We meet every Monday, at 10 AM in room 5.04 at Rektorska 4, Warsaw University of Technology - or online.
Join us at https://meet.drwhy.ai.
- 06.10 - organizational meeting
- 13.10 - Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models - Bartosz Kochański
- 20.10 - Michał Włodarczyk
- 27.10 - Monthly sync meeting (Hubert Baniecki, Dawid Płudowski, Julian Sienkiewicz)
- 03.11 - Jakub Grzywaczewski
- 17.11 - Bartek Sobieski
- 24.11 - Monthly sync meeting (Paulina Tomaszewska, Paweł Struski, Vladimir Zaigrajew)
- 01.12 - Dawid Płudowski
- 08.12 - Kamil Książek
- 15.12 - Monthly sync meeting (Bartek Sobieski, Jakub Grzywaczewski, Michał Włodarczyk)
- 12.01 - Agata Kaczmarek
- 19.01 - Monthly sync meeting (Kamil Książek, Bartosz Kochański, Agata Kaczmarek)
- 19.01 - Retro meeting
- 24.02 - Tracking information flow in biosystems from high-throughput data - Miron Kursa
- 03.03 - Introduction to Sparse Autoencoders SAE with ReLU (Anthropic; Blog; 21.05.2024), TopK (OpenAI; ICLR 2025; 06.06.2025) and JumpReLU (DeepMind; 09.08.2024; EMNLP 2024 Workshop) - (advising Vladimir)
- 10.03 - Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models (Northeastern University; ICLR 2025; 31.03.2025) - (advising Vladimir)
- 17.03 - Sparse Autoencoders Do Not Find Canonical Units of Analysis (Durham University/Independent; ICLR 2025; 07.02.2025) - (advising Vladimir)
- 24.03 - Interpreting CLIP with Hierarchical Sparse Autoencoders (My paper; Under Review; 30.01.2025) - Vladimir Zaigrajew
- 31.03 - ProtoViT: Interpretable image classification with adaptive prototype-based vision transformers - Paweł Gelar
- 07.04 - PIP-Net: Patch-based intuitive prototypes for interpretable image classification - Karol Dobiczek
- 14.04 - Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning - Hubert Baniecki
- 28.04 - Vlad (ICLR)
- 05.05 - Explaining in Diffusion: Explaining a Classifier Through Hierarchical Semantics with Text-to-Image Diffusion Models - Jakub Świstak
- 12.05 - Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model - Jakub Grzywaczewski
- 19.05 - Diffusion Posterior Sampling for General Noisy Inverse Problems - Tymoteusz Kwieciński
- 26.05 - DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations - Dawid Płudowski
- 31.05 - Wyjazd zespołu do Wilgi
- 02.06
- 09.06
Schedule for the first half of the semester (track: Context matters in Deep Learning Models - Computer Vision):
- 07.10 - guest lecture by nadkom. dr Paweł Olber
- 14.10 - Do Not Explain Vision Models without Context - Paulina Tomaszewska
- 21.10 - Positional Label for Self-Supervised Vision Transformer - Filip Kołodziejczyk
- 28.10 - Adversarial examples vs. context consistency defense for object detection - Hubert Baniecki
- 04.11 - Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training - Bartosz Kochański
- 18.11 - User study: Visual Counterfactual Explanations for Improved Model Understanding - Bartek Sobieski
- 25.11 - Vision Transformers provably learn spatial structure - Vladimir Zaigrajew
- 02.12 - Null-text Inversion for Editing Real Images using Guided Diffusion Models - Dawid Płudowski
- 09.12 - Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training - Tymoteusz Kwieciński
- 16.12 - Rethinking Visual Counterfactual Explanations Through Region Constraint - Bartek Sobieski
- 13.01 - Controlling The World by Sleight of Hand - Jakub Świstak
- 20.01 - Connecting counterfactual and attributions modes of explanation - Jan Jakubik
- 19.02.2024 - PhD Thesis discussion Explanation methods for sequential data model
- 26.02.2024 - PhD Thesis discussion Modele rekomendacyjne wspólnej filtracji w serwisach ogłoszeniowych
- 04.02.2024 - PhD Thesis presentation Modele rekomendacyjne wspólnej filtracji w serwisach ogłoszeniowych
- 11.03.2024 - PhD Thesis discussion Analysis and texture recognition of digital images for computer aided skin lesions diagnostics
- 18.03.2024 - PhD Thesis presentation Analysis and texture recognition of digital images for computer aided skin lesions diagnostics
- 25.03.2024 - Law in AI - Andrzej Porębski
- 08.04.2024 - Introduction to counterfactual explanations track - Mateusz Krzyziński, Bartek Sobieski
- 15.04.2024 - The Privacy Issue of Counterfactual Explanations: Explanation Linkage Attacks - Mikołaj Spytek
- 22.04.2024 - Text-to-Image Models for Counterfactual Explanations: A Black-Box Approach - Tymoteusz Kwieciński
- 06.05.2024 - GLOBE-CE: A Translation Based Approach for Global Counterfactual Explanations - Piotr Wilczyński
- 13.05.2024 - Introduction to ViT and transformer attributions - Filip Kołodziejczyk
- 20.05.2024 - MI^2 PhD thesis presentations - Weronika Guzik, Katarzyna Kobylińska, Katarzyna Woźnica.
