7 papers
Wasserstein Residuals: Learning Gradient Flows from Population Dynamics
Markus Heinonen, Yair Shenfeld, Ricardo Baptista +4
Reconstructing population dynamics is a central problem in the physical and data sciences. Often, the dynamics are modeled as a Wasserstein gradient flow (WGF): a curve of distribu…
The Spacetime of Diffusion Models: An Information Geometry Perspective
RafaÅ Karczewski, Markus Heinonen, Alison Pouplin +2
We present a novel geometric perspective on the latent space of diffusion models. We first show that the standard pullback approach, utilizing the deterministic probability flow OD…
Let Physics Guide Your Protein Flows: Topology-aware Unfolding and Generation
Yogesh Verma, Markus Heinonen, Vikas Garg
Protein structure prediction and folding are fundamental to understanding biology, with recent deep learning advances reshaping the field. Diffusion-based generative models have re…
Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models
RafaÅ Karczewski, Markus Heinonen, Vikas Garg
Diffusion models have emerged as a powerful class of generative models, capable of producing high-quality images by mapping noise to a data distribution. However, recent findings s…
Diffusion Models as Cartoonists: The Curious Case of High Density Regions
RafaÅ Karczewski, Markus Heinonen, Vikas Garg
We investigate what kind of images lie in the high-density regions of diffusion models. We introduce a theoretical mode-tracking process capable of pinpointing the exact mode of th…
E(3)-equivariant models cannot learn chirality: Field-based molecular generation
Alexandru Dumitrescu, Dani Korpela, Markus Heinonen +4
Obtaining the desired effect of drugs is highly dependent on their molecular geometries. Thus, the current prevailing paradigm focuses on 3D point-cloud atom representations, utili…