ma𝕏pool<p>UMA: A Family of Universal Models for Atoms<br><a href="https://ai.meta.com/research/publications/uma-a-family-of-universal-models-for-atoms/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">ai.meta.com/research/publicati</span><span class="invisible">ons/uma-a-family-of-universal-models-for-atoms/</span></a></p><p>family of Universal Models for Atoms (UMA), designed to push the frontier of speed, accuracy, and<br>generalization. UMA models are trained on half a billion unique 3D atomic structures (the largest<br>training runs to date) by compiling data across multiple chemical domains, e.g. molecules, materials,<br>and catalysts.</p><p><a href="https://mathstodon.xyz/tags/ml" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ml</span></a> <a href="https://mathstodon.xyz/tags/deepLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>deepLearning</span></a> <a href="https://mathstodon.xyz/tags/compChem" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>compChem</span></a> <a href="https://mathstodon.xyz/tags/computational" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>computational</span></a> <a href="https://mathstodon.xyz/tags/chemistry" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chemistry</span></a> <a href="https://mathstodon.xyz/tags/AImodels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AImodels</span></a></p>