MARS: Machine-Learned Force Field Framework for Automated Conformational Sampling, Vibrational Spectroscopy, and Microsolvation

PyTorch Code for Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

RNA search

Template-based protein design with Raygun

Code for Expanding Flow Maps

For predicting dropout during chemical mapping experiments

Official Codebase For paper "One-step Language Modeling via Continuous Denoising"

Context Parallelism Code for Boltz-2

Python code for learning Molecular Dynamics simulations

(ECCV 2026): Official code for Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models

Code for “Speculative Sampling For Faster Molecular Dynamics”.

RetroChimera: a frontier retrosynthesis model built on ensembling

Garnet biomolecular force field

Next generation machine learning force field on enzymatic catalysis

Run OpenMM with forces provided by any Python program

Python utility to estimate, compare, and reweight RNA energetics across many secondary structure algorithms.

scripts and examples for scoring pseudoknot designs based on chemical mapping data

[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

[NeurIPS 2023] Structural Pruning for Diffusion Models

Molecular Dynamics From Scratch: a from-zero, educational MD engine built on JAX and OpenMM, with CUDA-12 wheels, pytest validation, and a learning path that walks through forcefields, integrators,…

Official Implementation of "Meta Flow Maps enable scalable reward alignment"

Small library for running Keras models from a C++ application

Official implementation of Sharpness-Aware Flow Matching

Generative Modeling with Flux Matching

PyMOL plugin - drive PyMOL from Claude Code, Cursor, or any MCP client.

Geometric Byte Pair Encoding of Protein Structure (ICLR 2026)

SwitchCraft: A Programmatic Framework for Designing State-Switching Proteins