European Lighthouse of AI for Sustainability

CORDIS oferuje możliwość skorzystania z odnośników do publicznie dostępnych publikacji i rezultatów projektów realizowanych w ramach programów ramowych HORYZONT.

Odnośniki do rezultatów i publikacji związanych z poszczególnymi projektami 7PR, a także odnośniki do niektórych konkretnych kategorii wyników, takich jak zbiory danych i oprogramowanie, są dynamicznie pobierane z systemu OpenAIRE .

Rezultaty

Second release of methods for Sustainable AI

Report on the updated versions of the results of T1.2-T1.5, including preliminary testing of methods developed in T1.2.

First release of methods for Sustainable AI

The first release of methods developed in T1.2-T1.5

First release of AI tools for a sustainable society

The first release of algorithms developed in T2.2-T2.3-T2.4

First release of tools for Responsible AI systems

: The first release of methods developed in T3.5

Second release of the AI tools for a sustainable society

Description: Report the updates of T2.2-T2.3, including methods developed in T2.4 for cooperative AI.

Second release of tools for Trustworthy and Responsible AI

Description: Updated versions of the results of T3.2-T3.5.

First release of tools for Trustworthy AI

The first release of algorithms developed in T3.2-T3.4.

First annual report of the programme for reinforcing the world-class European AI community

First report on the activities implemented within the project to grow the ELIAS and ELLIS networks by establishing new research programs and expanding its membership.

First Innovation and Sustainability Report and Development of a Strategic Research Agenda (SRA)

First eport on the innovation and sustainability management strategy to handle the project outcomes. An overview of the comprehensive overview of the required research in the field of Sustainable AI.

First report about the Competitions

First report on the activities concerning the implemented competitions and the resulting scientific advancement.

First annual report on the young talents program implementation

First report of actions implemented in ELIAS for supporting young European talents at the doctoral and master levels.

First periodic report on the European Innovation Alliance

Report on the creation and the activities of the newly established EIA

First annual report on the young talent mobility program

First report on young researchers and mobility actions

Second ELIAS Communication, Dissemination and Exploitation Report

Periodic report on ELIAS strategic approach for dissemination, communication and exploitation

First periodic report on the programme for supporting academic mentors and young talent into technology transfer

First report on organising TTSS, implementing the Sciencepreneurship Fellows programme and setting up Sciencepreneurship Internships

First ELIAS Communication, Dissemination and Exploitation Report

First periodic report on ELIAS strategic approach for dissemination, communication and exploitation.

First annual report on the implementation of the European lighthouse in AI for sustainability

First report actions progressively implemented within ELIAS for expanding the ELIAS and ELLIS Networks with new institutions

Publikacje

Sharp Spectral Rates for Koopman Operator Learning. Neural Information Processing

Autorzy: V.R. Kostic, K. Lounici, P. Novelli, M. Pontil
Opublikowane w: Neural Information Processing Systems (NeurIPS), 2023
Wydawca: NeurIPS
DOI: 10.48550/arXiv:2302.02004

Transfer learning for atomistic simulations using GNNs and kernel mean embeddings

Autorzy: Falk, JI; Bonati, L; Novelli, P; Parrinello, M; Pontil, M
Opublikowane w: In: Oh, Alice and Naumann, Tristan and Globerson, Amir and Saenko, Kate and Hardt, Moritz and Levine, Sergey, (eds.) Advances in Neural Information Processing Systems. (2023), 2023
Wydawca: NeurIPS
DOI: 10.48550/arxiv.2306.01589

Gyrogroup Batch Normalization

Autorzy: Chen, Ziheng; Song, Yue; Wu, Xiao-Jun; Sebe, Niculae
Opublikowane w: International Conference on Learning Representations, 2025
Wydawca: ICLR
DOI: 10.5281/ZENODO.17688995

Diffusion Transformers for Tabular Data Time Series Generation

Autorzy: Garuti, Fabrizio; Sangineto, Enver; Luetto, Simone; Forni, Lorenzo; Cucchiara, Rita
Opublikowane w: ICLR, 2025
Wydawca: ICLR
DOI: 10.48550/ARXIV.2504.07566

Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring

Autorzy: Federico Di Gennaro, Khaled Eldowa, Nicolò Cesa-Bianchi
Opublikowane w: NeurIPS, 2025
Wydawca: NeurIPS
DOI: 10.52202/085713-2430

No-Regret Learning in Bilateral Trade via Global Budget Balance

Autorzy: Martino Bernasconi; Matteo Castiglioni; Andrea Celli; Federico Fusco
Opublikowane w: Proceedings of the 56th Annual ACM Symposium on Theory of Computing, 2024
Wydawca: ACM
DOI: 10.48550/ARXIV.2310.12370

Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning

Autorzy: Rypeść, Grzegorz; Cygert, Sebastian; Trzcinski, Tomasz; Twardowski, Bartłomiej
Opublikowane w: The Thirty-Eighth Annual Conference on Neural Information Processing Systems, 2024
Wydawca: NeurIPS
DOI: 10.5281/zenodo.14409015

BAdd: Bias Mitigation Through Bias Addition

Autorzy: Sarridis, Ioannis; Koutlis, Christos; Papadopoulos, Symeon; Diou, Christos
Opublikowane w: 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2025
Wydawca: IEEE
DOI: 10.5281/ZENODO.17107123

Sharing Key Semantics in Transformer Makes Efficient Image Restoration

Autorzy: Ren, B., Li, Y., Liang, J., Ranjan, R., Liu, M., Cucchiara, R., van Gool, L., Yang, M.-H., & Sebe, N.
Opublikowane w: Neural Information Processing Systems (NeurIPS), 2024
Wydawca: NeurIPS
DOI: 10.48550/arXiv.2405.20008

Novel Class Discovery for Ultra-Fine-Grained Visual Categorization

Autorzy: Liu, Yu; Cai, Yaqi; Jia, Qi; Qiu, Binglin; Wang, Weimin; Pu, Nan
Opublikowane w: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Wydawca: IEEE
DOI: 10.48550/ARXIV.2405.06283

Iterative Explainability for Weakly Supervised Segmentation in Medical PE Detection

Autorzy: Condrea, Florin; Rapaka, Saikiran; Leordeanu, Marius
Opublikowane w: 2024, ISSN 1876-1100
Wydawca: Springer
DOI: 10.48550/ARXIV.2412.07384

A fine-grained characterization of PAC learnability

Autorzy: Marco Bressan, Nataly Brukhim, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen
Opublikowane w: Proceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS 2025), 2025
Wydawca: PMLR

Linear Bandits with Memory

Autorzy: Giulia Clerici; Pierre Laforgue; N. Cesa Bianchi
Opublikowane w: Trans. Mach. Learn. Res., 2024
Wydawca: TMLR
DOI: 10.5281/ZENODO.13880461

Towards Human-AI Complementarity in Matching Tasks

Autorzy: Arnaiz-Rodríguez, Adrián; Corvelo Benz, Nina; Thejaswi, Suhas; Oliver, Nuria; Gomez-Rodriguez, Manuel
Opublikowane w: HLDM @ ECML-PKDD 2025, 2025
Wydawca: arXiv / ECML PKDD
DOI: 10.48550/ARXIV.2508.13285

TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration

Autorzy: Olszewski, Jan; Rymarczyk, Dawid; Wójcik, Piotr; Pach, Mateusz; Zieliński, Bartosz
Opublikowane w: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2311.15335

RMLR: Extending Multinomial Logistic Regression into General Geometries

Autorzy: Ziheng Chen, Yue Song, Rui Wang, Xiao-Jun Wu, Nicu Sebe
Opublikowane w: Neural Information Processing Systems (NeurIPS), 2024
Wydawca: NeurIPS
DOI: 10.48550/arXiv.2409.19433

Understanding Matrix Function Normalizations in Covariance Pooling from the Lens of Riemannian Geometry

Autorzy: Chen, Ziheng; Song, Yue; Wu, Xiao-Jun; Liu, Gaowen; Sebe, Niculae
Opublikowane w: ICLR 2025, 2025
Wydawca: ICLR
DOI: 10.5281/ZENODO.17689051

