#<\/span>Accepted Talks <\/h1>\n

\n

Automated Harmful Content Detection Using Grammar-Focused Representations of Text Data (slides)<\/a>
<\/span><\/strong>Daria Stetsenko (NASK PIB)<\/u>, Inez Okulska (NASK PIB) <\/p>\n

Building more helpful and safe dialogue agents via targeted human judgements
<\/span><\/strong>Maja Tr\u0119bacz (DeepMind) on behalf of all the authors: Amelia Glaese*, Nat McAleese*, Maja Tr\u0119bacz*<\/u>, John Aslanides*, Vlad Firoiu, Timo Ewalds, Maribeth Rauh, Laura Weidinger, Martin Chadwick, Phoebe Thacker, Lucy Campbell-Gillingham, Jonathan Uesato, Po-Sen Huang, Ramona Comanescu, Fan Yang, Abigail See, Sumanth Dathathri, Rory Greig, Charlie Chen, Doug Fritz, Jaume Sanchez Elias, Richard Green, So\u0148a Mokr\u00e1, Nicholas Fernando, Boxi Wu, Rachel Foley, Susannah Young, Iason Gabriel, William Isaac, John Mellor, Demis Hassabis, Koray Kavukcuoglu, Lisa Anne Hendricks, Geoffrey Irving (DeepMind), * - Equal contributions <\/p>\n

Consolidated learning \u2013 new approach to domain-specific strategy of hyperparameter optimization
<\/strong>Katarzyna Wo\u017anica (MI2DataLab; Warsaw University of Technology)<\/u> <\/p>\n

A Fictitious Play Approach for Multiplayer Computer Games (slides)<\/a>
<\/strong>Jacek Cyranka (University of Warsaw)<\/u>, Jarek Kochanowicz, Witold Szejgis<\/span> <\/p>\n

Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search (slides)<\/a>
<\/strong>Micha\u0142 Zawalski (University of Warsaw), Micha\u0142 Tyrolski (University of Warsaw)<\/u>, Konrad Czechowski (University of Warsaw), Damian Stachura (Jagiellonian University), Piotr Pi\u0119kos (University of Warsaw), Tomasz Odrzyg\u00f3\u017ad\u017a (IDEAS NCBR), Yuhuai Wu (Google Research; Stanford University), \u0141ukasz Kuci\u0144ski (Polish Academy of Sciences), Piotr Mi\u0142o\u015b (Polish Academy of Sciences; deepsense.ai) <\/p>\n

Fine-Grained Conditional Computation in Transformers (slides)<\/a>
<\/strong>Sebastian Jaszczur (IDEAS NCBR ; University of Warsaw)<\/u> <\/p>\n

From data acquisition to ML model for predicting outcomes of chemical reactions (slides)<\/a>
<\/strong>Micha\u0142 Sadowski (Molecule.one)<\/u>, Miko\u0142aj Sacha (Molecule.one) <\/p>\n

How to learn classifier chains using positive-unlabelled multi-label data? (slides)<\/a>
<\/strong>Pawe\u0142 Teisseyre (Polish Academy of Sciences; Warsaw University of Technology)<\/u> <\/p>\n

How to win MAI'2022 Depth Estimation challenge: manual backbone optimization combined with smart model pruning. (slides)<\/a>
<\/strong>\u0141ukasz Treszczotko (TCL Research Europe)<\/u>, Maciej Smyl (TCL Research Europe), Micha\u0142 Kudelski (TCL Research Europe)<\/span> <\/p>\n

Interactive sequential analysis of a model improves the performance of human decision-making (slides)<\/a>
<\/strong>Hubert Baniecki (University of Warsaw)<\/u>, Dariusz Parzych (Warsaw University of Technology), Przemys\u0142aw Biecek (Warsaw University of Technology; University of Warsaw) <\/p>\n

Interpretable Deep Learning with Prototypes
<\/strong>Bartosz Zieli\u0144ski (Jagiellonian University, IDEAS NCBR)<\/u> <\/p>\n

Introduction and analysis of Diffusion-based Deep Generative Models (slides)<\/a>
<\/strong>Kamil Deja (Warsaw University of Technology)<\/u>, Anna Kuzina (Vrije Universiteit Amsterdam), Tomasz Trzci\u0144ski (Warsaw University of Technology, IDEAS NCBR, Tooploox, Jagiellonian University<\/span>), Jakub Tomczak (Vrije Universiteit Amsterdam)<\/span>\n <\/p>\n

