Melanie F. Pradier

Senior Researcher @MSFTResearch. Previously: postdoc @Harvard, PhD @UC3M. Founding member of the ICBINB Initiative.

[Microsoft Research @MSFTResearch]

Microsoft researchers are driving trends and tackling major challenges in the midst of the ever-changing AI era. Check out Trista Chen, Flavio Griggio, Ahmed Awadallah, Jina Suh, and Cecily Morrison's conversations with Forward Future, a daily AI newsletter, to learn more about the people building the systems that are becoming part of our daily lives. https://t.co/SqYtgBBSma

[Melanie F. Pradier @MelaniePradier]

Excited to be presenting our work today at CLEAR 2025 🚀 🎉 ☺️https://t.co/3RSn3izW1X

In a nutshell, we improve estimation of treatment effects by matching along the Riemannian manifold of covariates as opposed to using other standard metrics such as Euclidean, Mahalanobis, etc.

[Melanie F. Pradier @MelaniePradier]

Unbelievable.... academic achievements should never be rewarded above human integrity: https://t.co/DKndYJXWFR

[Sahra Ghalebikesabi @SGhalebikesabi]

My team @GoogleDeepMind is hiring!!

We're looking for someone with strong engineering skills, experience in evaluating LLMs and/or a privacy/safety publication background. Join us to do some exciting research 🤖🔏

Apply here until next Monday, 9 am GMT

[Nicola Branchini @Branchini_Nic]

waiting times at A&E in Edinburgh - 6hrs without seeing a doctor and ongoing @NHSuk @NHSScotland
I guess we will find out how urgent it was by waiting

[Max Welling @wellingmax]

“We are on the brink of an irreversible climate disaster. This is a global emergency beyond any doubt. Much of the very fabric of life on Earth is imperiled. We are stepping into a critical and unpredictable new phase of the climate crisis.” https://t.co/NkoTLMLOqO

[Javier González @javiergonzh]

We are thrilled to announce the release of our latest paper, “Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models”, authored by Aditya Nori and myself.

https://t.co/cDTDAoPm9J

Hope you enjoy it!

[nature @Nature]

Slow productivity: do fewer things, work at a natural pace and obsess over quality https://t.co/XbRH3YDwmu

[I Can’t Believe it’s Not Better: RLC ‘24 @ICBINB_RLC]

With our final talk of the day, we’ve got @wwdabney here to help us to learn how RL is (really really) hard.

[I Can’t Believe it’s Not Better: RLC ‘24 @ICBINB_RLC]

During our ICBINB workshop, we have two talks focused on applications to safety-critical domains such as healthcare. The first talk, given by Dr. @shengpu_tang, Prof. @EmoryUniversity, will be a great cursory overview:

“RL for Healthcare Decision Making: The Perils and Promises”

[Melanie F. Pradier @MelaniePradier]

@SGhalebikesabi @UniofOxford @oxcsml @GoogleDeepMind Congratulations Sahra!! You deserve it 🎉

[CLeaR-Conference on Causal Learning and Reasoning @Conf_CLeaR]

We are thrilled to announce the 4th Conference on Causal Learning and Reasoning (CLeaR), taking place in Lausanne, Switzerland, from May 7-9, 2025!

Submission deadline: Nov 2, 2024, 11:59 PM AoE. For details, visit https://t.co/eyzQQsBopt 😀😎

[Daniela Massiceti @dannimassi]

Our team at @MSFTResearchCam is hiring a 2-year AI resident to drive progress in equitable multi-modal AI. Candidate should have a PhD in ML/related field with experience in multi-disciplinary research and a passion for equitable tech. Apply here: https://t.co/eiZ3eBHDAF🤓

[Aneesh Komanduri @akomandML]

Interested in causal representation learning and counterfactual generation? Check out our recent survey paper on causal generative modeling published in @TmlrOrg!

#TMLR #generative_models #causality
https://t.co/NflIdB6xOM

[James Hensman @jameshensman]

Our team is growing. Come and join us as part of the MSR AI Residency program to work on efficiency in deep learning.

https://t.co/WrjbCybsf7

[Nate Gruver @gruver_nate]

Predictions without reliable confidence are not actionable and potentially dangerous. In new work, we deeply investigate uncertainty calibration of large language models. We find LLMs must be taught to know what they don’t know:
https://t.co/pblidTDWK6
w/ @psiyumm et al.
1/8

[Victor Veitch 🔸 @victorveitch]

Fundamentally, high-level concepts group into categorical variables---mammal, reptile, fish, bird---with a semantic hierarchy---poodle is a dog is a mammal is an animal.

How do LLMs internally represent this structure?

https://t.co/HK2iFLUpte

[Francesco Locatello @FrancescoLocat8]

The first real-world causal downstream task for representation learning!

We collaborated with experimental ecologists and built a new benchmark for estimating the causal effect of a treatment on ants' behavior.

With this, we highlight many challenges for causality in science!