Connectivity-Driven Pseudo-Labeling Makes Stronger Cross-Domain Segmenters

Autorzy: Zhao, D., Zang, Q., Wang, S., Sebe, N., & Zhong, Z.
Opublikowane w: Neural Information Processing Systems (NeurIPS), December 2024, 2024
Wydawca: NeurIPS
DOI: 10.48550/arXiv.2312.06331

Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning

Autorzy: Goswami, Dipam; Soutif–Cormerais, Albin; Yuyang, Liu; Sandesh, Kamath; Twardowski, Bartłomiej; van de Weijer, Joost
Opublikowane w: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Wydawca: IEEE
DOI: 10.5281/ZENODO.12544249

A Characterization Theorem for Equivariant Networks with Point-wise Activations

Autorzy: M. Pacini, X. Dong, B. Lepri, and G. Santin
Opublikowane w: International Conference on Learning Representations 2024 (ICLR 2024)
Wydawca: ICLR
DOI: 10.48550/ARXIV.2401.09235

Building an AI-Ready Data Infrastructure Towards a SDG-focused Observatory for the Brazilian Amazon

Autorzy: Joao Pita Costa, Mirozlav Polzer, Leonardo Barrionuevo, Joao Paulo Veiga
Opublikowane w: Proceedings of the International Multiconference Information Society (IS2025) / SiKDD 2025, 2025
Wydawca: Jožef Stefan Institute
DOI: 10.70314/IS.2025.SIKDD.17

Best-of-Both-Worlds Algorithms for Linear Contextual Bandits

Autorzy: Kuroki, Yuko; Rumi, Alberto; Tsuchiya, Taira; Vitale, Fabio; Cesa-Bianchi, Nicolò
Opublikowane w: Aritifical Intelligence and Statistics Conference (AISTATS) 2024
Wydawca: PMLR
DOI: 10.5281/ZENODO.13880712

Who Sees the Risk? Stakeholder Conflicts and Explanatory Policies in LLM-based Risk Assessment

Autorzy: Srishti Yadav, Jasmina Gajcin, Erik Miehling, Elizabeth Daly
Wydawca: Zenodo
DOI: 10.48550/ARXIV.2511.03152

Frustratingly Easy Test-Time Adaptation of Vision-Language Models

Autorzy: Farina, Matteo; Franchi, Gianni; Iacca, Giovanni; Mancini, Massimiliano; Ricci, Elisa
Opublikowane w: Advances in Neural Information Processing Systems 37, 2024, ISSN 2331-8422
Wydawca: Curran Associates, Inc. / Neural Information Processing Systems Foundation
DOI: 10.48550/ARXIV.2405.18330

Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning

Autorzy: Stefan Smeu, Dragos-Alexandu Boldisor, Dan Oneata, Elisabeta Oneata
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2412.00175

A Lie Group Approach to Riemannian Normalization for SPD Neural Networks

Autorzy: Z. Chen, Y. Song, Y. Liu, and N. Sebe
Opublikowane w: International Conference on Learning Representations (ICLR)
Wydawca: ICLR
DOI: 10.48550/ARXIV.2403.11261

Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-supervised Learning

Autorzy: Bin Ren, Guofeng Mei, Danda Pani Paudel, Weijie Wang, Yawei Li, Mengyuan Liu, Rita Cucchiara, Luc Van Gool, Nicu Sebe
Opublikowane w: Lecture Notes in Computer Science, Computer Vision – ACCV 2024, 2024
Wydawca: Springer Nature Singapore
DOI: 10.1007/978-981-96-0963-5_4

Debiasing Surgeon: Fantastic Weights and How to Find Them

Autorzy: Nahon, Rémi; De Moura Matos, Ivan Luiz; Nguyen, Van-Tam; TARTAGLIONE, ENZO
Opublikowane w: European Conference on Computer Vision, 2024
Wydawca: Springer
DOI: 10.1007/978-3-031-73013-9_25

Exploiting Curvature in Online Convex Optimization with Delayed Feedback

Autorzy: Qiu, Hao; Esposito, Emmanuel; Zhang, Mengxiao
Opublikowane w: PMLR, 2025
Wydawca: PMLR
DOI: 10.48550/ARXIV.2506.07595