Lightweight Conditional Model Extrapolation for Streaming Data under Class Prior Shift (LIMES) (slides)<\/a>
<\/strong>Paulina Tomaszewska (Warsaw University of Technology)<\/u>, Christoph H. Lampert (Institute of Science and Technology Austria)<\/span> <\/p>\n

NeRF \u2013 Generating 3d world from a bunch of images (slides)<\/a>
<\/strong>\u0141ukasz Pier\u015bcieniewski (NVIDIA)<\/u>, Jan Olszewski (NVIDIA) <\/p>\n

One class classification approach to variational learning from Positive Unlabeled Data (slides)<\/a>
<\/strong>Jan Mielniczuk (Polish Academy of Sciences; Warsaw University of Technology)<\/u>, Adam Wawrze\u0144czyk (Polish Academy of Sciences)<\/span> <\/p>\n

Improved Feature Importance Computation for Tree Models Based on the Banzhaf Value
<\/strong>Piotr Sankowski (IDEAS NCBR, MIM Solutions and University of Warsaw)<\/u>, Adam Karczmarz (IDEAS NCBR; University of Warsaw), Tomasz Michalak (IDEAS NCBR; University of Warsaw), Anish Mukherjee (IDEAS NCBR; University of Warsaw), Piotr Wygocki (MIM Solutions; University of Warsaw)<\/span> <\/p>\n

Reinforcement learning in Datacenters<\/strong> (slides)<\/a>
Alessandro Seganti<\/span> (Equinix<\/span>)<\/u>, Darek Matlak (Equinix)<\/span> <\/p>\n

Sequential counterfactual prediction to support individualized decisions on treatment initiation
<\/strong>Pawe\u0142 Morzywo\u0142ek (Ghent University)<\/u>, Johan Steen (Ghent University), Wim Van Biesen (Ghent University), Johan Decruyenaere (Ghent University), Stijn Vansteelandt (Ghent University)<\/span> <\/p>\n

Harnessing the power of graph structures to understand changing user preferences over time and enhance item recommendations (slides)<\/a>
<\/strong>Tomasz Palczewski (Samsung Research America<\/span>)<\/u>, Anirudh Rao (Samsung Research America), Yingnan Zhu (Samsung Research America), Ayden Kim (Samsung Research America)<\/span> <\/p>\n

Towards self-certified learning: Probabilistic neural networks trained by PAC-Bayes with Backprop (slides)<\/a>
<\/strong>Omar Rivasplata (University College London)<\/u>, Mar\u00eda P\u00e9rez-Ortiz (University College London), John Shawe-Taylor (University College London), Csaba Szepesv\u00e1ri (University of Alberta, DeepMind Edmonton)<\/span> <\/p>\n

Uncertainty estimation in BERT-based Named Entity Recognition<\/span><\/strong> (slides)<\/a> <\/p>\n <\/div>\n

Alicja R\u0105czkowska (Allegro Machine Learning Research)<\/u><\/span>, Riccardo Belluzzo (Allegro Machine Learning Research), Pawe\u0142 Olszewski (Allegro Machine Learning Research), Piotr Zieli\u0144ski (Allegro Machine Learning Research), Pawe\u0142 Zawistowski (Allegro Machine Learning Research)<\/span> <\/p>\n

#<\/span>Accepted Posters <\/h1>\n

\n

Poster 01: survex: model-agnostic explainability for survival analysis (poster)<\/a>
<\/strong>Miko\u0142aj Spytek<\/span> (MI2DataLab, Warsaw University of Technology)<\/u>, Mateusz Krzyzi\u0144ski (MI2DataLab, Warsaw University of Technology), Hubert Baniecki (MI2DataLab, University of Warsaw), Przemys\u0142aw Biecek (MI2DataLab, Warsaw University of Technology)<\/span> <\/p>\n

