Starred repositories
Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold
[ICML 2025] Repurposing pre-trained score-based generative models for transition path sampling by minimizing the Onsager-Machlup (OM) action
Pretrained universal neural network potential for charge-informed atomistic modeling https://chgnet.lbl.gov
A fully open source biomolecular structure prediction model based on AlphaFold3
A partially latent flow matching model for the joint generation of a protein’s amino acid sequence and full atomistic structure, including both the backbone and side chain.
PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning
A PyTorch-based framework for Quantum Classical Simulation, Quantum Machine Learning, Quantum Neural Networks, Parameterized Quantum Circuits with support for easy deployments on real quantum compu…
Welcome to the Physics-based Deep Learning Book v0.3 - the GenAI Edition
Platonic Transformers: A Solid Choice For Equivariance
A Fast, Simplified Model for Molecular Generation with Improved Physical Quality
Landscaper is a comprehensive Python framework designed for exploring the loss landscapes of deep learning models.
Fast and memory-efficient exact attention
A lightweight library for PyTorch training tools and utilities
ZW471 / TopoteinWorkshop
Forked from a-r-j/ProteinWorkshopThis is a topological deep learning extension to the ProteinWorkshop framework for protein structure representation learning. This library substantially extends the original benchmark library to in…
This repository contains the source code for Bayesian Learned Interatomic Potentials (BLIP)
Central repository for biomolecular foundation models with shared trainers and pipeline components
A generalized computational framework for biomolecular modeling.
Open Babel is a chemical toolbox designed to speak the many languages of chemical data.
Python composable command line interface toolkit
PyTorch code and models for VJEPA2 self-supervised learning from video.
Hackable and optimized Transformers building blocks, supporting a composable construction.
structRFM: A fully open structure-guided RNA foundation model for robust structural and functional inference
A benchmark dataset for protein-ligand co-folding prediction
It's a package for evaluation of predicted poses, right?