic alignment of astronomical data with natural language using multi-modal models. (Jax) Code associated with https://arxiv.org/abs/…☆11Updated last month
- Galaxy images labelled by morphology (shape). Aimed at ML development and teaching.☆31Updated last year
- Coverage tests to check the quality of your posterior estimators.☆26Updated last month
- ML-friendly datasets of galaxy images and labels☆30Updated this week
- A JAX package for weak gravitational lensing☆27Updated 4 months ago
- Large-Scale Multimodal Dataset of Astronomical Data☆32Updated last month
- Investigating the information content in the cosmic web through dark matter halo graphs. Arxiv paper: https://arxiv.org/abs/2207.05202☆12Updated 8 months ago
- Differentiable cosmological emulators: the JAX version of cosmopower☆28Updated 2 months ago
- ☆16Updated 3 years ago
- Bayesian Light Source Separator☆40Updated this week
- Transformer-guided diffusion for galaxy clustering. Code repository associated with https://arxiv.org/abs/2311.17141☆20Updated 8 months ago
- Autoencoders for galaxies☆10Updated 3 years ago
- JAX port of GalSim, for parallelized, GPU accelerated, and differentiable galaxy image simulations.☆25Updated this week
- Fine-tune a 7B LLM on cosmology datasets☆21Updated 3 weeks ago
- A package to describe amortized (conditional) normalizing-flow PDFs defined jointly on tensor products of manifolds with coverage control…☆42Updated 7 months ago
- Using Graph Neural Networks to regress baryonic properties directly from full dark matter merger trees.☆24Updated last year
- Probabilistic modeling of tabular data with normalizing flows.☆54Updated 3 months ago
- Exploring how ChatGPT can be used to accelerate research in cosmology.☆12Updated last year
- Spectrum encoder and decoder☆33Updated 3 months ago
- Differentiable strong lens modelling on CPUs and GPUs☆23Updated 2 weeks ago
- Machine learning assisted marginal likelihood (Bayesian evidence) estimation for Bayesian model selection☆54Updated last month
- Streamlit app for galaxy similarity search☆21Updated 2 years ago
- Material for the CMU Quarks2Cosmos Conference Data Challenges☆14Updated last year
- tutorials on shape measurement☆10Updated 2 years ago
- Robust ML in Astro☆43Updated this week
- A differentiable cosmology library in JAX☆172Updated last month
- Using neural networks to extract sufficient statistics from data by maximising the Fisher information☆29Updated last year
- Code for Leung & Bovy 2023☆19Updated 2 weeks ago