Poster 02: forester: growing transparent tree-based models for everyone (poster)<\/a>
<\/strong>Anna Kozak (Warsaw University of Technology)<\/u>, Hubert Ruczy\u0144ski (Warsaw University of Technology), Patryk S\u0142owakiewicz (Warsaw University of Technology), Adrianna Grudzie\u0144 (Warsaw University of Technology)<\/span> <\/p>\n

Poster 03: Rapid reinforcement learning with the hierarchy of policies that chase fleeing targets
<\/strong>Micha\u0142 Bortkiewicz (Warsaw University of Technology)<\/u>, Jakub \u0141yskawa, Artur Grudkowski, Pawe\u0142 Wawrzy\u0144ski, Mateusz Ostaszewski <\/p>\n

Poster 04: Risk assessment of Polish joint stock companies using machine learning methods (poster)<\/a>
<\/strong>Aleksandra Szymura (Wroclaw University of Economics and Business<\/span>)<\/u> <\/p>\n

Poster 05: Informed Guided Rapidly-exploring Random Trees*-Connect for Near-Optimal Path Planning (poster)<\/a>
<\/strong>Dominik Belter<\/span> (Poznan University of Technology)<\/u> <\/p>\n

Poster 06: Continual learning on 3D point clouds with random compressed rehearsal<\/span> (poster)<\/a>
<\/strong>Maciej Zamorski<\/span> (Wroc\u0142aw University of Science and Technology, Hemolens Diagnostics)<\/u>, Micha\u0142 Stypu\u0142kowski (University of Wroc\u0142aw), Konrad Karanowski (Wroc\u0142aw University of Science and Technology), Tomasz Trzci\u0144ski (Warsaw University of Technology, IDEAS NCBR, Tooploox, Jagiellonian University), Maciej Zi\u0119ba (Wroc\u0142aw University of Science and Technology, Tooploox)<\/span> <\/p>\n

Poster 07: Machine Translation - from research to production<\/span> (poster)<\/a>
<\/strong>Karol Grzegorczyk<\/span> (Allegro Machine Learning Research<\/span>)<\/u>, Karol Karpi\u0144ski (Allegro Machine Learning Reaserch), Miko\u0142aj Koszowski (Allegro Machine Learning Reaserch)<\/span> <\/p>\n

Poster 08: Physics Informed Neural Network (PINN) for Infrasound propagation<\/span>
<\/strong>Nikesh Yadav<\/span> (Nicolaus Copernicus Astronomical Center, Polish Academy of Sciences<\/span>)<\/u> <\/p>\n

Poster 09: Neural Architecture for Online Ensemble Continual Learning<\/span> (poster)<\/a>
<\/strong>Mateusz W\u00f3jcik<\/span> (Alphamoon, Wroclaw University of Science and Technology<\/span>)<\/u>, Witold Ko\u015bciukiewicz (Alphamoon, Wroclaw University of Science and Technology), Adam Gonczarek (Alphamoon), Tomasz Kajdanowicz (Wroclaw University of Science and Technology)<\/span> <\/p>\n

Poster 10: QAOCDI: Deep Learning strikes at orthophotos analysis as never before<\/span> (poster)<\/a>
<\/strong>Przemyslaw Aszkowski<\/span> (Poznan University of Technology)<\/u>, Bartosz Ptak (Poznan University of Technology), Marek Kraft (Poznan University of Technology)<\/span> <\/p>\n

Poster 11: STALKer: Terribly Accurate, Horribly Fast, Deep Learning Pipeline for Automatic Hemp Stalks Segmentation and Grasping Point Detection<\/span> (poster)<\/a>
<\/strong>Mateusz Piechocki<\/span> (Poznan University of Technology)<\/u>, Dominik Pieczy\u0144ski (Poznan University of Technology), Marek Kraft (Poznan University of Technology)<\/span> <\/p>\n

Poster 12: Contrastive Learning for Multilingual Named Entity Linking<\/span>
<\/strong>Adam Kaczmarek<\/span> (University of Wroc\u0142aw<\/span>)<\/u> <\/p>\n

Poster 13: Memory Enhanced Document-level Joint Entity and Relation Extraction<\/span> (poster)<\/a>
<\/strong>Witold Ko\u015bciukiewicz<\/span> (Alphamoon, Wroclaw University of Science and Technology<\/span>)<\/u>, Mateusz W\u00f3jcik (Alphamoon, Wroclaw University of Science and Technology),<\/span> Adam Gonczarek (Alphamoon), Tomasz Kajdanowicz (Wroclaw University of Science and Technology)<\/span> <\/p>\n

