# Ivy: Templated Deep Learning for Inter-Framework Portability

arXiv: https://arxiv.org/abs/2102.02886 · HTML: https://mlsanity.com/paper/2102.02886/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 4 Feb 2021.

## Builds on (most cited first, 16 of 16)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems](https://mlsanity.com/paper/1512.01274/) (2015)
- [BA-Net: Dense Bundle Adjustment Network](https://mlsanity.com/paper/1806.04807/) (2018)
- [Value Iteration Networks](https://mlsanity.com/paper/1602.02867/) (2016)
- [CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM](https://mlsanity.com/paper/1804.00874/) (2018)
- [Scalable Differentiable Physics for Learning and Control](https://mlsanity.com/paper/2007.02168/) (2020)
- [Theano: A Python framework for fast computation of mathematical expressions](https://mlsanity.com/paper/1605.02688/) (2016)
- [PyRep: Bringing V-REP to Deep Robot Learning](https://mlsanity.com/paper/1906.11176/) (2019)
- [GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing](https://mlsanity.com/paper/1907.04433/) (2019)
- [Chainer: A Deep Learning Framework for Accelerating the Research Cycle](https://mlsanity.com/paper/1908.00213/) (2019)
- [DLTK: State of the Art Reference Implementations for Deep Learning on Medical Images](https://mlsanity.com/paper/1711.06853/) (2017)
- [ZhuSuan: A Library for Bayesian Deep Learning](https://mlsanity.com/paper/1709.05870/) (2017)

## Built on by (most cited first, 6 of 6)

- [Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation](https://mlsanity.com/paper/2106.12534/) (2021)
- [Adversarial Cheap Talk](https://mlsanity.com/paper/2211.11030/) (2022)
- [When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?](https://mlsanity.com/paper/2503.15231/) (2025)
- [Learning Graph Search Heuristics](https://mlsanity.com/paper/2212.03978/) (2022)
- [End-to-End Egospheric Spatial Memory](https://mlsanity.com/paper/2102.07764/) (2021)
- [Towards Migrating Neural Network Implementations](https://mlsanity.com/paper/2511.02610/) (2025)

## Abstract (arXiv)

We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks. Ivy unifies the core functions of these frameworks to exhibit consistent call signatures, syntax and input-output behaviour. New high-level framework-agnostic functions and classes, which are usable alongside framework-specific code, can then be implemented as compositions of the unified low-level Ivy functions. Ivy currently supports TensorFlow, PyTorch, MXNet, Jax and NumPy. We also release four pure-Ivy libraries for mechanics, 3D vision, robotics, and differentiable environments. Through our evaluations, we show that Ivy can significantly reduce lines of code with a runtime overhead of less than 1% in most cases. We welcome developers to join the Ivy community by writing their own functions, layers and libraries in Ivy, maximizing their audience and helping to accelerate DL research through inter-framework codebases. More information can be found at https://ivy-dl.org.