| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Original HTTPS Page] |
Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.
You must be logged in to block users.
Contact GitHub support about this userβs behavior. Learn more about reporting abuse.
Report abusePrincipal Investigator at Aithyra in Vienna, working on generative models for proteins and cells.
I'm a PI at Aithyra (a research institute at the intersection of ML and life sciences in Vienna, led by Michael Bronstein), where I build generative models for proteins and cells. My research focuses on:
Before Aithyra, I was a postdoc with Yoshua Bengio at Mila, and I completed my PhD at Yale advised by Smita Krishnaswamy. I also cofounded Dreamfold.
| Project | Description | Stars |
|---|---|---|
| TorchCFM | Conditional Flow Matching library for training flow models | |
| Open-dLLM | Open diffusion language model for code generation | |
| FoldFlow | SE(3)-stochastic flow matching for protein backbone generation | |
| DISCO | General multimodal protein design with DNA-encoded chemistry | |
| transferable-samplers | Amortized sampling of molecular systems with normalizing flows |
π Check out my publications β including work on FALCON, PAPL, and PITA.
π¦πΉ Based in Vienna, Austria Β· πΊπΈ Grew up in Seattle
TorchCFM: a Conditional Flow Matching library
Open diffusion language model for code generation β releasing pretraining, evaluation, inference, and checkpoints.
FoldFlow: SE(3)-Stochastic Flow Matching for Protein Backbone Generation
Code for the DISCO model: General Multimodal Protein Design Enables DNA-Encoding of Chemistry
Code for the paper Iterated Denoising Energy Matching for Sampling from Boltzmann Densities.
A repo for transferable sampling of molecular systems
| Back | FazBrowse Home | New Git URL |