Federated foundational models for embodied perception

Informazioni relative al progetto

FRONTIER

ID dell’accordo di sovvenzione: 101097822

DOI

10.3030/101097822

Data della firma CE 11 Maggio 2023

Data di avvio 1 Gennaio 2024

Data di completamento 31 Dicembre 2028

Finanziato da

• European Research Council (ERC)

Costo totale

€ 2 499 825,00

Contributo UE

€ 2 499 825,00

Coordinato da

CESKE VYSOKE UCENI TECHNICKE V PRAZE
Czechia

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Peer reviewed articles (6)

GJK++: Leveraging Acceleration Methods for Faster Collision Detection

Autori: Louis Montaut, Quentin Le Lidec, Vladimir Petrik, Josef Sivic, Justin Carpentier
Pubblicato in: IEEE Transactions on Robotics, Numero 40, 2024, ISSN 1552-3098
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TRO.2024.3386370

Temporally Consistent Object 6D Pose Estimation for Robot Control

Autori: Kateryna Zorina, Vojtech Priban, Mederic Fourmy, Josef Sivic, Vladimir Petrik
Pubblicato in: IEEE Robotics and Automation Letters, Numero 10, 2025, ISSN 2377-3766
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/LRA.2024.3502052

CoVAMPnet: Comparative Markov State Analysis for Studying Effects of Drug Candidates on Disordered Biomolecules

Autori: Sérgio M. Marques; Petr Kouba; Anthony Legrand; Jiri Sedlar; Lucas Disson; Joan Planas-Iglesias; Zainab Sanusi; Antonin Kunka; Jiri Damborsky; Tomas Pajdla; Zbynek Prokop; Stanislav Mazurenko; Josef Sivic; David Bednar
Pubblicato in: JACS Au, Numero 4, 2024, ISSN 2691-3704
Editore: American Chemical Society (ACS Publications)
DOI: 10.1101/2023.01.06.523007

Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS

Autori: Roman Bushuiev; Anton Bushuiev; Raman Samusevich; Corinna Brungs; Josef Sivic; Tomáš Pluskal
Pubblicato in: Nature Biotechnology, Numero 44, 2026, ISSN 1546-1696
Editore: Springer Nature
DOI: 10.26434/CHEMRXIV-2023-KSS3R-V4

Multi-Task Learning of Object States and State-Modifying Actions From Web Videos

Autori: Tomáš Souček, Jean-Baptiste Alayrac, Antoine Miech, Ivan Laptev, Josef Sivic
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numero 46, 2024, ISSN 0162-8828
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.48550/ARXIV.2211.13500

FocalPose++: Focal Length and Object Pose Estimation via Render and Compare

Autori: Martin Cífka, Georgy Ponimatkin, Yann Labbé, Bryan Russell, Mathieu Aubry, Vladimir Petrik, Josef Sivic
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numero 47, 2025, ISSN 0162-8828
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.48550/ARXIV.2312.02985

Conference proceedings (12)

One Protein Is All You Need

Autori: Anton Bushuiev, Roman Bushuiev, Olga Pimenova, Nikola Zadorozhny, Raman Samusevich, Elisabet Manaskova, Rachel Seongeun Kim, Hannes Stärk, Jiri Sedlar, Martin Steinegger, Tomáš Pluskal, Josef Sivic
Pubblicato in: International Conference on Learning Representations (ICLR), 2026
Editore: OpenReview / ICLR Foundation
DOI: 10.48550/ARXIV.2411.02109

Learning to Engineer Protein Flexibility

Autori: Petr Kouba, Joan Planas-Iglesias, Jiri Damborsky, Jiri Sedlar, Stanislav Mazurenko, Josef Sivic
Pubblicato in: International Conference on Learning Representations (ICLR), 2025
Editore: OpenReview / ICLR Foundation
DOI: 10.48550/ARXIV.2412.18275

AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment

Autori: Anna Šárová Mikeštíková, Mederic Fourmy, Martin Cífka, Josef Sivic, Vladimír Petrík
Pubblicato in: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR, 2026
Editore: IEEE / Computer Vision Foundation
DOI: 10.48550/ARXIV.2512.20538

