EXtreme Analytics for MINing Data spaces

Información del proyecto

EXA4MIND

Identificador del acuerdo de subvención: 101092944

DOI

10.3030/101092944

Proyecto cerrado

Fecha de la firma de la CE 23 Noviembre 2022

Fecha de inicio 1 Enero 2023

Fecha de finalización 30 Abril 2026

Financiado con arreglo a

• Digital, Industry and Space

Coste total

€ 4 911 425,00

Aportación de la UE

€ 4 911 425,00

Coordinado por

VSB - TECHNICAL UNIVERSITY OF OSTRAVA
Czechia

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

Documents, reports (7)

Application Cases and Architecture Requirements
Extreme Data Flow Patterns – Report
Data and Workflow Management Toolbox Alpha Status Report
Dissemination & Communication Interim Report
Architecture of AQIS
Continuous Improvements of Architecture, and Release management Process and System
Impact Master Plan

Other (1)

Intermediate Version of the ADAMS4SIMS System

Data Management Plan (1)

Data Management Plan

Publicaciones

Conference proceedings (17)

terazi: AI Fairness Tool for Doubly Imbalanced Data

Autores: Asli Umay Ozturk; Yigit Sever; Ata Yalcin; Viktoria Pauw; Stephan Hachinger; Ismail Hakki Toroslu; Pinar Karagoz
Publicado en: Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025
Editor: ACM
DOI: 10.1145/3746252.3761465

Wine in the Cloud, or: Smart Vineyards with a Distributed “Extreme Data Database” and Supercomputing

Autores: Piyush Harsh,,∗ Stephan Hachinger, Marc Derquennes, Andy Edmonds,Pinar Karagoz, Martin Golasowski, Mohamad Hayek and Jan Martinovič
Publicado en: ISGC&HEPiX2023, 2023
Editor: PoS
DOI: 10.22323/1.434.0021

Explaining Veracity Predictions with Evidence Summarization: A Multi-Task Model Approach

Autores: Recep Firat Cekinel, Pinar Karagoz
Publicado en: 2024 IEEE International Conference on Big Data (BigData), 2025
Editor: IEEE
DOI: 10.48550/ARXIV.2402.06443

Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategies

Autores: Karagöz, Pınar; Çekinel, Recep Fırat; Çöltekin, Çağrı
Publicado en: Proceedings of the 31st International Conference on Computational Linguistics, 2025
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2412.05155

Halton Scheduler For Masked Generative Image Transformer

Autores: Victor Besnier, Mickael Chen, David Hurych, Eduardo Valle, Matthieu Cord
Publicado en: International Conference on Learning Representations (ICLR), 2025
Editor: OpenReview
DOI: 10.48550/ARXIV.2503.17076

Three Pillars improving Vision Foundation Model Distillation for Lidar

Autores: Gilles Puy, Spyros Gidaris, Alexandre Boulch, Oriane Siméoni, Corentin Sautier, Patrick Pérez, Andrei Bursuc, Renaud Marlet
Publicado en: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Editor: IEEE/CVPR
DOI: 10.48550/ARXIV.2310.17504

Annealed Winner-Takes-All for Motion Forecasting

Autores: Xu, Yihong; Letzelter, Victor; Chen, Mickaël; Zablocki, Éloi; Cord, Matthieu
Publicado en: 2025 IEEE International Conference on Robotics and Automation (ICRA), 2025
Editor: IEEE
DOI: 10.48550/ARXIV.2409.11172

Database-aided Workflows on HPC for Plasma Physics Simulation

Autores: Viktoria Maike Paula Pauw, Hachinger Stephan, Jan Martinovič, Stephan Hachinger
Publicado en: Proceedings of International Symposium on Grids & Clouds (ISGC2025) — PoS(ISGC2025), 2025
Editor: Sissa Medialab
DOI: 10.22323/1.488.0024

Make Satire Boring Again: Reducing Stylistic Bias of Satirical Corpus by Utilizing Generative LLMs