Poster 14: Across space and across seasons - aerial imagery place recognition for navigation support<\/span>
<\/strong>Marek Kraft<\/span> (Pozna\u0144 University of Technology<\/span>)<\/u>, Micha\u0142 W\u0119grzynowski (Pozna\u0144 University of Technology), Dominik Pieczy\u0144ski (Pozna\u0144 University of Technology)<\/span> <\/p>\n

Poster 15: Biased AI image generations models and misconceptions about health conditions, but not only<\/span>
<\/strong>Adam Zadro\u017cny<\/span> (National Centre for Nuclear Research, University of Warsaw)<\/span><\/u>, Marianna Zadro\u017cna (ASP)<\/span> <\/p>\n

Poster 16: How to see through the objects on the occluded scene?<\/span> (poster)<\/a>
<\/strong>Miko\u0142aj Zieli\u0144ski<\/span> (Poznan University of Technology<\/span>)<\/u> <\/p>\n

Poster 17: Parametrization of radiological reports using pattern matching and language models<\/span>
<\/strong>Aleksander Obuchowski<\/span> (Gda\u0144sk University of Technology<\/span>)<\/u>, Barbara Klaudel (Gda\u0144sk University of Technology), Micha\u0142 Sta\u0144czyk (SentiOne)<\/span> <\/p>\n

Poster 18: Automatic image generation for application of advertisements generation based on diffusion models<\/span> (poster)<\/a>
<\/strong>Karol Piniarski<\/span> (Lingaro)<\/u> <\/p>\n

Poster 19: Automation of Citation Screening for Systematic Literature Reviews with the Usage of Eligibility Criteria<\/span>
<\/strong>Wojciech Kusa<\/span> (TU Wien<\/span>)<\/u>, Allan Hanbury (TU Wien), Petr Knoth (The Open University)<\/span> <\/p>\n

Poster 20: Previous opinions is all you need. Legal opinions retrieval system<\/span> (poster)<\/a>
<\/strong>Maciej Osowski<\/span> (Emplocity S.A.<\/span>),<\/u>Katarzyna Lorenc (Emplocity S.A.)<\/span> <\/p>\n

Poster 21: An active preference learning approach to aid the selection of validators in blockchain environments<\/span>
<\/strong>Grzegorz Miebs<\/span> (Poznan University of Technology; PSI Polska<\/span>)<\/u>, Jonas Gehrlein (Web3 Foundation), Matteo Brunelli (University of Trento), Mi\u0142osz Kadzi\u0144ski (Poznan University of Technology)<\/span> <\/p>\n

Poster 22: Challenges of domain adaptation in medical domain<\/span> (poster)<\/a>
<\/strong>Barbara Klaudel<\/span> (Radiato.ai; Gda\u0144sk University of Technolog; Orange<\/span>)<\/u>, Wasyl Badyra (Radiato.ai; Gda\u0144sk University of Technology; Sii), Piotr Fr\u0105ckowski (Radiato.ai; Gda\u0144sk University of Technology; Enamor), Sebastian Krajna (Radiato.ai; Gda\u0144sk University of Technology; MaxiEcu)<\/span> <\/p>\n

Poster 23: Coronary Ostia Localization Using Residual U-Net with Heatmap Matching and 3D DSNT<\/span> (poster)<\/a>
<\/strong>Mi\u0142osz Gajowczyk<\/span> (Hemolens Diagnostics<\/span>)<\/u>, Patryk Rygiel (Hemolens Diagnostics), Tomasz Konopczy\u0144ski (Hemolens Diagnostics)<\/span> <\/p>\n

Poster 24: Review of the no-show problem<\/span> (poster)<\/a>
<\/strong>Magdalena Cebula<\/span> (Orange)<\/u>, Jan Tarasiewicz, Mateusz Rymuza, Dominik St\u0119pnie\u0144, Adam Skorek<\/span> <\/p>\n

Poster 25: Application of Machine Learning for Early Cancer Detection<\/span> (poster)<\/a>
<\/strong>Rohit Thanki<\/span> (KRiAN GmbH<\/span>)<\/u>, Purva Joshi (Wroclaw University of Science and Technology)<\/span> <\/p>\n