- 27.05.2024 - AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation - Maciej Chrabąszcz
- 03.06.2024 - Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet - Vladimir Zaigrajew
- 10.06.2024 - Semester summary and discussion.
- 09.10.2023 - Organizational matters - Hubert Baniecki, Maciej Chrabąszcz, Bartek Sobieski
- 16.10.2023 - On Minimizing the Impact of Dataset Shifts on Actionable Explanations - Hubert Baniecki
- 23.10.2023 - On the Robustness of Removal-Based Feature Attributions - Mateusz Krzyziński
- 30.10.2023 - Discussion - AdvXAI: Robustness of explanations
- 06.11.2023 - Representation Engineering - Maciej Chrabąszcz
- 13.11.2023 - Adaptive Testing of Computer Vision Models - Mikołaj Spytek
- 20.11.2023 - Red Teaming Language Models with Language Models - Piotr Wilczyński
- 27.11.2023 - Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned - Vladimir Zaigrajew
- 04.12.2023 - Discussion - RedTeaming of foundation models
- 11.12.2023 - Introduction to Diffusion Models - Bartek Sobieski
- 18.12.2023 - Glaze: Protecting artists from style mimicry by text-to-image model - Tymoteusz Kwieciński
- 08.01.2023 - FLIRT: Feedback Loop In-context Red Teaming - Hubert Ruczyński
- 15.01.2024 - Red-Teaming the Stable Diffusion Safety Filter - Mateusz Grzyb
- 22.01.2024 - Discussion - Diffusion models for XAI
- 2023-02-20 - set-up meeting
- 2023-02-27 - Acquisition of chess knowledge in AlphaZero - Bartek Sobieski, Mikołaj Spytek
- 2023-03-06 - Aggregation of explanations - Weronika Hryniewska, Przemysław Biecek
- 2023-03-13 - Ensembles of models - how to get the most benefits - Anna Kozak, Hubert Ruczyński
- 2023-03-20 - Unfooling Perturbation-Based Post Hoc Explainers - Hubert Baniecki, Mateusz Krzyziński
- 2023-03-27 - Globally-Consistent Rule-Based Summary-Explanations for Machine Learning Models: Application to Credit-Risk Evaluation - Mikołaj Spytek, Mateusz Krzyziński
- 2023-04-03 - From "Where" to "What": Towards Human-Understandable Explanations through Concept Relevance Propagation - Maciej Chrabąszcz, Bartek Sobieski
- 2023-04-17 - Explainable Artificial Intelligence for the Study of the Impact of Environmental Factors on Human Health- Donato Romano (guest, remote meeting)
- 2023-04-24 - Shapley values and functional decompositions - Mateusz Krzyziński, Hubert Baniecki
- 2023-05-08 - Scalable Gaussian process-based transfer surrogates for hyperparameter optimization - Mateusz Grzyb, Katarzyna Woźnica
- 2023-05-15 - Automated Benchmark-Driven Design and Explanation of Hyperparameter Optimizers - Hubert Ruczyński, Anna Kozak
- 2023-05-22 - Formal methods for neural networks verification - Paulina Tomaszewska,
- 2023-05-29 - Adaptive Testing and Debugging of NLP models - Emilia Wiśnios, Maciej Chrabąszcz
- 2023-06-05 - Meta-learning from Tasks with Heterogeneous Attribute Spaces - Katarzyna Woźnica
- 2023-06-12 - summary meeting
- 2022-10-03 - Organisation of the seminar
- 2022-10-10 - xLungs - Efficient and Explainable Diagnostics’ Support for Radiologists
- 2022-10-17 - HOMER - Achieving Responsible ML by Human Oriented autoMated machinE leaRning
- 2022-10-24 - ATLAS - Automated documenT anaLysis for sociAl awareneSs
- 2022-11-07 - Explainable machine learning for survival analysis - Mateusz Krzyziński, Mikołaj Spytek, Hubert Baniecki
- 2022-11-14 - Lungs vector representations - Maciej Chrabąszcz, Bartek Sobieski, Weronika Hryniewska-Guzik
- 2022-11-21 - ATLAS: Explaining abstractive summarization - Emilia Wiśnios
- 2022-11-28 - How to organize our work - discussion
- 2022-12-05 - Cancelled
- 2022-11-12 - New era of AutoML? - Katarzyna Woźnica, Anna Kozak
- 2022-11-19 - research presentation: xLungs
- 2023-01-02 - HOMER update
- 2023-01-09 - ATLAS update
