Following current trends, the next PM will be in office for approximately minus 200 days

We're hiring interns in the Autonomous Systems and Robotics Research group here at Microsoft.
If you are a PhD student interested in working at the intersection of fluids simulations and ML, please consider applying:

careers.microsoft.com/us/en/job/1480…

Fantastic paper and fantastic team!

Hot off the press🔥
Check out our work on machine learning prediction of the heat capacity of MOFs in Nature Materials: nature.com/articles/s4156…

A summary 🧵👇
With Charithea Charalambous, Daniele Ongari, Mehrdad Asgari Amir Farmahini, Frank Noe, Susana Garcia, Lev Sarkisov, Berend Smit

Excited to share our new paper! ✨

Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design
arxiv.org/abs/2210.05274

See the thread 🧵

Machine learning pizza CECAM !!!

☺️😉💪

The chapter I have written last year on ML wave function is now online in final form! 😎📖🖥️
sciencedirect.com/science/articl…
In this work I discuss different approaches to represent the wave function with machine learning models; in particular RBM, GPS, FermiNet, PauliNet and SchNOrb.

Join me at #MSFTResearchSummit on October 18 where we’ll discuss 'The Fifth Paradigm of Scientific Discovery​' and address the question: what transformational impact can deep learning have on the way we practice science? Register now.

aka.ms/Register_Resea…

Temperature steerable flows and Boltzmann generators, Manuel Dibak, Leon Klein, Andreas Krämer, and Frank Noé Leon Klein Andreas Krämer Frank Noe Freie Universität #StatisticalPhysics go.aps.org/3MARa93

See what's trending in Machine Learning: Science and Technology right now at bit.ly/3MfoXUS featuring articles by Alan Aspuru-Guzik Steven Brunton Frank Noe Mario Krenn Philippe Schwaller (he/him) Pascal Friederich Teodoro Laino Nong Artrith KaestnerGroup #machinelearning #AI #compchem #materials #quantum #physics

Nice view from new ⁦Microsoft Research⁩ AI4Science Berlin office

Method to compute chemical potentials of mixtures from equilibrium molecular dynamics simulations.
Only modest system size & postprocessing are needed.
Applicable to a variety of systems including eletrolytes, organic molecules in water, dense mixtures...
aip.scitation.org/doi/10.1063/5.…

Lovely day at ⁦Freie Universität⁩

Dall-E continues to impress me, but what’s the caption to generate this image and who on earth came up with it?

I think ML career advice on industry vs academia often misses an important point. The variance within industry and within academia is larger than the difference between them.

Compare specific opportunities — teams, labs, mentors, & advisors — rather than general categories.

Using this occasion to lift the curtain as well :)

I will stay in Berlin and join Microsoft Research/Frank Noe end of the year as a Senior Researcher, Deep Learning for Molecular Modeling 🧬🤖📎

Very excited about this opportunity and very happy to continue the joint work ❤️