@AdamEFoster

Senior Researcher at Microsoft Research AI for Science. Previously Oxford PhD in machine learning

 London, England
ae-foster.github.io
Joined November 2014
  • Tweets96
  • Following251
  • Followers727
4Media
Last call - open til Oct 30! Are you excited about #MachineLearning and developing new architectures for Molecular Biology? Joint us for the next chapter of BioEmu at @MSFTResearch AI for Science - Berlin DE or Cambridge UK. aka.ms/bioemu-ml
10
48
6,552
Want to join our BioEmu team in @MSFTResearch AI for Science as an Intern? Berlin DE or Cambridge UK are available. Preference for candidates at the end of their PhDs, but open for everything: jobs.careers.microsoft.com/g…
Frank Noe@FrankNoeBerlin10 Jul 2025
BioEmu now published in @ScienceMagazine !! What is BioEmu? Check out this video: youtu.be/LStKhWcL0VE?si=tQQX…

Scalable emulation of protein equilibrium ensembles with BioEmu

Following the sequence and structure revolutions, predicting functi...

youtube.com
16
59
7,681
I have an opening for a 2-year postdoc in probabilistic machine learning and/or experimental design. The application deadline is the 3rd of September. See here for details and how to apply: tinyurl.com/rainmlpostdoc202…
11
1
51
4,340
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
1
15
1
63
4,975
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/…). openreview.net/forum?id=WIjg…
1
5
1
33
2,469
Adam Foster retweeted
Tian Xie@xie_tian2 Oct 2024
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 for Science. jobs.careers.microsoft.com/g…
31
9
109
36,256
Excited to share that I recently defended my DPhil 🎉 Huge thanks to my supervisors @tom_rainforth and @yeewhye, all my co-authors, especially @AdamEFoster, collaborators and mentors. Thanks to my assessors @maosbot and @samikaski for the interesting and stimulating discussion. And of course thanks to @StatMLIO, @OxfordStats and @SPC_Oxford for funding my DPhil 💸 #PhDone 🫳🎤
8
2
1
64
2,913
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
1
21
1
56
12,420
Adam Foster retweeted
Wessel@ikwess5 Jun 2024
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/d41586-0…

Superfast Microsoft AI is first to predict air pollution for the whole world

Nature - The model, called Aurora, also forecasts global weather for ten days — all in less than a minute.

nature.com
7
31
2,249
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.
Paris Perdikaris@ParisPerdikaris22 May 2024
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
3
14
86
12,213
Last call for internship applications in @MSFTResearch #AI4Science on #deeplearning / #ArtificialInteligence for protein biophysics. Closing the search end of this week.
Frank Noe@FrankNoeBerlin1 Feb 2024
Internship opportunity at @MSFTResearch #AI4Science on generative protein models. Location Berlin, Amsterdam or Cambridge. Apply here asap: jobs.careers.microsoft.com/g…
18
2
58
10,709
We are recruiting four career development fellowships (2x 2year, 2x 5year) in Machine Learning or Statistics at @OxfordStats. These are independent posts with half teaching loads. I can strongly recommend them from personal experience Details and apply: tinyurl.com/fnoxfrod
1
15
1
34
14,377
Interested in accelerating scientific discovery with AI? Join our interdisciplinary global team! Two exciting opportunities for engineers: Amsterdam or Berlin: jobs.careers.microsoft.com/g… Beijing: jobs.careers.microsoft.com/g…
1
24
5
92
40,582
I’ll be at ICML🌺 to present my @Microsoft Research internship project “CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design” — work done with Joel Jennings, @tom_rainforth, Cheng Zhang and @AdamEFoster 1/7
1
6
1
52
3,838
Maximise expected info gain in model params (aka BALD) → effective active learning? Sadly not! EPIG, our alternative, shares BALD’s 1950s foundations but targets predictions. arxiv.org/abs/2304.08151 #AISTATS2023 w/ @blackhc @seb_far @yaringal @adamefoster @tom_rainforth 1/5

Prediction-Oriented Bayesian Active Learning

Information-theoretic approaches to active learning have traditionally focused on maximising the information gathered about the model parameters, most commonly by optimising the BALD score. We...

arxiv.org
4
24
2
83
18,013
Join us for on a wonderful postdoc position at @MSFTResearch AI4Science Berlin on #MachineLearning for Molecules! careers.microsoft.com/us/en/…
30
2
88
9,298
Not all data is created equal! How can we decide what to acquire? Bayesian experimental design (BED) is a principled framework that has recently seen a surge of interest. Our review of modern BED, building up from the basics to today’s frontier: arxiv.org/abs/2302.14545 1/4
2
16
66
6,662
We've got really good at utilizing data. But methods for acquiring that data are often still rudimentary. Our new review paper shows how Bayesian experimental design has recently transformed to now provide a powerful mechanism to acquire data intelligently arxiv.org/abs/2302.14545
2
30
1
121
18,357
Interested in the optimal design of experiments, adaptive data acquisition, or active learning? Then check out my tutorial on Bayesian Experimental Design from the Cambridge Ellis Machine Learning Summer School Part 1: youtu.be/5oGdDGPVLjc Part 2: youtu.be/yCHp_wzpq8o
3
82
447
Adam Foster retweeted
Nick Pawlowski@pwnic22 Aug 2022
I'm happy to share more information about our #NeurIPS2022 workshop on Causal ML for real-world impact. Please submit short papers until Sept, 30th and join us in New Orleans on Dec, 2nd. You can find more information and CfP here: cml-4-impact.vanderschaar-la…

NeurIPS 2022 Workshop on Causality for Real-world Impact // van der Schaar Lab

This workshop was held at NeurIPS on 2nd December 2023 Causality has a long history, providing it with many principled approaches to identify a causal effect [1-3] (or even distill cause from effect...

vanderschaar-lab.com
2
23
3
94
Load more