Our latest work

Featured work from the group members

*
AbODE: Ab initio Antibody Design using Conjoined ODEs

AbODE: Ab initio Antibody Design using Conjoined ODEs

we propose a generative model for antibody design using conjoined interacting neural ODEs

Modular Flows: Differential Molecular Generation

Modular Flows: Differential Molecular Generation

We propose generative graph normalizing flow models, based on a system of coupled node ODEs, that repeatedly reconcile locally toward globally aligned densities for high quality molecular generation.

Provably expressive temporal graph networks

Provably expressive temporal graph networks

We analyze the representational power and limits of modern models for (event-based) temporal graphs. We leverage our theoretical insights to introduce an architecture that is provably more expressive than existing ones.

Symmetry-induced Disentanglement on Graphs

Symmetry-induced Disentanglement on Graphs

A new formalism for disentanglement on graphs.

Why GANs are overkill for NLP

This work offers a novel theoretical perspective on why, despite numerous attempts, adversarial approaches to generative modeling …