Tiny Inference-Time Scaling with Latent Verifiers

Autorzy: Bucciarelli, Davide; Turri, Evelyn; Baraldi, Lorenzo; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
Opublikowane w: CVF/IEEE International Conference on Computer Vision and Pattern Recognition - Findings (CVPR)
Wydawca: CVF/IEEE
DOI: 10.5281/ZENODO.19369320

Beauty and the Bias: Exploring the Impact of Attractiveness on Multimodal Large Language Models

Autorzy: Gulati, Aditya; D'Incà, Moreno; Sebe, Niculae; Lepri, Bruno; Oliver, Nuria
Opublikowane w: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 2025
Wydawca: ACM
DOI: 10.48550/ARXIV.2504.16104

When Algorithms Play Favorites: Lookism in the Generation and Perception of Faces

Autorzy: Doh, Miriam; Gulati, Aditya; Mancas, Matei; Oliver, Nuria
Opublikowane w: Proceedings of Fourth European Workshop on Algorithmic Fairness, 2025
Wydawca: PMLR
DOI: 10.5281/ZENODO.18015328

Of dice and games: a theory of generalized boosting

Autorzy: Marco Bressan, Nataly Brukhim, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen
Opublikowane w: Proceedings of the 38th Annual Conference on Learning Theory (COLT)., 2025
Wydawca: PMLR

Is Multiple Object Tracking a Matter of Specialization?

Autorzy: Gianluca Mancusi; Mattia Bernardi; Aniello Panariello; Angelo Porrello; Rita Cucchiara; Simone Calderara
Opublikowane w: Advances in Neural Information Processing Systems 37, 2024, ISSN 1049-5258
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2411.00553

Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry

Autorzy: Chen, Ziheng; Song, Yue; Wu, Xiao-Jun; Liu, Gaowen; Sebe, Niculae
Opublikowane w: International Conference on Learning Representations, 2024
Wydawca: ICLR
DOI: 10.5281/ZENODO.17689051

Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals

Autorzy: Davide Lobba, Fulvio Sanguigni, Bin Ren, Marcella Cornia, Rita Cucchiara, Nicu Sebe
Opublikowane w: International Conference on Learning Representations (ICLR)
Wydawca: ICLR

A deep cut into Split Federated Self-supervised Learning

Autorzy: Przewięźlikowski, Marcin; Osial, Marcin; Zieliński, Bartosz; Śmieja, Marek
Opublikowane w: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)
Wydawca: Springer
DOI: 10.5281/ZENODO.12546665

You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control

Autorzy: De Toni, Giovanni; Purificato, Erasmo; Gomez, Emilia; passerini, andrea; Lepri, Bruno; Consonni, Cristian
Opublikowane w: ACM, 2025
Wydawca: ACM
DOI: 10.1145/3705328.3748054

Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery

Autorzy: Xiao Liu, Nan Pu, Haiyang Zheng, Wenjing Li, Nicu Sebe, Zhun Zhong
Opublikowane w: ICCV 2025, 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2507.04051

Scaling Vision-Language Models Is Not Enough to Mitigate Bias

Autorzy: Ioannis Sarridis, Ioannis Kompatsiaris, Symeon Papadopoulos
Opublikowane w: ACM MM, 2026
Wydawca: ACM
DOI: 10.1145/3767308.3836012

CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP

Autorzy: Songlong Xing; Zhengyu Zhao; Nicu Sebe
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Wydawca: IEEE
DOI: 10.1109/CVPR52734.2025.01413

Finding the PG schema of any (semi)structured dataset: a tale of graphs and abstraction

Autorzy: Barret, Nelly; Enache, Tudor; Manolescu, Ioana; Mohanty, Madhulika
Opublikowane w: 2024 IEEE 40th International Conference on Data Engineering Workshops (ICDEW), 2024
Wydawca: IEEE
DOI: 10.1109/ICDEW61823.2024.00055

