wangkua1
Research Scientist at Snap Inc. Prev: Postdoc at Stanford CS. PhD from UofT and the Vector Institute.
Snap Inc.Mountain View, California
Pinned Repositories
ais
Annealed Importance Sampling (AIS) for generative models.
apd_public
Code for "Adversarial Distillation of Bayesian Neural Network Posteriors" https://arxiv.org/abs/1806.10317
BDMC
PyTorch implementation of Bidirectional Monte Carlo, Annealed Importance Sampling, and Hamiltonian Monte Carlo
cinic-10
A drop-in replacement for CIFAR-10.
cleverhans
A library for benchmarking vulnerability to adversarial examples
CloserLookFewShot
source code to ICLR'19, 'A Closer Look at Few-shot Classification'
fs-ood
Kuan-Chieh Wang, Paul Vicol, Eleni Triantafillou, Richard Zemel. (2020). “Few-shot Out-of-Distribution Detection.” (ICML) Workshop on Uncertainty and Robustness in Deep Learning
nemo-cvpr2023
[CVPR 2023 Highlight] Official implementation of "NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action"
sportvu
vmi
Code for "Variational Model Inversion Attacks" Wang et al., NeurIPS2021
wangkua1's Repositories
wangkua1/nemo-cvpr2023
[CVPR 2023 Highlight] Official implementation of "NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action"
wangkua1/vmi
Code for "Variational Model Inversion Attacks" Wang et al., NeurIPS2021
wangkua1/apd_public
Code for "Adversarial Distillation of Bayesian Neural Network Posteriors" https://arxiv.org/abs/1806.10317
wangkua1/fs-ood
Kuan-Chieh Wang, Paul Vicol, Eleni Triantafillou, Richard Zemel. (2020). “Few-shot Out-of-Distribution Detection.” (ICML) Workshop on Uncertainty and Robustness in Deep Learning
wangkua1/sportvu
wangkua1/ais
Annealed Importance Sampling (AIS) for generative models.
wangkua1/BDMC
PyTorch implementation of Bidirectional Monte Carlo, Annealed Importance Sampling, and Hamiltonian Monte Carlo
wangkua1/cinic-10
A drop-in replacement for CIFAR-10.
wangkua1/CloserLookFewShot
source code to ICLR'19, 'A Closer Look at Few-shot Classification'
wangkua1/data-efficient-gans
Differentiable Augmentation for Data-Efficient GAN Training
wangkua1/dci-knn
Fast k-Nearest Neighbour Search using Dynamic Continuous Indexing (DCI)
wangkua1/EverybodyDanceNow
Motion Retargeting Video Subjects
wangkua1/GLAMR
[CVPR 2022 Oral] Official PyTorch Implementation of "GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras”.
wangkua1/Glow-PyTorch
Simple, extendable, easy to understand Glow implementation in PyTorch
wangkua1/group_DRO
Distributionally robust neural networks for group shifts
wangkua1/improved_wgan_training
Code for reproducing experiments in "Improved Training of Wasserstein GANs"
wangkua1/InsightFace_Pytorch
Pytorch0.4.1 codes for InsightFace
wangkua1/mixmatch
wangkua1/motion-diffusion-model
The official PyTorch implementation of the paper "Human Motion Diffusion Model"
wangkua1/neural-statistician
PyTorch Implementation of Neural Statistician
wangkua1/normalizing_flows
Pytorch implementations of density estimation algorithms: BNAF, Glow, MAF, RealNVP, planar flows
wangkua1/NVAE
The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)
wangkua1/pytorch-fid
A Port of Fréchet Inception Distance (FID score) to PyTorch
wangkua1/releasing-research-code
Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)
wangkua1/robustness
Corruption and Perturbation Robustness (ICLR 2019)
wangkua1/ssl_bad_gan
Good Semi-Supervised Learning That Requires a Bad GAN
wangkua1/stylegan2-ada-pytorch
StyleGAN2-ADA - Official PyTorch implementation
wangkua1/VIBE
Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
wangkua1/view_neti
wangkua1/wangkua1.github.io
A beautiful, simple, clean, and responsive Jekyll theme for academics