Materials Project Seminars – Tess Smidt, "An Orientation in Symmetry-Aware ML Methods"

Unfortunately, the 1st minute is missing due to recording issues. But Tess makes up for it with a wonderful presentation! :) Slides can be downloaded here: https://docs.google.com/presentation/d/1QF5sssSehwwHpwqY-zoMYFIB1ILiKqh14eN8K06BTdo Links to recent work in order of appearance: * Quantifying chemical short-range order in metallic alloys (https://arxiv.org/abs/2311.01545) * Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs, ICLR 2023 (https://openreview.net/forum?id=KwmPfARgOTD) * EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations (https://arxiv.org/abs/2306.12059) * Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields (https://openreview.net/forum?id=X7gqOBG8ow) * Phonon predictions with E(3)-equivariant graph neural networks, NeurIPS 2023 - AI4Mat Workshop (https://openreview.net/forum?id=xxyHjer00Y) * Ophiuchus: Scalable Modeling of Protein Structures through Hierarchical Coarse-graining SO (3)-Equivariant Autoencoders (https://arxiv.org/abs/2310.02508) * Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for Molecule Generation (https://arxiv.org/abs/2311.16199) * Relaxed Octahedral Group Convolution for Learning Symmetry Breaking in 3D Physical Systems, NeurIPS 2023 - AI4Science Workshop (https://openreview.net/forum?id=B8EpSHEp9j)