Paper-Conference

Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation
Proteins are essential for almost all biological processes and derive their diverse functions from complex 3D structures, which are in …
Guillaume Huguet*, James Vuckovic*, Kilian Fatras, Eric Thibodeau-Laufer, Pablo Lemos, Riashat Islam, Cheng-Hao Liu, Jarrid Rector-Brooks, Tara Akhound-Sadegh, Michael Bronstein, Alex Tong*, Avishek Joey Bose*
PDF Cite
Metric Flow Matching for Smooth Interpolations on the Data Manifold
Matching objectives underpin the success of modern generative models and rely on constructing conditional paths that transform a source …
Kacper Kapusniak, Peter Potaptchik, Teodora Reu, Leo Zhang, Alex Tong, Michael Bronstein, Avishek Joey Bose, Francesco Di Giovanni
PDF Cite Code Logg Video
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of …
Tara Akhound-Sadegh*, Jarrid Rector-Brooks*, Avishek Joey Bose*, Sarthak Mittal, Pablo Lemos, Cheng-Hao Liu, Marcin Sendera, Siamak Ravanbakhsh, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Alex Tong
PDF Cite Code
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
A Computational Framework for Solving Wasserstein Lagrangian Flows
The dynamical formulation of the optimal transport can be extended through various choices of the underlying geometry (kinetic energy), …
Kirill Neklyudov*, Rob Brekelmans*, Alex Tong, Lazar Atanackovic, Qiang Liu, Alireza Makhzani
PDF Cite Code
SE(3)-Stochastic Flow Matching for Protein Backbone Generation
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.
Avishek Joey Bose*, Tara Akhound-Sadegh*, Kilian Fatras, Guillaume Huguet, Jarrid Rector-Brooks, Cheng-Hao Liu, Andrei Cristian Nica, Maksym Korablyov, Michael Bronstein, Alex Tong
PDF Cite Code MoML Video Logg Video VantAI Video
SE(3)-Stochastic Flow Matching for Protein Backbone Generation
Simulation-Free Schrodinger Bridges via Score and Flow Matching
We present simulation-free score and flow matching ([SF]2M), a simulation-free objective for inferring stochastic dynamics given …
Alex Tong*, Nikolay Malkin*, Kilian Fatras*, Lazar Atanackovic, Yanlei Zhang, Guillaume Huguet, Guy Wolf, Yoshua Bengio
PDF Cite Code
A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction
Guillaume Huguet*, Alex Tong*, Edward De Brouwer*, Yanlei Zhang, Guy Wolf, Ian Adelstein, Smita Krishnaswamy
PDF Cite Code
DynGFN: Bayesian Dynamic Causal Discovery Using Generative Flow Networks
One of the grand challenges of cell biology is inferring the gene regulatory network (GRN) which describes interactions between genes …
Lazar Atanackovic*, Alex Tong*, Jason Hartford, Leo J. Lee, Bo Wang, Yoshua Bengio
PDF Cite Code
DynGFN: Bayesian Dynamic Causal Discovery Using Generative Flow Networks
Geodesic Sinkhorn for Fast and Accurate Optimal Transport on Manifolds
Efficient computation of optimal transport distance between distributions is of growing importance in data science. Sinkhorn-based …
Guillaume Huguet*, Alex Tong*, María Ramos Zapatero, Christpher J. Tape, Guy Wolf, Smita Krishnaswamy
PDF Cite
Neural FIM for Learning Fisher Information Metrics from Point Cloud Data
Oluwadamilola Fasina*, Guillaume Huguet*, Alex Tong, Yanlei Zhang, Guy Wolf, Maximilian Nickel, Ian Adelstein, Smita Krishnaswamy
PDF Cite