ermongroup

Course notes for CS228: Probabilistic Graphical Models.

Denoising Diffusion Implicit Models

PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations

Noise Conditional Score Networks (NeurIPS 2019, Oral)

Codes for "CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation"

The official PyTorch implementation for NCSNv2 (NeurIPS 2020)

Code for IEEE Communication Magazine (A Survey on Behaviour Recognition Using WiFi Channle State Information)

Multi-Agent Adversarial Inverse Reinforcement Learning, ICML 2019.

Implementation of VLAE

Official code for TEOChat, the first vision-language assistant for temporal earth observation data (ICLR 2025).

Code for reproducing results in the sliced score matching paper (UAI 2019)

Code for "Stochastic Optimization of Sorting Networks using Continuous Relaxations", ICLR 2019.

Code for "A-NICE-MC: Adversarial Training for MCMC"

Implementation and examples for Tile2Vec

Official implementation for the paper: Permutation Invariant Graph Generation via Score-Based Generative Modeling

Code for "Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models", AAAI 2018.

Implementation of Sequential Variational Autoencoder

Code for "Generative Adversarial Training for Markov Chains" (ICLR 2017 Workshop)

Code that accompanies the paper Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance

Meta-Inverse Reinforcement Learning with Probabilistic Context Variables

PyTorch implementation for the ICLR 2020 paper "Understanding the Limitations of Variational Mutual Information Estimators"

PyTorch Implementation of `Learning to Process Fewer Pixels` - [CVPR20 (Oral)]

Code for the unrestricted adversarial examples paper (NeurIPS 2018)

PiRank: Learning to Rank via Differentiable Sorting

Code for Graphite iterative graph generation

Code for Reparameterizable Subset Sampling via Continuous Relaxations, IJCAI 2019.

Code for "Calibrated Model-Based Deep Reinforcement Learning", ICML 2019.

Neural Joint-Source Channel Coding

Code for "Diversity can be Transferred: Output Diversification for White- and Black-box Attacks"