AI4Science-WestlakeU/diffphycon

[NeurIPS2024] DiffPhyCon uses generative models to control complex physical systems

39
/ 100
Emerging

DiffPhyCon helps engineers and scientists control complex physical systems, like fluid dynamics or the movement of soft robots, with greater precision and flexibility. You provide data describing the system's behavior, and it generates optimal control signals to guide the system towards a desired outcome. This is ideal for researchers and control engineers working with challenging physical simulations.

Use this if you need to find precise control sequences for highly complex or dynamic physical systems, especially when traditional control methods struggle.

Not ideal if your system is simple enough for classic control methods or if you need real-time, ultra-low-latency control in a safety-critical application without further integration.

fluid-dynamics robotics-control physical-simulation computational-physics system-optimization
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

47

Forks

4

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/AI4Science-WestlakeU/diffphycon"

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