Poster 26: Deep learning based prediction of flow behind circular cylinders for application in wind Turbines<\/span>
<\/strong> Nikesh Yadav<\/span> (Nicolaus Copernicus Astronomical Center, Polish Academy of Sciences<\/span>)<\/u>, Yurii Kurchenko (Warsaw University of Technology), Kacper Paw\u0142owski (Warsaw University of Technology), Dominika Czerwi\u0144ska (Warsaw University of Technology)<\/span> <\/p>\n

Poster 27: How could ML and AI help people with disabilities?<\/span>
<\/strong>Anna Tumanova<\/span> (Lingaro<\/span>)<\/u> <\/p>\n

Poster 28: Monitoring system of NLP models - why? what? and how to built one yourself.<\/span> (poster)<\/a>
<\/strong>Wojciech Pyrak<\/span> (Tidio<\/span>)<\/u>, \u0141ukasz Woronkiewicz (Tidio)<\/span> <\/p>\n

Poster 29: Neural-network based atomistic modeling of plastic deformation mechanisms in single-crystalline molybdenum<\/span> (poster)<\/a>
<\/strong>Amirhossein Naghdi Dorabati<\/span> (NOMATEN CoE, National Centre for Nuclear Research<\/span>)<\/u>, Mikko Alava (Aalto University), Stefanos Papanikolaou (NOMATEN CoE, National Centre for Nuclear Research)<\/span> <\/p>\n

Poster 30: Challenges in the automatic analysis of images from capsule endoscopy<\/span> (poster)<\/a>
<\/strong>Edyta Rogula<\/span> (Biocam<\/span>)<\/u>, Julia Pietraszek (Biocam), Amelia Okulewicz (Biocam)<\/span> <\/p>\n

Poster 31: Modern data augmentation, why so unintuitive? Overview of mixing augmentation methods.<\/span> (poster)<\/a>
<\/strong>Dominik Lewy<\/span> (Lingaro<\/span>)<\/u> <\/p>\n

Poster 32: State-of-the-Art Polish\u2013Ukrainian Machine Translation (poster)<\/a>
<\/strong>Helena Skowro\u0144ska (Shopai. sp. z o. o.)<\/u>, Pawe\u0142 Wnuk (Shopai. sp. z o. o.) <\/p>\n

Poster 33: BrightBox - explainable AI class tool to diagnose errors of ML models
<\/strong>And\u017celika Zalewska (QED Software)<\/span><\/u>, Artur \u017b\u00f3\u0142kowski (QED Software, Warsaw University of Technology), Andrzej Janusz (QED Software) <\/p>\n

Poster 34: Semantic Space of distributional models as compared to human\u2019s abstract categorization and roots for creative association<\/span> (poster)<\/a>
<\/strong>Urszula Kuczma (Expertisly)<\/u>, Joanna R\u0105czaszek-Leonardi (University of Warsaw), Kristian Tylen (University of Aarhus) <\/p>\n <\/div>\n <\/div>\n <\/div>\n \n <\/div>\n \n <\/section>\n \n","protected":false},"excerpt":{"rendered":"

#Accepted Talks Automated Harmful Content Detection Using Grammar-Focused Representations of Text Data (slides)Daria Stetsenko (NASK PIB), Inez Okulska (NASK PIB) Building more…<\/p>\n","protected":false},"author":5,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-3498","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/conference2022.mlinpl.org\/wp-json\/wp\/v2\/pages\/3498","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/conference2022.mlinpl.org\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/conference2022.mlinpl.org\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/conference2022.mlinpl.org\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/conference2022.mlinpl.org\/wp-json\/wp\/v2\/comments?post=3498"}],"version-history":[{"count":33,"href":"https:\/\/conference2022.mlinpl.org\/wp-json\/wp\/v2\/pages\/3498\/revisions"}],"predecessor-version":[{"id":4448,"href":"https:\/\/conference2022.mlinpl.org\/wp-json\/wp\/v2\/pages\/3498\/revisions\/4448"}],"wp:attachment":[{"href":"https:\/\/conference2022.mlinpl.org\/wp-json\/wp\/v2\/media?parent=3498"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}