- 2023-01-16 - Workshop: How to prepare presentation with storytelling? - Zuzanna Kwiatkowska
- 2023-01-23 - Summary
- 2022-06-13 Summary of the seminar and ongoing matters
- 2022-06-06 LIMEcraft: Handcrafted superpixel selection and inspection for Visual eXplanations - Weronika Hryniewska
- 2022-05-30 Industrial PhD (lesson learned) - Tomasz Stanisławek
- 2022-05-23 Hyperparameter optimization with Reinforcement Learning - Bartek Sobieski
- 2022-05-16 Monitoring of AI regulations using natural language processing - Stanisław Giziński & Stanisław Łaniewski
- 2022-05-09 Extensions of the SHAP method: using Shapley value to interpret models with dependencies and survival analysis models - Mateusz Krzyziński
- 2022-04-25 Comparative analysis of veins and arteries used in coronary artery bypass grafting. PhD Thesis - Piotr Zawierucha
- 2022-04-11
Monitoring of AI regulations using natural language processing - Stanisław Giziński - 2022-04-04 🎉 PhD defense (11-14 am) - Tomasz Stanisławek
- 2022-03-28 Running services and calculations in our Kubernetes cluster - Piotr Piątyszek
- 2022-03-21 Hybrid model of Fuzzy Cognitive Map - Decision Tree in making medical decisions - Hoang Thien Ly
- 2022-03-14 Duel-based Deep Learning system for solving IQ tests - Paulina Tomaszewska
- 2022-03-07 Expected goal (xG) models and XAI - Mustafa Cavus
- 2022-02-28 Organisation of the seminar and ongoing matters
- 2022-01-31 Impact of Imperfect Diagnostic Tests in ME/CFS Association Analyses - João Malato
- 2022-01-24 Models selecting prototypes with ProtoPNet - Adam Kozłowski
- 2022-01-17 Bayesian Optimization with a Prior for the Optimum - Bartłomiej Sobieski
- 2022-01-10 Evaluating explanations - Hubert Baniecki
- 2022-01-03 Explanations of multimodal neural networks - Piotr Czarnecki
- 2021-12-20 NeurIPS2021 – takeaways - Paulina Tomaszewska
- 2021-12-13 Auto-sklearn:Automating Design Decisions in AutoML - Mustafa Cavus
- 2021-12-06 Malaria pipelines - Andre Fonseca
- 2021-11-29 Auto-sklearn: Portfolio Successive Halving in PoSH - Mustafa Cavus
- 2021-11-22 MONAI framework for deep learning in healthcare imaging - Michał Sokólski
- 2021-11-15 Multi-fidelity optimization - Kasia Woźnica
- 2021-11-08 Stream data analysis - Kamil Wereszczyński
- 2021-10-25 Auto-sklearn: problem statement + challenge description - Kasia Woźnica
- 2021-10-18 How to increase the visibility of a statistician in the modern world of collaborative research? - Nuno Sepúlveda
- 2021-10-11 Multivariate data vis, Linear projections, and their application to local explanations of models - Nicholas Spyrison
- 2021-10-04 Organisation of the seminar
MI2 Summer CONF August 2, 2021 - Conference Book
SUCCESSful data visualization using International Business Communication Standard - Bartosz Sawicki, Kinga Ułasik
triplot4python: the remedy for dealing with correlated features in explanations - Mateusz Krzyziński , Artur Żółkowski
The medLIME algorithm - Adrianna Grudzień
Multitasking and transfer learning capabilities in Deep Learning - Maria Kałuska
Guide through jungle of models! forester: An R package to automatically select between tree-based models - Hoang Thien Ly, Szymon Szmajdziński
FairPANs - bringing fairness to neural networks - Hubert Ruczyński
metaMIMIC: an analysis of hyperparameter transfer possibilities for tabular data using MIMIC-IV database - Mateusz Grzyb , Zuzanna Trafas
Monitoring of AI regulation - Stanisław Giziński
Wakacyjny Klub Dyskusyjny, czwartki o 10:00
- 2021-08-26
- 2021-08-12
- 2021-08-05
- 2021-07-29
- 2021-07-22
- 2021-07-15
- 2021-06-17 MI2 responsible AI talks - An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department - Farah Shamout & DeCoviD team at 1 p.m.
