Adam Foster
@AdamEFoster
Senior Researcher at Microsoft Research AI for Science. Previously Oxford PhD in machine learning
I am very happy to share Orbformer, a foundation model for wavefunctions using deep QMC that offers a route to tackle strongly correlated quantum states! arxiv.org/abs/2506.19960
There’s a lot of confusion around uncertainty in machine learning. We argue the "aleatoric vs epistemic" view has contributed to this and present a rigorous alternative. #ICML2025 with @janundnik @eleanortrollope @markvanderwilk @adamefoster @tom_rainforth 1/5
The aleatoric-epistemic view on uncertainty doesn't serve ML researchers' needs and should be replaced. Come to the talk and poster tomorrow (Sat 14 Dec) at the #NeurIPS2024 workshop on Bayesian decisions (gp-seminar-series.github.io/neurips-2024). openreview.net/forum?id=WIjgb…
BIG opportunities to join @MSFTResearch AI for science: one senior researcher and one RSDE position, both focused on applications in molecular biology with the awesome @FrankNoeBerlin. Cambridge, UK or Berlin, DE.
Interested in working with a highly collaborative, interdisciplinary team to push the state of the art of generative AI for materials design? Join us as an intern by applying through this link! We are the team behind the MatterGen and MatterSim models from Microsoft Research AI…
Curious what I've been working on since joining AI for science? With an incredible, multidisciplinary team we've studied the 'wave function -> election density' marginalisation using score matching & NCE. This has some big gains over older Gaussian-based methods.
Introducing Neural Electron Real-space Density (NERD) models! 🧠 You’ve solved the electronic Schrödinger equation using PauliNet or Psiformer - what next? Important properties come from the 1-electron density (the marginal #MachineLearning) arxiv.org/abs/2409.01306
I have an opening for a 2.5-year postdoc position in the RainML lab as part of my ERC grant on probabilistic machine learning and intelligent data acquisition. Application deadline 10th July 2024. See here for details and to apply: tinyurl.com/rainmlpostdoc
Whoa, Aurora is featured in a Nature news article! We believe that forecasting atmospheric chemistry is only the beginning of what’s possible with foundation models for environmental forecasting. nature.com/articles/d4158…
Thrilled to share what we have been working on for the past year. Aurora is a major step forward towards a foundation model of the entire Earth system. I am very excited by all the downstream applications it will enable.
Excited to introduce Aurora: a foundation model of the atmosphere. In <1min, Aurora produces 5-day global air pollution predictions and 10-day high-resolution weather forecasts that outperform SOTA classical simulation tools and the best specialized deep learning models… 1/n
Terrific work from @fbickfordsmith on active learning with pretrained model backbones
The current default recipe for Bayesian active learning doesn’t really work beyond MNIST scale. We suggest why that is and identify a simple fix. arxiv.org/abs/2404.17249 @aistats_conf with @adamefoster @tom_rainforth 1/5