Oskar Kviman
Ph.D. student working in the Lagergren Lab at KTH, Stockholm.
email: okviman@kth.se or okviman@gmail.com
Research interests
Generative AI: flow matching, Schrödinger bridges, diffusion models, variational autoencoders, generative adversarial networks, normalizing flows;
Computational cancer: differential expression testing, spatial transcriptomics, scRNA-seq, phylogenetics;
Statistical inference: variational inference, sequential Monte Carlo, optimal transport, MCMC, statistical testing;
Conference Publications/Preprints
- Multi-Marginal Flow Matching with Adversarially Learnt Interpolants, full-length version of our workshop paper in Frontiers in Probabilistic Inference 2025 (with Kirill Tamogashev, Nicola Branchini, Víctor Elvira, Jens Lagergren and Nikolay Malkin)
- On the Bias of Variational Resampling, submitted to an ML conference 2025 (with Axel Finke, Nicola Branchini and Víctor Elvira)
- LN’s t-test: A Principled Approach to t-testing in scRNA-seq, bioRxiv (with Seong-Hwan Jun and Jens Lagergren)
- Efficient Mixture Learning in Black-Box Variational Inference, ICML 2024 (with Alexandra Hotti, Ricky Molén, Víctor Elvira and Jens Lagergren)
- Indirectly Parameterized Concrete Autoencoders, ICML 2024 (with Alfred Nilsson, Klas Wijk, Sai Bharath Chandra Gutha, Erik Englesson, Alexandra Hotti, Carlo Saccardi, Jens Lagergren, Ricardo Vinuesa and Hossein Azizpour)
- Variational Resampling, AISTATS 2024 (with Nicola Branchini, Víctor Elvira and Jens Lagergren)
- Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoders, ICML 2023 (with Ricky Molén, Alexandra Hotti, Semih Kurt, Víctor Elvira and Jens Lagergren)
- VaiPhy: a Variational Inference Based Algorithm for Phylogeny, [Oral] NeurIPS 2022 (with Hazal Koptagel, Harald Melin, Negar Safinianaini and Jens Lagergren)
- Multiple Importance Sampling ELBO and Deep Ensembles of Variational Approximations, AISTATS 2022 (with Harald Melin, Hazal Koptagel, Víctor Elvira and Jens Lagergren) [5-min presentation]
- Statistical Distance Based Deterministic Offspring Selection in SMC Methods, arxiv (with Hazal Koptagel, Harald Melin and Jens Lagergren)
- Sequence Disambiguation with Synaptic Traces in Associative Neural Networks, ICANN 2019 (with Ramon H. Martinez, Anders Lansner and Pawel Herman)
Journal Publications
- Improved Variational Bayesian Phylogenetic Inference using Mixtures, TMLR 2024 (with Ricky Molén and Jens Lagergren)
- [Re] Tensor Monte Carlo: Particle Methods for the GPU Era, NeurIPS 2019 Reproducibility Challenge/ReScience-C Journal Publication (with Linus Nilsson and Martin Larsson
Theses
- KL/TV Reshuffling: Statistical Distance Based Offspring Selection in SMC Methods, Master Thesis 2020 (supervised by Jens Lagergren)
- Applicability of a Translucent Barrier Based Model of Noise, Bachelor Thesis 2018 (with Linus Nilsson; supervised by Saikat Chatterjee)
Acknowledged in
- Reinforced sequential Monte Carlo for amortised sampling
- PhyloGFN: Phylogenetic inference with generative flow networks
| Reviewing | Teaching at KTH | Master Thesis Supervision |
|---|---|---|
| ICLR 2025 | Statistical Methods in Applied Computer Science (Lecturer; 2021-) | Xindi Liu (KTH; 2022) |
| AAAI 2025 | Machine Learning, Advanced Course (TA; 2020-2022) | Ricky Molén (KTH; 2022) |
| NerIPS 2025 | Deep Learning, Advanced Course (TA; 2021-2022) | |
| Advances in approximate Bayesian inference 2023 | ||
| NeurIPS 2023 | ||
| AISTATS 2023: rewarded Top reviewer (10%; link) | ||
| NeurIPS 2022 | ||
| ICML 2022 | ||
| AISTATS 2022 | ||
| ICML 2021 |