Autores: Öztürk, Aslı Umay; Çekinel, Recep Fırat; Karagöz, Pınar
Publicado en: Proceedings of the 18th Workshop on Building and Using Comparable Corpora (BUCC), 2025
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2412.09247

Management of Physics Simulations with Databases

Autores: Viktoria Maike Paula Pauw, David Číž, Vojtěch Mlýnský, Pavel Banáš, Michal Otyepka, Stephan Hachinger, Jan Martinovič
Publicado en: Proceedings of International Symposium on Grids & Clouds (ISGC) 2024 — PoS(ISGC2024), 2024
Editor: Sissa Medialab
DOI: 10.22323/1.458.0031

Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?

Autores: Xu, Yihong; Chambon, Loïck; Zablocki, Éloi; Chen, Mickaël; Alahi, Alexandre; Cord, Matthieu; Pérez, Patrick
Publicado en: 2024 IEEE International Conference on Robotics and Automation (ICRA), 2024
Editor: IEEE
DOI: 10.48550/ARXIV.2306.09281

POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images (pre-print version)

Autores: Antonín Vobecký, Oriane Siméoni, David Hurych, Spyros Gidaris, Andrei Bursuc, Patrick Perez, Josef Sivic
Publicado en: NeurIPS 2023, 2024
Editor: NeurIPS

ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions

Autores: Tomás Soucek; Prajwal Gatti; Michael Wray; Ivan Laptev; Dima Damen; Josef Sivic
Publicado en: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Editor: IEEE
DOI: 10.48550/ARXIV.2412.01987

Cross-Lingual Learning vs. Low-Resource Fine-Tuning: A Case Study with Fact-Checking in Turkish

Autores: Firat Cekinel, Pinar Karagoz, Cagri Coltekin
Publicado en: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024
Editor: ELRA and ICCL

OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks

Autores: Sophia Sirko-Galouchenko, Alexandre Boulch, Spyros Gidaris, Andrei Bursuc, Antonin Vobecky, Patrick Pérez, Renaud Marlet
Publicado en: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024
Editor: IEEE
DOI: 10.1109/CVPRW63382.2024.00452

GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos

Autores: Tomás Soucek; Dima Damen; Michael Wray; Ivan Laptev; Josef Sivic
Publicado en: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Editor: IEEE
DOI: 10.48550/ARXIV.2312.07322

IndexAI: AI Based Index Selection for NoSQL Databases (pre-print version)

Autores: Mohammad Mahdi Khosravi, Pinar Karagoz, and Ismail Hakki Toroslu
Publicado en: 2023 IEEE International Conference on Big Data, 2024
Editor: IEEE
DOI: 10.1109/BigData59044.2023.10386521

Other (11)

Poster: ADAMS4SIMS - Database Curation for MD Simulations

Autores: Číž, D., Furmánek, R., Pauw, V., Martinovič, J., Otyepka, M., Banáš, P., Mlýnský, V.
Publicado en: HPCSE 2024, 2024
Editor: Zenodo
DOI: 10.5281/ZENODO.12704253

Poster: Integrated Database of Force-Field Parameters, Experimental Measurements, and Molecular Dynamics Simulations as a Tool for Force Field Development

Autores: Pavel Banas, Mlynsky Vojtech, David Ciz, Radek Furmanek, Nestor Pilat, Anna Spackova, Viktoria Pauw, Stephan Hachinger, Jiri Sponer, Jan Martinovic, Michal Otyepka
Publicado en: CECAM Workshop “RNA Modelling Across Scales” 2025, 2025
Editor: Zenodo
DOI: 10.5281/ZENODO.19916756

Poster: A universal molecular force field format for transparent and accessible parameters for MD simulations of biomolecular systems

