ML in PL

ML in PL Association is a non-profit organization devoted to fostering the machine learning community in Poland and promoting a deep understanding of ML methods

[ML in PL @MLinPL]

Early Bird Registration Form: https://t.co/OeTp4CGfEW

[ML in PL @MLinPL]

Early bird registration for ML in PL 2026 is open — starting today, June 1st. It also happens to be Children's Day in Poland. Apparently a good day to start things.

Register at the link below.

[ML in PL @MLinPL]

3/ Herke van Hoof — Modular Learning for Improving AI Assistants

Most AI wins require abundant data. Robotics, real-world infrastructure, scientific domains don't have that. Herke advocates for modular approaches — composing complex behaviour from simpler elements — with three concrete projects on generalisation, data efficiency, and instructability.

Link: https://t.co/qAEE1JCi68

[ML in PL @MLinPL]

That's a wrap on this season's recordings. The last batch goes wide: hardware control, ML in science and engineering, and AI that works beyond data-rich settings.

[ML in PL @MLinPL]

2/ Johannes Brandstetter — What's the Next Wave of Disruption in Science and Engineering?

From weather modeling to CFD to multi-physics simulation — Johannes connects the dots and makes the case that scientific ML is past the proof-of-concept stage. The focus: what it actually takes to build reference models for whole industry verticals.

Link: https://t.co/cShMS24OtV

[ML in PL @MLinPL]

3/ Gerhard Wunder, Maura Pintor & Jakub Kałużny — Discussion Panel: AI in Security

Inherent vulnerabilities of AI models, adversarial attack vectors, adequacy of traditional security measures, ethical implications of AI in security systems. The kind of conversation that's more useful than a single paper.

Link: https://t.co/qiBhF7pTCb

[ML in PL @MLinPL]

How far can a model generalize? Across scales, across domains, across the boundary between capability and safety? Three talks, three angles on that question.

[ML in PL @MLinPL]

2/ Alexey Dosovitskiy — From Pixels to Nucleotides

From computer vision through transformers to mRNA-based drug design. Alexey covers "off-the-grid" architectures for visual data and connects them to ML for drug design. A cross-domain talk that earns the framing by actually showing the connections.

Link: https://t.co/VD24UM91CH

[ML in PL @MLinPL]

See you in Warsaw, October 8–10, for the 10th edition.

[ML in PL @MLinPL]

Why do deep networks train the way they do, and why do they forget what they learn? Those questions have run through fifteen years of Razvan Pascanu's work, from a PhD with Yoshua Bengio to Google DeepMind. He is the first name on our 10th edition lineup.

[ML in PL @MLinPL]

Razvan Pascanu has been a research scientist at Google DeepMind since 2014. Before this, he completed his PhD at Universite de Montréal with prof. Yoshua Bengio, where he worked on understanding deep networks, specifically recurrent neural architectures. During his career he has made significant contributions to theory of deep networks, optimization, recurrent architectures as well as deep reinforcement learning, continual learning, meta-learning and graph neural networks. For details on his work please see https://t.co/s5GZESFnT4. He has been Program Chair for the Neural Information Processing Systems (NeurIPS) conference and currently acts as General Chair, as well as a Program Chair for the Conference on Life-long Learning Agents (CoLLAs) and the Learning on Graphs Conference (LoG). He has organized various workshops on topics such as continual learning at top-tier conferences. He is also one of the main organizers of the Eastern European Machine Learning Summer School (EEML) and EEML workshop series, as well as an organizer of the Romanian AI Days.

[ML in PL @MLinPL]

3/ Michael Vollenweider — Learning Personalized Treatment Decisions in Precision Medicine

Not all treatment assignment bias hurts equally. Michael models bias types via mutual information and shows some have minimal effect on counterfactual prediction. Benchmarked on TCGA and real drug/CRISPR screens. A concrete argument for thinking carefully about which bias you're dealing with.

Link: https://t.co/Ho3n4k2IWH

[ML in PL @MLinPL]

Medicine is one of the places where causal ML stops being a research exercise and starts having consequences. Three talks on what the methods can actually deliver — from fundamental limits of causal discovery to personalized treatment decisions in clinical data.

[ML in PL @MLinPL]

2/ Paweł Morzywołek — Inference on Local Variable Importance Measures for Heterogeneous Treatment Effects

Treatment effects vary across individuals. Which variables drive that variation — and can you test it rigorously enough for clinical use? Local importance measures, global inference, semiparametric theory, valid with ML estimators. Demonstrated on infectious disease prevention.

Link: https://t.co/gdt0KMtu1P

[ML in PL @MLinPL]

It takes a lot of people to run a conference. This year, ten coordinators are each responsible for a different piece of ML in PL Conference. Meet the first two.

Patryk Rygiel
Runs Call for Contributions. By day, PhD candidate at the University of Twente building neural surrogates for blood flow simulations and geometric deep learning for cardiovascular risk (two medical device patents came out of that work). Has been through NVIDIA, a med-tech startup, and enough AI events across Europe that organizing one more felt like a natural next step. Climbs rocks when not climbing submission deadlines.

Jakub Myśliwiec
Five years in ML in PL, second year running the Speakers' Team. Holds a double Master's from Utrecht (AI + Game & Media Technology) and now does R&D at Cyclomedia, where he reconstructs 3D scenes from street-level imagery using Gaussian Splatting. Certified climbing instructor. The rest of his time splits between ultimate frisbee, FPV drones, board games, and whatever sci-fi novel is on the nightstand.

[ML in PL @MLinPL]

3/ Jan Mielniczuk — Joint Empirical Risk Minimization for Instance-Dependent Positive-Unlabeled Data

PU learning usually assumes constant propensity. Jan doesn't. He jointly minimizes empirical risk over class probability and instance-dependent propensity score, with consistency guarantees from empirical process theory. Matches or beats state-of-the-art across 20 datasets.

Link: https://t.co/xu2WGJBzeU

[ML in PL @MLinPL]

Good models aren't always reliable models. Benchmark numbers look clean, but real deployment comes with distribution shift, unlabeled data, and applications where "it usually works" isn't good enough. Three talks that dig into exactly that territory.

[ML in PL @MLinPL]

2/ Paweł Teisseyre — A Generalized Approach to Label Shift: the Conditional Probability Shift Model

Covariate shift and label shift don't cover all distribution mismatch. CPS fills a specific gap: the conditional class distribution changes, the rest doesn't. CPSM estimates via multinomial regression + EM, works with any classifier, and outperforms LS baselines on MIMIC — especially where LS methods don't even flag a problem.

Link: https://t.co/7zFZJxexr1