- 2021-06-14 Podsumowanie roku
- 2021-06-07 What Will You Tell Me About the Chart? - Recognition and Description Process - Karolina Seweryn, Katarzyna Lorenc
- 2021-05-31 Robustness in Computer Vision - Sebastian Cygert
- 2021-05-24 Protagonists’ Catcher in Novels - A Dataset and A Tool - Weronika Łajewska
- 2021-05-19 Cross-validation: what does it estimate and how well does it do it? - Alicja Gosiewska
- 2021-05-17 The deriving of a computational approach test for testing equality of several populations’ means in the presence of nuisance parameter - Mustafa Cauvus
- 2021-05-10 Monitor wariantów SARS-CoV-2 - Hubert Baniecki, Piotr Piątyszek, Hanna Zdulska
- 2021-04-26 Towards Explainable AutoML: xAutoML - Marius Lindauer
- 2021-04-19 MI2DataLab against Covid19
- 2021-04-12 Generative Adversarial Network in Medical Imaging - Weronika Hryniewska
- 2021-03-29 Marginal Attribution by Conditioning on Quantiles - Anna Kozak
- 2021-03-22 Beyond Fairness: Towards a Just, Equitable, and Accountable Computer Vision - Piotr Czarnecki
- 2021-03-15 Discussion on reviewing conference papers
- 2021-03-08 MIMIC III - Medical Information Mart for Intensive Care - Katarzyna Kobylińska
- 2021-03-01 Cleora - Barbara Rychalska
- 2021-02-22 Gonito & Information extraction challenges and their evaluation - Filip Graliński
- 2021-01-25 Seminarium organizacyjne
- 2021-01-18 Transfer Learning of pre-trained CNN representations - Michał Sokólski
- 2021-01-11 Adversarial attacks on Explainable AI methods - Hubert Baniecki, Wojciech Kretowicz
- 2020-12-21 Podsumowanie roku 2020
- 2020-12-14 Towards explainable meta-learning - Kasia Woźnica
- 2020-12-07 Responsible AI & H2O - Jean-Matthieu SCHERTZER
- 2020-11-30 XAI for image based COVID-19 detection - Weronika Hryniewska
- 2020-11-23 Looking to listen: Audio separation and localization with visual clues - Piotr Czarnecki
- 2020-11-16 Interpretable Machine Learning with application to Credit Scoring - Alicja Gosiewska
- 2020-11-09 XAI in medicine - Katarzyna Kobylińska
- 2020-11-02 Graph-based Recommendation Systems - Barbara Rychalska
- 2020-10-26 2020 NLP trends & UniCase - Rethinking Casing in Language Models - Tomasz Stanisławek
- 2020-10-19
- 2020-10-12
- 2020-10-05 Seminarium organizacyjne
- 2020-09-11 Semantyczne modelowanie danych doświadczalnych i jego zastosowanie w analizie wyników fenotypowania roślin - Hanna Ćwiek-Kupczyńska
- 2020-08-03 Review of chest imaging findings in COVID-19 - Weronika Hryniewska
- 2020-07-28 Introduction to fairness - basic concepts and implementation of fairmodels package - Jakub Wiśniewski
- 2020-06-08 XAI for modelling of covid-19 mortality for the Polish population - Przemysław Biecek
- 2020-06-01 Detecting and overcoming bias in data with explainable artificial intelligence - Agnieszka Mikołajczyk
- 2020-05-25 Graph Convolutional Networks - Piotr Czarnecki
- 2020-05-18
- 2020-05-11
- 2020-05-04
- 2020-04-27
- 2020-04-06 Visualizing and Measuring the Geometry of BERT - Dominika Basaj
- 2020-03-30 The Mythos of Model Interpretability - Kasia Woźnica, Anna Kozak
