Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Arash Vahdat

Score-Based Generative Modeling with Critically-Damped Langevin Diffusion


Dec 30, 2021
Tim Dockhorn, Arash Vahdat, Karsten Kreis


  Access Paper or Ask Questions

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs


Dec 15, 2021
Zhisheng Xiao, Karsten Kreis, Arash Vahdat


  Access Paper or Ask Questions

AdaViT: Adaptive Tokens for Efficient Vision Transformer


Dec 14, 2021
Hongxu Yin, Arash Vahdat, Jose Alvarez, Arun Mallya, Jan Kautz, Pavlo Molchanov


  Access Paper or Ask Questions

Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence


Nov 29, 2021
Tianshi Cao, Alex Bie, Arash Vahdat, Sanja Fidler, Karsten Kreis

* Accepted to NeurIPS 2021. 13 pages, 7 pages of supplementary; 6 tables, 8 figures 

  Access Paper or Ask Questions

Controllable and Compositional Generation with Latent-Space Energy-Based Models


Oct 21, 2021
Weili Nie, Arash Vahdat, Anima Anandkumar

* 32 pages, NeurIPS 2021 

  Access Paper or Ask Questions

HANT: Hardware-Aware Network Transformation


Jul 12, 2021
Pavlo Molchanov, Jimmy Hall, Hongxu Yin, Jan Kautz, Nicolo Fusi, Arash Vahdat


  Access Paper or Ask Questions

Score-based Generative Modeling in Latent Space


Jun 10, 2021
Arash Vahdat, Karsten Kreis, Jan Kautz


  Access Paper or Ask Questions

Multi-task Transformation Learning for Robust Out-of-Distribution Detection


Jun 07, 2021
Sina Mohseni, Arash Vahdat, Jay Yadawa


  Access Paper or Ask Questions

See through Gradients: Image Batch Recovery via GradInversion


Apr 15, 2021
Hongxu Yin, Arun Mallya, Arash Vahdat, Jose M. Alvarez, Jan Kautz, Pavlo Molchanov

* CVPR 2021 accepted paper 

  Access Paper or Ask Questions

NCP-VAE: Variational Autoencoders with Noise Contrastive Priors


Oct 06, 2020
Jyoti Aneja, Alexander Schwing, Jan Kautz, Arash Vahdat

* 22 pages including appendix 

  Access Paper or Ask Questions

VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models


Oct 01, 2020
Zhisheng Xiao, Karsten Kreis, Jan Kautz, Arash Vahdat

* 32 pages including appendix 

  Access Paper or Ask Questions

NVAE: A Deep Hierarchical Variational Autoencoder


Jul 08, 2020
Arash Vahdat, Jan Kautz

* Some images are downsized to meet arXiv requirements. Check https://arash-vahdat.github.io/NVAE_arxiv.pdf for a high-resolution version (24 MB) 

  Access Paper or Ask Questions

Contrastive Learning for Weakly Supervised Phrase Grounding


Jun 17, 2020
Tanmay Gupta, Arash Vahdat, Gal Chechik, Xiaodong Yang, Jan Kautz, Derek Hoiem


  Access Paper or Ask Questions

On the distance between two neural networks and the stability of learning


Feb 09, 2020
Jeremy Bernstein, Arash Vahdat, Yisong Yue, Ming-Yu Liu


  Access Paper or Ask Questions

UNAS: Differentiable Architecture Search Meets Reinforcement Learning


Dec 16, 2019
Arash Vahdat, Arun Mallya, Ming-Yu Liu, Jan Kautz


  Access Paper or Ask Questions

A Robust Learning Approach to Domain Adaptive Object Detection


Apr 04, 2019
Mehran Khodabandeh, Arash Vahdat, Mani Ranjbar, William G. Macready


  Access Paper or Ask Questions

Learning Undirected Posteriors by Backpropagation through MCMC Updates


Jan 11, 2019
Arash Vahdat, Evgeny Andriyash, William G. Macready


  Access Paper or Ask Questions

Weakly Supervised Semantic Image Segmentation with Self-correcting Networks


Nov 17, 2018
Mostafa S. Ibrahim, Arash Vahdat, William G. Macready


  Access Paper or Ask Questions

DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors


Oct 15, 2018
Arash Vahdat, Evgeny Andriyash, William G. Macready

* Neural Information Processing Systems (NIPS) 2018 

  Access Paper or Ask Questions

Improved Gradient-Based Optimization Over Discrete Distributions


Sep 29, 2018
Evgeny Andriyash, Arash Vahdat, Bill Macready


  Access Paper or Ask Questions

DVAE++: Discrete Variational Autoencoders with Overlapping Transformations


May 25, 2018
Arash Vahdat, William G. Macready, Zhengbing Bian, Amir Khoshaman, Evgeny Andriyash

* Published as a conference paper at International Conference on Machine Learning (ICML), 2018 

  Access Paper or Ask Questions

Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks


Nov 03, 2017
Arash Vahdat

* To appear in Neural Information Processing Systems (NIPS) 2017 

  Access Paper or Ask Questions

Hierarchical Deep Temporal Models for Group Activity Recognition


Jul 09, 2016
Mostafa S. Ibrahim, Srikanth Muralidharan, Zhiwei Deng, Arash Vahdat, Greg Mori

* arXiv admin note: text overlap with arXiv:1511.06040 

  Access Paper or Ask Questions

Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition


Apr 12, 2016
Zhiwei Deng, Arash Vahdat, Hexiang Hu, Greg Mori

* CVPR 2016 

  Access Paper or Ask Questions

A Hierarchical Deep Temporal Model for Group Activity Recognition


Apr 05, 2016
Moustafa Ibrahim, Srikanth Muralidharan, Zhiwei Deng, Arash Vahdat, Greg Mori

* cs.cv Accepted to CVPR 2016 

  Access Paper or Ask Questions

Visual Recognition by Counting Instances: A Multi-Instance Cardinality Potential Kernel


Apr 09, 2015
Hossein Hajimirsadeghi, Wang Yan, Arash Vahdat, Greg Mori


  Access Paper or Ask Questions

Discovering Human Interactions in Videos with Limited Data Labeling


Feb 12, 2015
Mehran Khodabandeh, Arash Vahdat, Guang-Tong Zhou, Hossein Hajimirsadeghi, Mehrsan Javan Roshtkhari, Greg Mori, Stephen Se


  Access Paper or Ask Questions