Proteins, Galaxies, and Robotaxis: GraphML News August’22

August is a notoriously quiet month when it comes to research and news. As folks slowly come back from vacations, we see more and more interesting articles and releases:

🧬 Meta AI released the weights for 3B and 15B ESM-2 models - we recently covered how cool those models are and how you can predict 3D protein structure right from the frozen language model hidden states. Now you can try them on your own premise!

💫 Yesukhei Jagvaral from the Department of Physics at CMU wrote a wonderful post with cool graphics how the team uses GNNs to model scalar and vector quantities of real galaxies with graph GANs. Each galaxy is a node in the graph and has a set of physical features (like mass or tidal fields). Galaxies are connected through the radius nearest neighbors algorithm. The authors train generative models that yield good approximations of real physical properties agreeing with simulations.

🚕 Zoox, a robotaxi startup, employs GNNs to model road dynamics and improve estimations of what’s happening around the car. The post is a bit obscure about the prediction task but we can hypothesize it has to do with vehicle dynamics (like molecular dynamics, but for cars and pedestrians).