Emiel Hoogeboom
PhD Candidate
(advised by Max Welling)
Delta Lab
Institute of Informatics
University of Amsterdam
Emiel Hoogeboom and is a PhD Candidate at the University of Amsterdam under the supervision of Max Welling, in the UvA-Bosch Delta Lab. Research interests include deep generative models and molecular generation.
Selected Publications
-
ICLRAutoregressive Diffusion ModelsIn International Conference on Learning Representations, ICLR Jul 2022
-
arXivEquivariant Diffusion for Molecule Generation in 3DCoRR Jul 2022
-
AABILearning Discrete Distributions by DequantizationIn 3rd Symposium on Advances in Approximate Bayesian Inference, AABI Jul 2021
-
NeurIPSArgmax Flows and Multinomial Diffusion: Learning Categorical DistributionsIn Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems, NeurIPS Jul 2021
-
NeurIPSE(n) Equivariant Normalizing FlowsIn Advances in Neural Information Processing Systems, NeurIPS Jul 2021
-
ICMLSelf Normalizing FlowsIn Proceedings of the 38th International Conference on Machine Learning, ICML Jul 2021
-
INNF+Discrete Denoising FlowsIn ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models Jul 2021
-
AABIVariational Determinant Estimation with Spherical Normalizing FlowsIn Third Symposium on Advances in Approximate Bayesian Inference, AABI Jul 2021
-
ICMLE(n) Equivariant Graph Neural NetworksIn Proceedings of the 38th International Conference on Machine Learning, ICML Jul 2021
-
NeurIPSThe Convolution Exponential and Generalized Sylvester FlowsIn Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS Jul 2020
-
NeurIPSSurVAE Flows: Surjections to Bridge the Gap between VAEs and FlowsIn Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS Jul 2020
-
ICMLPredictive Sampling with Forecasting Autoregressive ModelsIn Proceedings of the 37th International Conference on Machine Learning, ICML Jul 2020
-
ICMLEmerging Convolutions for Generative Normalizing FlowsIn Proceedings of the 36th International Conference on Machine Learning, ICML Jul 2019
-
NeurIPSInteger Discrete Flows and Lossless CompressionIn Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS Jul 2019
-
arXivLearning Likelihoods with Conditional Normalizing FlowsCoRR Jul 2019
-
ICLRHexaConvIn 6th International Conference on Learning Representations, ICLR Jul 2018