Learning to Design Protein–Protein Interactions with Enhanced Generalization

Autori: Anton Bushuiev, Roman Bushuiev, Petr Kouba, Anatolii Filkin, Marketa Gabrielova, Michal Gabriel, Jiri Sedlar, Tomas Pluskal, Jiri Damborsky, Stanislav Mazurenko, Josef Sivic
Pubblicato in: International Conference on Learning Representations (ICLR), 2024
Editore: OpenReview / ICLR Foundation
DOI: 10.48550/ARXIV.2310.18515

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

Autori: Tomáš Souček, Dima Damen, Michael Wray, Ivan Laptev, Josef Sivic
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Editore: IEEE
DOI: 10.48550/ARXIV.2312.07322

MassSpecGym: A benchmark for the discovery and identification of molecules

Autori: Bushuiev, Roman; Bushuiev, Anton; de Jonge, Niek F.; Young, Adamo; Kretschmer, Fleming; Samusevich, Raman; Heirman, Janne; Wang, Fei; Zhang, Luke; Dührkop, Kai; Ludwig, Marcus; Haupt, Nils A.; Kalia, Apurva; Brungs, Corinna; Schmid, Robin; Greiner, Russell; Wang, Bo; Wishart, David S.; Liu, Li Ping; Rousu, Juho; Bittremieux, Wout; Rost, Hannes; Mak, Tytus D.; Hassoun, Soha; Huber, Florian; van der Hooft, Justin J.J.; Stravs, Michael A.; Böcker, Sebastian; Sivic, Josef; Pluskal, Tomáš
Pubblicato in: Conference on Neural Information Processing Systems (NeurIPS), Datasets & Benchmarks Track, 2024
Editore: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.48550/ARXIV.2410.23326

Generalization Beyond Benchmarks: Evaluating Learnable Protein–Ligand Scoring Functions on Unseen Targets

Autori: Jakub Kopko, David Graber, Saltuk Mustafa Eyrilmez, Stanislav Mazurenko, David Bednar, Jiri Sedlar, Josef Sivic
Pubblicato in: AI for Scientific Discovery Workshop, NeurIPS, 2025
Editore: arXiv (Cornell University)
DOI: 10.48550/ARXIV.2512.05386

De Novo Generation of Functional Terpene Synthases Using TpsGP

Autori: Hamsini Ramanathan, Roman Bushuiev, Matouš Soldát, Jiří Kohout, Téo Hebra, Joshua David Smith, Josef Sivic, Tomáš Pluskal
Pubblicato in: NeurIPS 2025 AI for Science Workshop and Machine Learning for Structural Biology (MLSB) Workshop 2025, 2025
Editore: OpenReview / NeurIPS workshops
DOI: 10.48550/ARXIV.2512.08772

Large-scale Pre-training for Grounded Video Caption Generation

Autori: Evangelos Kazakos, Cordelia Schmid, Josef Sivic
Pubblicato in: IEEE/CVF International Conference on Computer Vision (ICCV), 2025
Editore: IEEE / Computer Vision Foundatio
DOI: 10.48550/ARXIV.2503.10781

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

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

Revealing data leakage in protein interaction benchmarks

Autori: Anton Bushuiev; Roman Bushuiev; Jirí Sedlár; Tomás Pluskal; Jirí Damborský; Stanislav Mazurenko; Josef Sivic
Pubblicato in: GEM Workshop at International Conference on Learning Representations (ICLR), 2024
Editore: OpenReview / ICLR Foundation
DOI: 10.48550/ARXIV.2404.10457

6D Object Pose Tracking in Internet Videos for Robotic Manipulation

Autori: Georgy Ponimatkin, Martin Cífka, Tomáš Souček, Mederic Fourmy, Yann Labbé, Vladimír Petrík, Josef Sivic
Pubblicato in: International Conference on Learning Representations (ICLR), 2025
Editore: OpenReview / ICLR Foundation
DOI: 10.48550/ARXIV.2503.10307