Pour le 21/01/2019
Travail à faire par binôme.
Choisir un papier dans la liste ci-dessous. Trouver un autre papier sur une thématique proche et qui ne soit pas dans la liste.
Préparer une présentation de 10 mn par binôme et un rapport de 4 pages max décrivant la problématique étudiée et le travail réalisé dans ces papiers.
Tout le monde assiste à toute la journée de présentation, dans la mesure du possible.
Modèles génératifs
Almahairi, A., Rajeswar, S., Sordoni, A., Bachman, P. and Courville, A. 2018. Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data. ICML (2018), PMLR 80:195-204.
Dinh, L., Sohm-Dickstein, J. and Bengio, S. 2017. Density Estimation using Real NVP. Iclr (2017).
Grathwohl, W., Chen, R.T.Q., Bettencourt, J., Sutskever, I. and Duvenaud, D. 2019. FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models. ICLR (2019).
Kingma, D.P. and Dhariwal, P. 2018. Glow : Generative Flow with Invertible 1 ⇥ 1 Convolutions. NIPS (2018).
Pajot A., de Bezenac E., Gallinari P., Unsupervised Adversarial Image Reconstruction, ICLR 2019.
Systèmes dynamiques
Chen, T.Q., Rubanova, Y., Bettencourt, J. and Duvenaud, D. 1987. Neural Ordinary Differential Equations. (1987), 1–19. – best paper Nips 2018
Videos
Denton, E. and Birodkar, V. 2017. Unsupervised Learning of Disentangled Representations from Video. NIPS (2017), 4414–4423.
Denton, E. and Fergus, R. 2018. Stochastic Video Generation with a Learned Prior. ICML (2018), 1182–1191.
Lee, A.X., Zhang, R., Ebert, F., Abbeel, P., Finn, C. and Levine, S. 2018. Stochastic Variational Video Prediction. ICLR (2018).
Text generation and generative models
Subramanian, S., Sai, R., Sordoni, A., Trischler, A., Courville, A. and Pal, C. 2018. Towards Text Generation with Adversarially Learned Neural Outlines. Neural Information Processing Systems (NIPS). Nips (2018), 1–13.
Wang, H., Qin, Z. and Wan, T. 2018. Text generation based on generative adversarial nets with latent variables. (2018). ArXiv 1712.00170
Hu, Z., Yang, Z., Liang, X., Salakhutdinov, R. and Xing, E.P. 2017. Toward Controlled Generation of Text. ICML (2017), PMLR 70:1587-1596.
Xu, J., Ren, X., Lin, J. and Sun, X. 2018. DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text. EMNLP (2018).
Guan, J., Li, R., Yu, S. and Zhang, X. 2018. Generation of Synthetic Electronic Medical Record Text. 1812.02793v1 (2018)
Learning text representations
Peters, M.E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K. and Zettlemoyer, L. 2018. Deep contextualized word representations. NAACL (2018), 2227–2237.
Devlin, J., Chang, M.-W., Lee, K. and Toutanova, K. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. http://arxiv.org/abs/1810.04805 (2018).
Dialogue
Serban, I.V., Sordoni, A., Charlin, L., Pineau, J., Courville, A. and Bengio, Y. 2017. A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues. AAAI (2017), 3295–3301.