Markus Heinonen

Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models ICML 2025 Diffusion Models as Cartoonists: The Curious Case of High Density Regions ICLR 2025 E(3)-equivariant models cannot learn chirality: Field-based molecular generation ICLR 2025 Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models ICLR 2025 Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs ICLR 2025 From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport CVPR 2025 Progressive Tempering Sampler with Diffusion ICML 2025 Robust Classification by Coupling Data Mollification with Label Smoothing AISTATS 2025 What Ails Generative Structure-based Drug Design: Expressivity is Too Little or Too Much? AISTATS 2025 ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs ICLR 2024 Improving robustness to corruptions with multiplicative weight perturbations NeurIPS 2024 Input-gradient space particle inference for neural network ensembles ICLR 2024 AbODE: Ab initio antibody design using conjoined ODEs ICML 2023 Continuous-Time Functional Diffusion Processes NeurIPS 2023 Generative Modelling with Inverse Heat Dissipation ICLR 2023 Incorporating functional summary information in Bayesian neural networks using a Dirichlet process likelihood approach AISTATS 2023 Latent Neural ODEs with Sparse Bayesian Multiple Shooting ICLR 2023 Learning Space-Time Continuous Latent Neural PDEs from Partially Observed States NeurIPS 2023 Modular Flows: Differential Molecular Generation NeurIPS 2022 Tackling covariate shift with node-based Bayesian neural networks ICML 2022 Variational multiple shooting for Bayesian ODEs with Gaussian processes UAI 2022 Bayesian Inference for Optimal Transport with Stochastic Cost ACML 2021 Continuous-time Model-based Reinforcement Learning ICML 2021 De-randomizing MCMC dynamics with the diffusion Stein operator NeurIPS 2021 Learning continuous-time PDEs from sparse data with graph neural networks ICLR 2021 Sparse Gaussian Processes Revisited: Bayesian Approaches to Inducing-Variable Approximations AISTATS 2021 Learning spectrograms with convolutional spectral kernels AISTATS 2020 Deep learning with differential Gaussian process flows AISTATS 2019 Harmonizable mixture kernels with variational Fourier features AISTATS 2019 ODE2VAE: Deep generative second order ODEs with Bayesian neural networks NeurIPS 2019 Learning unknown ODE models with Gaussian processes ICML 2018 A Mutually-Dependent Hadamard Kernel for Modelling Latent Variable Couplings ACML 2017 Non-Stationary Spectral Kernels NeurIPS 2017 Non-Stationary Gaussian Process Regression with Hamiltonian Monte Carlo AISTATS 2016 Random Fourier Features For Operator-Valued Kernels ACML 2016