taraak/pita

Code for the paper Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities.

28
/ 100
Experimental

This project helps researchers and computational chemists more accurately simulate complex molecular systems, particularly at low temperatures. It takes data from molecular dynamics (MD) simulations, often collected at higher temperatures, and produces more stable and accurate molecular configurations at desired lower temperatures. This is ideal for scientists studying molecular behavior, drug discovery, or materials science.

No commits in the last 6 months.

Use this if you need to generate realistic molecular configurations at specific, often low, temperatures where direct simulation is challenging or computationally expensive.

Not ideal if you are looking for a general-purpose simulation tool or if your primary need is not focused on sampling from Boltzmann densities in molecular systems.

molecular-dynamics computational-chemistry materials-science drug-discovery statistical-mechanics
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 7 / 25
Community 12 / 25

How are scores calculated?

Stars

35

Forks

5

Language

Python

License

Last pushed

Jul 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/taraak/pita"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.