paper-conference

We present FoldFlow a novel flow matching model for protein design. We present theory and practical tricks for flow models over SE(3)^N. Empirically, we validate these models on protein backbone generation of up to 300 amino acids leading to high-quality designable, diverse, and novel samples.

We present simulation-free score and flow matching ([SF]2M), a simulation-free objective for inferring stochastic dynamics given …

One of the grand challenges of cell biology is inferring the gene regulatory network (GRN) which describes interactions between genes …

Efficient computation of optimal transport distance between distributions is of growing importance in data science. Sinkhorn-based …

We present methods for learning simple flows over R^d with optimal transport conditional flow matching (OT-CFM). Training with this objective leads to imprved results on a variety of conditional and unconditional generation tasks, such as inferring single cell dynamics, unsupervised image translation, and Schrodinger bridge inference.

While numerous methods have been proposed for computing distances between probability distributions in Euclidean space, relatively …

We present a method called Manifold Interpolating Optimal-Transport Flow (MIOFlow) that learns stochastic, continuous population …

In modern relational machine learning it is common to encounter large graphs that arise via interactions or similarities between …