Xun Huang

MonarchRT. Python

FastGen. NVIDIA FastGen: Fast Generation from Diffusion Models

KnapFormer. Python

Self-Forcing. Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

LaCT. Code release for paper "Test-Time Training Done Right"

CausVid. (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

pixel2style2pixel. Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework

PlotNeuralNet. Latex code for making neural networks diagrams

BigGAN-PyTorch. The author's officially unofficial PyTorch BigGAN implementation.

IIC. Invariant Information Clustering for Unsupervised Image Classification and Segmentation

structural-analogy. Pytorch implementation for the paper "Structural-analogy from a Single Image Pair"

CMC. [arXiv 2019] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis

ETNet. ETNet: Error Transition Network for Arbitrary Style Transfer (NeurIPS 2019)

DomainIntersectionDifference. Pytorch implementation of of "Domain Intersection and Domain Difference" (ICCV 2019)

HashingDeepLearning. Codebase for "SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems"

improved-precision-and-recall-metric. Improved Precision and Recall Metric for Assessing Generative Models - Official TensorFlow Implementation

spiral. We provide a pre-trained model for unconditional 19-step generation of CelebA-HQ images

cyclical_annealing. OpenEdge ABL

gan_steerability. On the "steerability" of generative adversarial networks

PointFlow. PointFlow : 3D Point Cloud Generation with Continuous Normalizing Flows

mbu-content-tansfer. Mask Based Unsupervised Content Transfer (ICLR 2020)

metropolis-hastings-gans. Python

CloserLookFewShot. source code to ICLR'19, 'A Closer Look at Few-shot Classification'

STROTSS. Style Transfer by Relaxed Optimal Transport and Self-Similarity (CVPR 2019)

augmented-neural-odes. Pytorch implementation of Augmented Neural ODEs :sunflower:

class-balanced-loss. Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

FUNIT. Translate images to unseen domains in the test time with few example images.

996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.

finegan. FineGAN: Unsupervised Hierarchical Disentanglement for Fine-grained Object Generation and Discovery

Im2Pencil. The source code of CVPR19 'Im2Pencil: Controllable Pencil Illustration from Photographs'.

SPADE. Semantic Image Synthesis with SPADE

NeuralBabyTalk. Pytorch code of for our CVPR 2018 paper "Neural Baby Talk"

ffjord. code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".

stylegan. StyleGAN - Official TensorFlow Implementation

show-control-and-tell. Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions. CVPR 2019

Stylized-ImageNet. Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)

neural-collage. Collaging on Internal Representations: An Intuitive Approach for Semantic Transfiguration

latent_3d_points. Auto-encoding & Generating 3D Point-Clouds.

torchdiffeq. Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

pwc. This repository is no longer maintained.

cycada_release. Code to accompany ICML 2018 paper

TwinGAN. Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs

vid2vid. Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

video_prediction. Stochastic Adversarial Video Prediction

GAN_stability. Code for paper "Which Training Methods for GANs do actually Converge? (ICML 2018)"

gan_bound. Pytorch implementation of "Estimating the Success of Unsupervised Image to Image Translation" ECCV 2018

Switchable-Normalization. Code for Switchable Normalization from "Differentiable Learning-to-Normalize via Switchable Normalization", https://arxiv.org/abs/1806.10779

film. FiLM: Visual Reasoning with a General Conditioning Layer

Unsupervised-Attention-guided-Image-to-Image-Translation. Unsupervised Attention-Guided Image to Image Translation

GAIA. Generative Adversarial Interpolative Autoencoder (GAIA) is a Generative Adversarial Network (GAN) made up of Autoencoders (AE) trained explicitly on interpolations to promote convexity and better latent interpolations.

glow. Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

avatar-net. Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration

style_transfer. Style Transfer as Optimal Transport

contextualLoss. The Contextual Loss

scalable_agent. A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.

two-stream-dyntex-synth. Code for the paper "Two-Stream Convolutional Networks for Dynamic Texture Synthesis". Presented at CVPR '18.

PyTorch-GAN. PyTorch implementations of Generative Adversarial Networks.

