| 2025 | AISTATS | Robust Classification by Coupling Data Mollification with Label Smoothing. | Markus Heinonen, Ba-Hien Tran, Michael Kampffmeyer, Maurizio Filippone |
| 2025 | AISTATS | What Ails Generative Structure-based Drug Design: Expressivity is Too Little or Too Much? | Rafal Karczewski, Samuel Kaski, Markus Heinonen, Vikas K. Garg |
| 2025 | CVPR | From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport. | Quentin Bouniot, Ievgen Redko, Anton Mallasto, Charlotte Laclau, Oliver Struckmeier, Karol Arndt, Markus Heinonen, Ville Kyrki, Samuel Kaski |
| 2025 | ICLR | E(3)-equivariant models cannot learn chirality: Field-based molecular generation. | Alexandru Dumitrescu, Dani Korpela, Markus Heinonen, Yogesh Verma, Valerii Iakovlev, Vikas Garg, Harri Lhdesmki |
| 2025 | ICLR | Diffusion Models as Cartoonists: The Curious Case of High Density Regions. | Rafal Karczewski, Markus Heinonen, Vikas Garg |
| 2025 | ICLR | Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models. | Najwa Laabid, Severi Rissanen, Markus Heinonen, Arno Solin, Vikas Garg |
| 2025 | ICLR | Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs. | Severi Rissanen, Markus Heinonen, Arno Solin |
| 2025 | ICML | Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models. | Rafal Karczewski, Markus Heinonen, Vikas K. Garg |
| 2025 | ICML | Progressive Tempering Sampler with Diffusion. | Severi Rissanen, Ruikang Ouyang, Jiajun He, Wenlin Chen, Markus Heinonen, Arno Solin, Jos Miguel Hernndez-Lobato |
| 2024 | ICANN | Balancing Imbalanced Toxicity Models: Using MolBERT with Focal Loss. | Muhammad Arslan Masood, Samuel Kaski, Hugo Ceulemans, Dorota Herman, Markus Heinonen |
| 2024 | ICANN | Towards Interpretable Models of Chemist Preferences for Human-in-the-Loop Assisted Drug Discovery. | Yasmine Nahal, Markus Heinonen, Mikhail Kabeshov, Jon Paul Janet, Eva Nittinger, Ola Engkvist, Samuel Kaski |
| 2024 | ICLR | Input-gradient space particle inference for neural network ensembles. | Trung Q. Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski |
| 2024 | ICLR | ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs. | Yogesh Verma, Markus Heinonen, Vikas Garg |
| 2023 | AISTATS | Incorporating functional summary information in Bayesian neural networks using a Dirichlet process likelihood approach. | Vishnu Raj, Tianyu Cui, Markus Heinonen, Pekka Marttinen |
| 2023 | ICLR | Latent Neural ODEs with Sparse Bayesian Multiple Shooting. | Valerii Iakovlev, agatay Yildiz, Markus Heinonen, Harri Lhdesmki |
| 2023 | ICLR | Generative Modelling with Inverse Heat Dissipation. | Severi Rissanen, Markus Heinonen, Arno Solin |
| 2023 | ICML | AbODE: Ab initio antibody design using conjoined ODEs. | Yogesh Verma, Markus Heinonen, Vikas Garg |
| 2022 | ICML | Tackling covariate shift with node-based Bayesian neural networks. | Trung Q. Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski |
| 2022 | UAI | Variational multiple shooting for Bayesian ODEs with Gaussian processes. | Pashupati Hegde, agatay Yildiz, Harri Lhdesmki, Samuel Kaski, Markus Heinonen |
| 2021 | ACML | Bayesian Inference for Optimal Transport with Stochastic Cost. | Anton Mallasto, Markus Heinonen, Samuel Kaski |
| 2021 | AISTATS | Sparse Gaussian Processes Revisited: Bayesian Approaches to Inducing-Variable Approximations. | Simone Rossi, Markus Heinonen, Edwin V. Bonilla, Zheyang Shen, Maurizio Filippone |
| 2021 | ICLR | Learning continuous-time PDEs from sparse data with graph neural networks. | Valerii Iakovlev, Markus Heinonen, Harri Lhdesmki |
| 2021 | ICML | Continuous-time Model-based Reinforcement Learning. | agatay Yildiz, Markus Heinonen, Harri Lhdesmki |
| 2020 | AISTATS | Learning spectrograms with convolutional spectral kernels. | Zheyang Shen, Markus Heinonen, Samuel Kaski |
| 2019 | AISTATS | Deep learning with differential Gaussian process flows. | Pashupati Hegde, Markus Heinonen, Harri Lhdesmki, Samuel Kaski |
| 2019 | AISTATS | Harmonizable mixture kernels with variational Fourier features. | Zheyang Shen, Markus Heinonen, Samuel Kaski |
| 2018 | ICML | Learning unknown ODE models with Gaussian processes. | Markus Heinonen, agatay Yildiz, Henrik Mannerstrm, Jukka Intosalmi, Harri Lhdesmki |
| 2018 | UAI | Variational zero-inflated Gaussian processes with sparse kernels. | Pashupati Hegde, Markus Heinonen, Samuel Kaski |
| 2017 | ACML | A Mutually-Dependent Hadamard Kernel for Modelling Latent Variable Couplings. | Sami Remes, Markus Heinonen, Samuel Kaski |
| 2016 | ACML | Random Fourier Features For Operator-Valued Kernels. | Romain Brault, Markus Heinonen, Florence d'Alch-Buc |
| 2016 | AISTATS | Non-Stationary Gaussian Process Regression with Hamiltonian Monte Carlo. | Markus Heinonen, Henrik Mannerstrm, Juho Rousu, Samuel Kaski, Harri Lhdesmki |