-
Came up in a group meeting discussion. Could be a neat idea to try to differentiate with respect to graph weights and see if you can get something like a force by propagating that through a pretrained…
-
I've started investigating whether it's possible to run stable MD simulations using models trained on SPICE. I'm opening this issue as a place to describe my results and discuss approaches.
As a s…
-
OPTIMADE specification v1.0.1 defines a structure as a set of sites, occupied by mixtures of atoms, with each atom described by its chemical type, mass and occupancy (proportion in the mixture). Means…
-
**Project details:**
- Project Name: GPUMD
- Github URL: https://gpumd.org/ and https://github.com/brucefan1983/GPUMD
- Category: Interatomic Potentials (ML-IAP)
- Labels: "ml-iap", "lang-cpp"…
-
**Summary**
**Detailed Description**
**Further Information, Files, and Links**
-
# Introduction
There have been an emerging trend and great interest in foundation machine learning interatomic potentials (MLIPs/MLFFs) for simulating atomistic systems close to density functional …
-
CC_HDNNP is not a particularly memorable or informative name, and references HDNNPs due to the current focus on support for n2p2. Since we intend to add support for more modern (and performant) MLIPs,…
-
**Submitting author:** @aksam432 (Akshay Krishna Ammothum Kandy)
**Repository:** https://github.com/LAM-GROUP/PLIP
**Branch with paper.md** (empty if default branch): paper
**Version:** v0.3.4
**Edito…
-
### Name
Josh Vita
### Email
vita1@llnl.gov
### Dataset name
Amorphous_Zeolitic_Imidazolate_Frameworks_2023
### Authors
Nicolas Castel, Dune Andre, Connor Edwards, Jack D. Evans, …
jvita updated
8 months ago
-
Hi,
I heard about this project at MRS Fall last week and I am looking at the matbench discovery page. Shouldn't training size (e.g. 1.6 million vs 133 k) be the same for a fair comparison, else th…
knc6 updated
10 months ago