I'm hiring a post-doc for the Healthy AI Lab 📣. Come join us to work on machine learning methods to improve decision-making, e.g., in health applications. If you can't stop thinking about research problems until you make progress, you may be the right fit!
www.chalmers.se/en/about-cha...
Great first day of the 3rd annual CHAIR Structured Learning Workshop @ Chalmers! 🥳
Event page & agenda: ui.ungpd.com/Events/60bfc...
1st day featuring:
@betapata.bsky.social
@janstuehmer.bsky.social
@arnauddoucet.bsky.social
@frejohk.bsky.social
Key to this is to decouple environment interaction from language generation while maintaining the reasoning capabilities of pre-trained models.
Project page: expa-rl.github.io
Pre-print: arxiv.org/abs/2510.07581
PS. Nick is on the job market!
🚨 Preprint on LLMs in external environments:
Zhongqi (Nick) Yue, a great post-doc in my lab, has led the development of EARL—a new reinforcement learning framework for LLMs to interact with external environments, greatly improving over text-only interaction in reasoning tasks.
Thank you Branislav Kveton, Sandeep Juneja, Slawomir Nowaczyk and Yevgeny Seldin for serving as Newton's grading committee and opponent!
Read Newton's PhD thesis here: research.chalmers.se/publication/...
Last Friday, Newton Mwai Kinyanjui defended his PhD thesis "Leveraging Structural Priors and Historical Data for Practical Treatment Personalization with Multi-Armed Bandits". It's been a pleasure having you in the lab, Newton! Looking forward to seeing what the next chapter brings!
Last Friday, Newton Mwai Kinyanjui defended his PhD thesis "Leveraging Structural Priors and Historical Data for Practical Treatment Personalization with Multi-Armed Bandits". It's been a pleasure having you in the lab, Newton! Looking forward to seeing the next chapter!
We are delighted to announce the #EurIPS 2025 Workshops 🎉: eurips.cc/workshops/
We received 52 proposals, which were single-blind reviewed by more than 35 expert reviewers, leading to 18 accepted workshops (acceptance rate 34.6%).
Anton's thesis: research.chalmers.se/publication/...
Lena's thesis: research.chalmers.se/en/publicati...
This week has been an absolute joy for me as the leader of the Healthy AI Lab! Two of my students, Anton Matsson (3rd from right) and Lena Stempfle (2nd from right), defended their theses and became the first PhD graduates under my supervision 🎉 You will both be sorely missed!
Going to ICML next week? Find Anton and talk to him about our work on prediction models that learn to avoid missing values!
In a tree, features are used depending on the values and availability of other features. By penalizing reliance on missing values in computing predictions, we can learn trees that are unlikely to ask for a feature unless it is available (and predictive)
In this work, we show that you can fit interpretable models that are unlikely to even *ask for* features that are missing at test time by learning to avoid using them in the first place. For trees, this is contextual...
If you want to fit an interpretable ML model like a tree or a GLM, how can you make sure that it's still accurate and interpretable when input features are missing at test time? Standard methods like imputation or missingness indicators tend to break one or the other...
I'm thrilled to share that Lena Stempfle's, Anton Matsson's and Newton Mwai's paper "Prediction models that learn to avoid missing values" was accepted to ICML and awarded a spotlight! Arxiv here: arxiv.org/abs/2505.03393
More below👇
10 days to go to apply for this PhD student position in my lab!
Last but not least: The student will be co-advised by the fantastic @urish.bsky.social!
Our CS department is listing 5 positions. Make sure to select "F. Johansson - Reducing waste in tabular machine learning by generalizing out-of-table" to indicate which project you would like to work in.
Deadline May 15!
We are hiring a *PhD student* in my group to work on machine learning generalization "out-of-table". Help build methods that learn from large volumes of tabular data to generate models for new tasks! Apply here: www.chalmers.se/en/about-cha...
Our CS department is listing 5 positions. Make sure to select "F. Johansson - Reducing waste in tabular machine learning by generalizing out-of-table" to indicate which project you would like to work in.
Deadline May 15!
No argument there—I'm pretty sure that's a different question though.
Clearly not but I was surprised at how many orals at NeurIPS were missing speakers too. Any chance of having reserve speakers? Sure, there is an honor in being awarded an oral but, as a conference-goer, having a 20-min gap in the schedule due to a missing speaker seems like a missed opportunity.
Open for work!
Unfortunately, I just found out that all funding and grants for my 2025 projects are canceled.
Would love the opportunity to continue the musical journey started with #Ultros. Comfortable with #GameMusic #GameAudio. Retweets appreciated linktr.ee/ratvader
The first paper by Herman Bergström, Emil Carlsson, Devdatt Dubhashi, and me, explores how important context is to active preference learning from pairwise feedback: arxiv.org/abs/2405.03059
In the second, I develop a benchmark for evaluating estimators of causal effects. arxiv.org/abs/2405.16069
I'm currently at NeurIPS eager to talk about the two papers from my group:
* Active Preference Learning for Ordering Items In-and Out-of-sample (arxiv.org/abs/2405.03059)
* IncomeSCM: From tabular data set to time-series simulator and causal estimation benchmark (arxiv.org/abs/2405.16069)
