# Neural ODEs and Beyond

### General Architecture for Neural ODEs
* [Neural Ordinary Differential Equations](https://arxiv.org/pdf/1806.07366.pdf), NIPS 2018, Best Paper
* [Augmented Neural ODEs](https://arxiv.org/pdf/1904.01681.pdf), NIPS 2019
* [On Second Order Behaviour in Augmented Neural ODEs](https://arxiv.org/pdf/2006.07220.pdf), NIPS 2020
* [Dissecting Neural ODEs](https://arxiv.org/pdf/2002.08071.pdf), NIPS 2020
* [Neural ODE Process](https://openreview.net/pdf?id=27acGyyI1BY), ICLR 2021
* [Continuous Latent Process Flows](https://arxiv.org/pdf/2106.15580.pdf), 2021

### NODEs and Time Series Analysis
* [STEER: Simple Temporal Regularization For Neural ODEs](https://arxiv.org/pdf/2006.10711.pdf), NIPS 2020
* [Latent odes for irregularly-sampled time series](https://arxiv.org/pdf/1907.03907.pdf), NIPS 2019
*

### NODEs and Robustness
* [On robustness of neural ordinary differential equations](https://arxiv.org/pdf/1910.05513.pdf), ICLR 2020
* [Neural SDE: Stabilizing Neural ODE Networks with Stochastic
Noise](https://arxiv.org/abs/1906.02355), CVPR 2021
* [Adversarial Robustness of Stabilized NeuralODEs Might be from
Obfuscated Gradients](https://arxiv.org/pdf/2009.13145.pdf), Arxiv 2021, [codes](https://github.com/yao-lab/SONet)
* [Defending Neural ODE Image Classifiers from Adversarial Attacks with Tolerance Randomization](https://www.springerprofessional.de/en/defending-neural-ode-image-classifiers-from-adversarial-attacks-/18900158), ICPR 2021
* [META-SOLVER FOR NEURAL ORDINARY DIFFERENTIAL EQUATIONS](https://arxiv.org/pdf/2103.08561.pdf), 2021

### NODEs and Transformers
* [Learning to Encode Position for Transformer
with Continuous Dynamical Model](http://proceedings.mlr.press/v130/xu21g/xu21g.pdf), ICML 2020

### NODEs and Continual Learning
* [Continual Learning in the Teacher-Student Setup: Impact of Task Similarity](https://proceedings.mlr.press/v139/lee21e.html), ICML 2021

### NODEs and Few-shot (Meta) Learning
* [MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning](https://arxiv.org/pdf/2103.14341.pdf), 2021
* [Learning Dynamic Alignment via Meta-filter for Few-shot Learning](https://openaccess.thecvf.com/content/CVPR2021/papers/Xu_Learning_Dynamic_Alignment_via_Meta-Filter_for_Few-Shot_Learning_CVPR_2021_paper.pdf), CVPR 2021
* [Meta Learning in the Continuous Time Limit](http://proceedings.mlr.press/v130/xu21g/xu21g.pdf), AISTATS 2021

### NODEs and Generative Models
* [ODE2VAE: Deep generative second order ODEs with Bayesian neural networks](https://arxiv.org/pdf/1905.10994.pdf), NIPS 2019
* [OCT-GAN: Neural ODE-based Conditional Tabular GANs](https://dl.acm.org/doi/pdf/10.1145/3442381.3449999), WWW 2021

### NODEs and Graph
* [Continuous–Depth Neural Models for Dynamic Graph Prediction](https://arxiv.org/pdf/2106.11581.pdf), AAAI 20
* [](https://)

### NODEs and Reinforcement Learning
* [Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs](https://arxiv.org/pdf/2006.16210.pdf), NIPS 2020
* [Faster Policy Learning with Continuous-Time Gradients](http://proceedings.mlr.press/v144/ainsworth21a/ainsworth21a.pdf), L4DC 2021
* [Continuous-time Model-based Reinforcement Learning](http://proceedings.mlr.press/v139/yildiz21a/yildiz21a.pdf), ICML 2021

### NODEs and Transfer Learning
* [Transfer Learning using Neural Ordinary Differential Equations](https://arxiv.org/pdf/2001.07342.pdf), 2021

### NODEs and Medical Imaging
* [ODE-based Deep Network for MRI Reconstruction](https://arxiv.org/abs/1912.12325), 2019
* [MRI Image Reconstruction via Learning Optimization Using Neural ODEs](https://link.springer.com/chapter/10.1007/978-3-030-59713-9_9), MICCAI 2020
* [Multi-scale Neural ODEs for 3D Medical Image Registration](https://arxiv.org/pdf/2106.08493.pdf), 2021

### Others
* [Towards Adaptive Residual Network Training: A Neural-ODE Perspective](http://proceedings.mlr.press/v119/dong20c/dong20c.pdf), ICML 2020
* [RESNET AFTER ALL? NEURAL ODES AND THEIR NUMERICAL SOLUTION](https://openreview.net/pdf?id=HxzSxSxLOJZ), ICLR 2021