Minimalistic README.md.

README.md

@@ -1,27 +1,19 @@
-[![Build Status](https://travis-ci.org/mackelab/nflows.svg?branch=master)](https://travis-ci.org/mackelab/nflows)
-
-
 ## Description
-Building on code for "On Contrastive Learning for Likelihood-free Inference" in https://github.com/conormdurkan/lfi, the relevant part is mostly from https://github.com/bayesiains/nsf.
-
-A toolbox for conditional density estimation in python/pytorch, currently featuring 
-two families of neural conditional density estimators: normalizing flows and mixture-density networks. 
-
+`nflows` is a comprehensive collection of [normalizing flows](https://arxiv.org/abs/1912.02762) using [PyTorch](https://pytorch.org).
 
 ## Setup
 
 You can install all the dependencies using the `environment.yml` file to create a conda environment: `conda env create -f environment.yml`
 
-Alternatively, you can install via setup.py using pip install -e ".[dev]" (the dev flag installs development and testing dependencies).
-
-## Examples
+Alternatively, you can install via `setup.py` using `pip install -e ".[dev]"` (the `dev` flag installs development and testing dependencies).
 
-Examples are collected in notebooks in `examples/`. 
 
-## Git LFS
+## References
+`nflows` is derived from [bayesiains/nsf](https://github.com/bayesiains/nsf) originally published with
+> C. Durkan, A. Bekasov, I. Murray, G. Papamakarios, _Neural Spline Flows_, NeurIPS 2019.
+> [[arXiv]](https://arxiv.org/abs/1906.04032) [[bibtex]](https://gpapamak.github.io/bibtex/neural_spline_flows.bib)
 
-We use git lfs to store binary files, e.g., example notebooks. To use git lfs follow installation instructions here https://git-lfs.github.com/. 
 
-## Acknowledgements
-This code builds heavily on previous work by [Conor Durkan](https://conormdurkan.github.io/), [George Papamakarios](https://gpapamak.github.io/) and [Artur Bekasov](https://arturbekasov.github.io/), and in particular on their 
-repositories include [bayesiains/nsf](https://github.com/bayesiains/nsf) and [conormdurkan/lfi](https://github.com/conormdurkan/lfi). 
+`nflows` have been used as density estimators for likelihood-free inference in 
+> Conor Durkan, Iain Murray, George Papamakarios, _On Contrastive Learning for Likelihood-free Inference_
+> [[arXiv]](https://arxiv.org/abs/2002.03712).