Autores: Banáš, P., Mlýnský, V., Číž, D., Furmánek, R., Pilát, N., Špačková, A., Pauw, V., Hachinger, S., Šponer, J., Martinovič, J., Otyepka, M.
Publicado en: CECAM Workshop “RNA Modelling Across Scales”, 2025
Editor: Zenodo
DOI: 10.5281/ZENODO.19923305

Poster: Integrated Database of Force-Field Parameters, Experimental Measurements and Molecular Dynamics Simulations as a Tool for Force Field Development

Autores: Banáš, P., Mlýnský, V., Číž, D., Furmánek, R., Pilát, N., Špačková, A., Pauw, V., Hachinger, S., Šponer, J., Martinovič, J., Otyepka, M.
Publicado en: EuChemS CompChem 2025 “Shaping the Future of Chemistry”, 2025
Editor: Zenodo
DOI: 10.5281/ZENODO.17174936

Poster: Optimised DBMS Deployments and DBMS Benchmarks for Extreme Data Workflows

Autores: Gurbanov, H., Brunati, R., Karagoz, P., Toroslu, I. H., Hayek, M., Golasowski, M., Hachinger, S., Martinovič, J.
Publicado en: HPCSE 2024, 2024
Editor: Zenodo
DOI: 10.5281/ZENODO.19923504

Poster: Tuning and tweaking of the state-of-the-art amber OL3 RNA force field

Autores: Mlýnský, V., Kührová, P., Krepl, M., Stadlbauer, P., Otyepka, M., Bussi, G., Banáš, P., Šponer, J.
Publicado en: EuChemS CompChem 2023, 2023
Editor: Zenodo
DOI: 10.5281/ZENODO.19923213

Poster: POP3D: Open-Vocabulary 3D Occupancy Prediction from Images

Autores: A. Vobecky, O. Siméoni, D. Hurych, S. Gidaris, A. Bursuc, P. Pérez, J. Šivic
Publicado en: NeurIPS 2023, 2024
Editor: Zenodo
DOI: 10.5281/ZENODO.12704479

Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic Consistency

Autores: Patrik Vacek, David Hurych, Karel Zimmermann, Tomáš Svoboda
Publicado en: 2024
Editor: ArXiv
DOI: 10.48550/ARXIV.2312.08879

Poster: Tapping Data Spaces in HPC: Enabling, Exploring and Benchmarking Database & Object Store Usage

Autores: Mohamad Hayek, Stephan Hachinger, Huseyn Gurbanov, Viktoria Pauw, Martin Golasowski, Jan Martinovič, Pinar Karagoz, Ismail Hakki Toroslu
Publicado en: SCA/HPC Asia 2026, 2026
Editor: Zenodo
DOI: 10.5281/ZENODO.19912565

Poster: EXA4MIND AI Inference Service Solution

Autores: Adam Matus, Jan Martinovic, Jakub Konvicka, Tomas Martinovic, Firat Cekinel, Görkem Özer, Pinar Karagoz, Ismail Toroslu
Publicado en: SCA/HPC Asia 2026, 2026
Editor: Zenodo
DOI: 10.5281/ZENODO.19912708

Poster: How to Make Data Pipeline Scalable: A Case Study for Healthcare Data Analytics

Autores: Atakan Gelecek, Pinar Karagoz Ismail Hakki Toroslu, Stephan Hachinger, Jan Martinovic
Publicado en: SCA/HPC Asia 2026, 2026
Editor: Zenodo
DOI: 10.5281/ZENODO.19912338

Peer reviewed articles (10)

DocSpider: a dataset of cross-domain natural language querying for MongoDB

Autores: Arif Görkem Özer; Recep Firat Cekinel; Ismail Hakki Toroslu; Pinar Karagoz
Publicado en: Natural Language Processing, 2025, ISSN 2977-0424
Editor: Cambridge University Press
DOI: 10.1017/NLP.2024.63

