| Likelihood regret: An out-of-distribution detection score for variational auto-encoder Z Xiao, Q Yan, Y Amit Advances in neural information processing systems 33, 20685-20696, 2020 | 180 | 2020 |
| Generative latent flow Z Xiao, Q Yan, Y Amit arXiv preprint arXiv:1905.10485, 2019 | 33 | 2019 |
| Do we really need to learn representations from in-domain data for outlier detection? Z Xiao, Q Yan, Y Amit arXiv preprint arXiv:2105.09270, 2021 | 20 | 2021 |
| Generative latent flow: A framework for non-adversarial image generation Z Xiao, Q Yan, Y Chen, Y Amit arXiv preprint arXiv:1905.10485, 2019 | 13 | 2019 |
| A method to model conditional distributions with normalizing flows Z Xiao, Q Yan, Y Amit arXiv preprint arXiv:1911.02052, 2019 | 9 | 2019 |
| Exponential tilting of generative models: Improving sample quality by training and sampling from latent energy Z Xiao, Q Yan, Y Amit arXiv preprint arXiv:2006.08100, 2020 | 7 | 2020 |
| Ebms trained with maximum likelihood are generator models trained with a self-adverserial loss Z Xiao, Q Yan, Y Amit arXiv preprint arXiv:2102.11757, 2021 | 3 | 2021 |
| System and a method for training a neural network having autoencoder architecture to recover missing data E Laftchiev, Q Yan, D Nikovski US Patent 11,698,946, 2023 | | 2023 |
| Deep Generative Models: Design, Improvements and Applications Q Yan The University of Chicago, 2022 | | 2022 |
| The Missing Input Problem E Laftchiev, Q Yan, D Nikovski 2020 IEEE International Conference on Big Data (Big Data), 1565-1573, 2020 | | 2020 |
| Improving Sample Quality by Training and Sampling from Latent Energy Z Xiao, Q Yan, Y Amit | | |