MUNIT-keras. A keras (tensorflow) reimplementation of MUNIT: Multimodal Unsupervised Image-to-Image Translation https://arxiv.org/abs/1804.04732

MUNIT-Tensorflow. Simple Tensorflow implementation of "Multimodal Unsupervised Image-to-Image Translation" (ECCV 2018)

MUNIT. Multimodal Unsupervised Image-to-Image Translation

undreamt. Unsupervised Neural Machine Translation

inn. Code for the ICCV 2017 paper "Introspective Neural Networks for Generative Modeling"

FastPhotoStyle. Style transfer, deep learning, feature transform

man. Multinomial Adversarial Networks for Multi-Domain Text Classification (NAACL 2018)

textstyletransferdata. Python

PerceptualSimilarity. LPIPS metric. pip install lpips

openrec. OpenRec is an open-source and modular library for neural network-inspired recommendation algorithms

triple-gan. See Triple-GAN-V2 in PyTorch: https://github.com/taufikxu/Triple-GAN

arbitrary_style_transfer. Fast Neural Style Transfer with Arbitrary Style using AdaIN Layer - Based on Huang et al. "Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization"

deep-image-prior. Image restoration with neural networks but without learning.

pix2pixHD. Synthesizing and manipulating 2048x1024 images with conditional GANs

matplotlib_for_papers. Handout for the tutorial "Creating publication-quality figures with matplotlib"

TTUR. Two time-scale update rule for training GANs

BGAN. boundary-seeking generative adversarial networks

coulomb_gan. Implementation of Coulomb GANs

deep-voice-conversion. Deep neural networks for voice conversion (voice style transfer) in Tensorflow

progressive_growing_of_gans. Progressive Growing of GANs for Improved Quality, Stability, and Variation

densevid_eval. Evaluation code for Dense-Captioning Events in Videos

UNIT. Unsupervised Image-to-Image Translation

UniversalStyleTransfer. The source code of NIPS17 'Universal Style Transfer via Feature Transforms'.

rl-attack-detection. Code for "Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight"

iaf. Code for reproducing key results in the paper "Improving Variational Inference with Inverse Autoregressive Flow"

vae_vampprior. Code for the paper "VAE with a VampPrior", J.M. Tomczak & M. Welling

pointnet2. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

channel-pruning. Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)

drnet. Lua

Hierarchical-Model-for-Long-term-Video-Prediction. Given the previous frames of the video as input, we want to get the long-term frame prediction.

chainer-gan-lib. Chainer implementation of recent GAN variants

SSGAN-Tensorflow. A Tensorflow implementation of Semi-supervised Learning Generative Adversarial Networks (NIPS 2016: Improved Techniques for Training GANs).

lr-gan.pytorch. Pytorch code for our ICLR 2017 paper "Layered-Recursive GAN for image generation"

pysc2. StarCraft II Learning Environment

cegan_iclr2017. Code release for the paper "Calibrating Energy-based Generative Adversarial Networks"

mocogan. MoCoGAN: Decomposing Motion and Content for Video Generation

maml. Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

pytorch-visdom. Support powerful visual logging in PyTorch.

meta-learning-lstm. This repo contains the source code accompanying a scientific paper with the same name.

ntm-one-shot. One-shot Learning with Memory-Augmented Neural Networks

revnet-public. Code for "The Reversible Residual Network: Backpropagation Without Storing Activations"

MemNN. Memory Networks implementations

Neural-Style-Transfer-Papers. :pencil2: Neural Style Transfer: A Review

treelstm.pytorch. Tree LSTM implementation in PyTorch

drnet_cvpr2017. Detecting Visual Relationships with Deep Relational Networks

svg. A Python SVG parser and drawing module

multimodal_transfer. tensorflow implementation of 'Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer'

tf-AdaIN. AdaIN style transfer in Tensorflow

vqa.pytorch. Visual Question Answering in Pytorch

dsprites-dataset. Dataset to assess the disentanglement properties of unsupervised learning methods

rnn.wgan. Code for training and evaluation of the model from "Language Generation with Recurrent Generative Adversarial Networks without Pre-training"

DistanceGAN. Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017

pytorch-a3c. PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".

awesome-vqa. Visual Q&A reading list

baselines. OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

pointGAN. point set generative adversarial nets

Deep-Image-Analogy. The source code of 'Visual Attribute Transfer through Deep Image Analogy'.

really-awesome-gan. A list of papers on Generative Adversarial (Neural) Networks

the-incredible-pytorch. The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

awesome-adversarial-machine-learning. A curated list of awesome adversarial machine learning resources

noreward-rl. [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

Deep-Feature-Flow. Deep Feature Flow for Video Recognition

clevr-iep. Inferring and Executing Programs for Visual Reasoning

fairseq-lua. Facebook AI Research Sequence-to-Sequence Toolkit

deep-learning-papers. Papers about deep learning ordered by task, date. Current state-of-the-art papers are labelled.

bigan. code for "Adversarial Feature Learning"

textfool. Plausible looking adversarial examples for text classification

unreal. Reinforcement learning with unsupervised auxiliary tasks

NAS-Bench-201. NAS-Bench-201 API and Instruction

videoseg. [CVPR 2017] Video motion segmentation and tracking

AdaIN-style. AdaIN-style live demo @ Labokube - Belkium - Brussels - Digital art jam 8-16/04/2017

visdial. [CVPR 2017] Torch code for Visual Dialog

LapSRN. Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (CVPR 2017)

tempens. Temporal ensembling for semi-supervised learning

3D-R2N2. Single/multi view image(s) to voxel reconstruction using a recurrent neural network