Destabilization of Structured RNAs by OPC and TIP4PD Water Models

Autores: Miroslav Krepl, Vojtěch Mlýnský, Agnesa Rusnáková, Pavel Banáš, Michal Otyepka, Jiří Šponer
Publicado en: Journal of Chemical Theory and Computation, Edición 22, 2026, ISSN 1549-9618
Editor: American Chemical Society (ACS)
DOI: 10.1021/ACS.JCTC.5C01678

The Kink-Turn 7 Motif: An Additional Test for RNA Force Field Performance

Autores: Toon Lemmens, Vojtěch Mlýnský, Jiří Šponer, Martin Pykal, Pavel Banáš, Michal Otyepka, Miroslav Krepl
Publicado en: Journal of Chemical Theory and Computation, Edición 21, 2025, ISSN 1549-9618
Editor: American Chemical Society (ACS)
DOI: 10.1021/ACS.JCTC.5C00776

Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation

Autores: Antonín Vobecký; David Hurych; Oriane Siméoni; Spyros Gidaris; Andrei Bursuc; Patrick Pérez; Josef Sivic
Publicado en: International Journal of Computer Vision, 2025, ISSN 1573-1405
Editor: Springer Nature
DOI: 10.1007/S11263-024-02320-3

MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments

Autores: Spyros Gidaris, Andrei Bursuc, Oriane Simeoni, Antonin Vobecky, Nikos Komodakis, Matthieu Cord, Patrick Pérez
Publicado en: Transactions on Machine Learning Research, Edición 2, 2024, ISSN 2835-8856
Editor: JMLR
DOI: 10.48550/arXiv.2307.09361

Let It Flow: Simultaneous Optimization of 3D Flow and Object Clustering

Autores: Patrik Vacek, David Hurych, Karel Zimmermann, Tomáš Svoboda
Publicado en: IEEE Transactions on Intelligent Vehicles, Edición 10, 2026, ISSN 2379-8904
Editor: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TIV.2024.3443316

Simple Adjustment of Intranucleotide Base-Phosphate Interaction in the OL3 AMBER Force Field Improves RNA Simulations

Autores: Vojtěch Mlýnský, Petra Kührová, Petr Stadlbauer, Miroslav Krepl, Michal Otyepka, Pavel Banáš*, and Jiří Šponer*
Publicado en: (JCTC) Journal of Chemical Theory and Computation, Edición Volume 19, Edición 22, 2023, ISSN 1549-9626
Editor: ACS Publications
DOI: 10.1021/acs.jctc.3c00990

Computer Folding of Parallel <scp>DNA</scp> G‐Quadruplex: Hitchhiker's Guide to the Conformational Space

Autores: Michal Janeček, Petra Kührová, Vojtěch Mlýnský, Petr Stadlbauer, Michal Otyepka, Giovanni Bussi, Jiří Šponer, Pavel Banáš
Publicado en: Journal of Computational Chemistry, Edición 46, 2025, ISSN 0192-8651
Editor: Wiley
DOI: 10.1002/JCC.27535

Can We Ever Develop an Ideal RNA Force Field? Lessons Learned from Simulations of the UUCG RNA Tetraloop and Other Systems

Autores: Vojtěch Mlýnský, Petra Kührová, Martin Pykal, Miroslav Krepl, Petr Stadlbauer, Michal Otyepka, Pavel Banáš, Jiří Šponer
Publicado en: Journal of Chemical Theory and Computation, Edición 21, 2025, ISSN 1549-9618
Editor: American Chemical Society (ACS)
DOI: 10.1021/ACS.JCTC.4C01357

Data management for distributed computational workflows: An iRODS-based setup and its performance

Autores: Mohamad Hayek, Martin Golasowski, Stephan Hachinger, Rubén J. García-Hernández, Johannes Munke, Gabriel Lindner, Kateřina Slaninová, Philipp Tunka, Vít Vondrák, Dieter Kranzlmüller, Jan Martinovič
Publicado en: PLOS One, Edición 21, 2026, ISSN 1932-6203
Editor: Public Library of Science (PLoS)
DOI: 10.1371/JOURNAL.PONE.0340757