Generative models are necessary to fully capture uncertainty and conformational flexibility of protein structures, but how can we build such models? At the ICLR MLDD workshop, we'll present EigenFold, work led by Bowen Jing with undergrad students Ezra Erives and Peter Pao-Huang!

Happy new year everyone! In 2023, we worked on a broad range of tasks, from privacy-preserving analytics 🔒 to language models for protein sequences 🧪 to more! Here are some highlights from our awesome students, postdocs, and engineers. Citations at the end of the🧵 1/

I'm thrilled to share that a rotation project fully led by my first PhD student, the amazing Peter Pao-Huang Peter Pao-Huang, has been accepted to ICML 2025! Peter's paper, “Geometric Generative Modeling with Noise-Conditioned Graph Networks”, addresses a fundamental limitation

Introducing Locus: the first AI system to outperform human experts at AI R&D Locus conducts research autonomously over multiple days and achieves superhuman results on RE-Bench given the same resources as humans, as well as SOTA performance on GPU kernel & ML engineering tasks.

Biology emerges from interactions at different physical scales, from molecular to cellular to multicellular layers. Introducing PULSAR🌌, a multi-scale and multicellular foundation learns how genes impact cellular states and how groups of cells coordinate to collectively define