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

PointSetGeneration. Code for ``A Point Set Generation Network for 3D Object Reconstruction from a Single Image''

conditional-similarity-networks. Python

adversarial-frcnn. A-Fast-RCNN (CVPR 2017)

AGE. Code for the paper "Adversarial Generator-Encoder Networks"

3dinn. Single Image 3D Interpreter Network

scene-graph-TF-release. "Scene Graph Generation by Iterative Message Passing" code repository

improved_wgan_training. Code for reproducing experiments in "Improved Training of Wasserstein GANs"

fast-artistic-videos. Arbitrary Style Transfer for Videos with Adaptive Instance Normalization https://arxiv.org/abs/1703.06868

DT-RAM. Lua

nets. Draw your net

CycleGAN. Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

octnet. OctNet: Learning Deep 3D Representations at High Resolutions

DeepBach. code accompanying "DeepBach: a Steerable Model for Bach Chorales Generation" paper

sact. Spatially Adaptive Computation Time for Residual Networks

cleverhans. An adversarial example library for constructing attacks, building defenses, and benchmarking both

triplet-network-pytorch. Python

dynamics. A Compositional Object-Based Approach to Learning Physical Dynamics

deep-photo-styletransfer. Code and data for paper "Deep Photo Style Transfer": https://arxiv.org/abs/1703.07511

XNOR-Net. ImageNet classification using binary Convolutional Neural Networks

PixelNet. The repository contains source code and models to use PixelNet architecture used for various pixel-level tasks. More details can be accessed at <http://www.cs.cmu.edu/~aayushb/pixelNet/>.

AdaIN-style. Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

DiscoGAN. Official implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"

DiscoGAN-pytorch. PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"

Fast_Multi_Style_Transfer-tensorflow. Multi style transfer. You can make Gogh + Manet + Picasso style image

NeuralImageSynthesis. Code to reproduce the results from the paper "Controlling Perceptual Factors in Neural Style Transfer" (https://arxiv.org/abs/1611.07865).

splitbrainauto. Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction. In CVPR, 2017.

shake-shake. 2.86% and 15.85% on CIFAR-10 and CIFAR-100

image-analogies. Generate image analogies using neural matching and blending.

painters. :art: Winning solution for the Painter by Numbers competition on Kaggle.

Faster-High-Res-Neural-Inpainting. High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis

fast-pixel-cnn. Speed up PixelCNN++ image generation by up to a 183 times

textvae. Theano code for experiments in the paper "A Hybrid Convolutional Variational Autoencoder for Text Generation."

densenet-pytorch. A PyTorch Implementation for Densely Connected Convolutional Networks (DenseNets)

Neural-Dialogue-Generation. Lua

lsgan. This is the project for LS-GAN (Loss-Sensitive GAN)

quasi-rnn. Character-level Neural Translation using Quasi-RNNs

ResNeXt. Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

WassersteinGAN. Python

magenta. Magenta: Music and Art Generation with Machine Intelligence

fast-neural-style. Feedforward style transfer

style-swap. code for "Fast Patch-based Style Transfer of Arbitrary Style".

gmmn. Generative moment matching networks

opt-mmd. Learning kernels to maximize the power of MMD tests

newtonian. Lua

simulated-unsupervised-tensorflow. TensorFlow implementation of "Learning from Simulated and Unsupervised Images through Adversarial Training"

deepdecoder. Python

tf-dann. Domain-Adversarial Neural Network in Tensorflow

chainer-gan-denoising-feature-matching. Chainer implementation of Improving Generative Adversarial Networks with Denoising Feature Matching

mcic-coco.

dpnn. deep extensions to nn

3dgan-release. 3D Generative Adversarial Network

PixelDTGAN. A torch implementation of "Pixel-Level Domain Transfer"

c-rnn-gan. Implementation of C-RNN-GAN.

unsupervised-videos. Unsupervised Learning of Video Representations using LSTMs

videogan. Generating Videos with Scene Dynamics. NIPS 2016.

MIXER. Mixed Incremental Cross-Entropy REINFORCE ICLR 2016

real-nvp. Implementation of Real-NVP in Tensorflow

LSTM-Generative-and-Discriminative. Python

SGAN. Stacked Generative Adversarial Networks

ganhacks. starter from "How to Train a GAN?" at NIPS2016

ppgn. Code for paper "Plug and Play Generative Networks"

autoencoding_beyond_pixels. Generative image model with learned similarity measures

VideoPredictionICLR2016. Lua

npy4th. Numpy format for Torch

lab. A customisable 3D platform for agent-based AI research

learning-to-learn. Learning to Learn in TensorFlow