- 2020-03-23 AI Explainability 360 by IBM - Michał Kuźba
- 2020-03-09 NLP: Current trends in language modelling and transfer learning - Tomasz Stanisławek
- 2020-03-02 Lifting Interpretability-Performance Trade-off via Automated Feature Engineering (SAFE) - Alicja Gosiewska
- 2020-02-24 Wyjaśnienia sieci ARA - Weronika Hryniewska
- 2020-01-27
- 2020-01-20
- 2020-01-13 ARA: accurate, reliable and active histopathological image classification framework with Bayesian deep learning - Łukasz Rączkowski
- 2019-12-16 Podsumowanie roku
- 2019-12-09 How can we discover a biomarker for Chronic Fatigue Syndrome? - Nuno Sepúlveda
- 2019-12-02
- 2019-11-25 Neural Machine Translation: achievements, challenges and the way forward - Barbara Rychalska
- 2019-11-18 CONLL & EMNLP - Tomasz Stanisławek
- 2019-10-28 Inpainting - Weronika Hryniewska
- 2019-10-21 Analiza dźwięku - Piotr Czarnecki
- 2019-10-07
- 2019-09-30 Seminarium organizacyjne
- 2019-06-10 - Podsumowanie roku
- 2019-06-03 - Analiza danych marketingowych - Adrian Foltyn
- 2019-05-27 - Adversarial training on text datasets - Kamil Grabowski
- 2019-05-20 - Mini-hackaton dot. wizualizacji modeli
- 2019-05-13 - Mikrosegmentacja - Adam Dobrakowski
- 2019-05-06 - Przyczynowość - Mateusz Kobos
- 2019-04-29 - Optymalizacja bayesowska - Michał Burdukiewicz
- 2019-04-15 - Tunability: Importance of Hyperparameters of Machine Learning Algorithms - Alicja Gosiewska
- 2019-04-08 - Feast - Przemysław Biecek
- 2019-04-01 - Named Entity Recognition - is there a glass ceiling? - Tomasz Stanisławek
- 2019-03-25 - Artykuł na ACL - Dominika Basaj i Alicja Gosiewska.
- 2019-03-18 - ExplainPrediction & sales example - Mateusz Staniak
- 2019-03-11 - TFML - Michał Kuźba
- 2019-03-04 - Explaining Classifications for Individual Instances - Katarzyna Kobylińska
- 2019-02-25 - Bioinformatyka - Michał Burdukiewicz
- 2019-02-18 - Seminarium organizacyjne
- 2019-01-28 - Przegląd prac z konferencji FATML - Dominika Basaj
- 2019-01-21 - Wizualna eksploracja modeli - Agnieszka Ciepielewska
- 2019-01-14 - NA - Alicja Gosiewska
- 2019-01-07 - Propensity Weighting to Investigate Health Disparities and Assess Indirect Effects - Chris Drake, UC Davis
- 2018-12-10 - Przewidywanie właściwości sekwencji biologicznych w oparciu o analizę n-gramów - Michał Burdukiewicz
- 2018-12-03 - Wrażenia z Krakowa - Alicja Gosiewska, Mateusz Staniak
- 2018-11-26 - EMNLP Conference Highlights - Dominika Basaj
- 2018-11-19 - Atencja - Tomasz Stanisławek
- 2018-11-12 - Wolne (100-lecie dnia po odzyskaniu niepodległości)
- 2018-11-5, 2018-11-6 - Christoph Molnar (LMU), Alicja Gosiewska, Przemysław Biecek, Klasyfikacja tekstów z użyciem Transfer Learning i Active Learning - Michał Kuźba (seminarium robocze)
- 2018-10-29 - Mythos of Interpretability - Mateusz Staniak
- 2018-10-22 - The Family of Relief algorithms - Alicja Gosiewska
- 2018-10-15 - Concept drift & IML - Mateusz Staniak, Przemyslaw Biecek
- 2018-10-8 - Interpretability & Security in NLP models - Dominika Basaj