Markus Heinonen

PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inference

The Spacetime of Diffusion Models: An Information Geometry Perspective

Optimizing Data Augmentation through Bayesian Model Selection

Scaling Laws for Uncertainty in Deep Learning

Let Physics Guide Your Protein Flows: Topology-aware Unfolding and Generation

E(3)-equivariant models cannot learn chirality: Field-based molecular generation

Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models

Diffusion Models as Cartoonists: The Curious Case of High Density Regions

Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs

Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models

Progressive Tempering Sampler with Diffusion