Revisiting Supervision for Continual Representation Learning

Autorzy: Marczak, Daniel; Cygert, Sebastian; Trzciński, Tomasz; Twardowski, Bartłomiej
Opublikowane w: The 18th European Conference on Computer Vision (ECCV)
Wydawca: Springer
DOI: 10.5281/ZENODO.13841791

AlignCAT: Visual-Linguistic Alignment of Category and Attribute for Weakly Supervised Visual Grounding

Autorzy: Yidan Wang, Chenyi Zhuang, Wutao Liu, Pan Gao, Nicu Sebe
Opublikowane w: ACM Multimedia, 2025
Wydawca: ACM
DOI: 10.1145/3746027.3755751

Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning

Autorzy: Haiyang Zheng, Nan Pu, Wenjing Li, Teng Long, Nicu Sebe, Zhun Zhong
Opublikowane w: AAAI 2026, 2026
Wydawca: IEEE
DOI: 10.1609/AAAI.V40I16.38341

On the Brazilian Observatory for Artificial Intelligence

Autorzy: Rafael Meira Silva, Cristina Godoy Oliveira, Luiz Costa, Joao Paulo Candia Vieira and Joao Pita Costa
Opublikowane w: In Proceedings of the SIKDD 2024
Wydawca: Jožef Stefan Instutute
DOI: 10.70314/IS.2024.SIKDD.18

FairShap: A Data Re-weighting Approach for Algorithmic Fairness based on Shapley Values

Autorzy: Adrian, Rodriguez; Oliver, Nuria
Opublikowane w: ICLR 2024 workshop on Data-centric Machine Learning Research (DMLR)
Wydawca: ICLR
DOI: 10.48550/ARXIV.2303.01928

Dynamic Regret Reduces to Kernelized Static Regret

Autorzy: Andrew Jacobsen, Alessandro Rudi, Francesco Orabona, Nicolo Cesa-Bianchi
Opublikowane w: NeurIPS, 2025
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2507.05478

FreeInsert: Disentangled Text-Guided Object Insertion in 3D Gaussian Scene without Spatial Priors

Autorzy: Chenxi Li; Weijie Wang; Qiang Li; Nicu Sebe; Bruno Lepri; Weizhi Nie
Opublikowane w: Proceedings of the 33rd ACM International Conference on Multimedia, 2025
Wydawca: ACM
DOI: 10.48550/ARXIV.2505.01322

Not All Splits Are Equal: Rethinking Attribute Generalization Across Unrelated Categories

Autorzy: Firca, Liviu Nicolae; Barbalau, Antonio; Oneață, Dan; Burceanu, Elena
Opublikowane w: NeurIPS 2025 Workshop (Accepted at CauScien: Uncovering Causality in Science, and Reliable ML from Unreliable Data), 2025
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2509.06998

Improving Fairness using Vision-Language Driven Image Augmentation

Autorzy: D'Inca`, Moreno; Tzelepis, Christos; Patras, Ioannis; Sebe, Nicu
Opublikowane w: 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
Wydawca: IEEE
DOI: 10.48550/arxiv.2311.01573

Learning (Approximately) Equivariant Networks via Constrained Optimization

Autorzy: Andrei Manolache, Luiz F. O. Chamon, Mathias Niepert
Opublikowane w: NeurIPS ORAL, 2025
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2505.13631

FactCheckBureau: Build Your Own Fact-Check Analysis Pipeline

Autorzy: Gaur, Garima
Opublikowane w: CIKM, 2024
Wydawca: ACM
DOI: 10.1145/3627673.3679220

Putting Context in Context: the Impact of Discussion Structure on Text Classification

Autorzy: Penzo, Nicolò; Longa, Antonio; Lepri, Bruno; Tonelli, Sara; Guerini, Marco
Opublikowane w: 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2024
Wydawca: ACL
DOI: 10.48550/arxiv.2402.02975

Automated In-the-Wild Data Collection for Continual AI Generated Image Detection

Autorzy: Thanasis Pantsios, Dimitrios Karageorgiou, Christos Koutlis, George Karantaidis, Olga Papadopoulou, Symeon Papadopoulos
Opublikowane w: ACM International Workshop on Multimedia AI against Disinformation 2026 (MAD 2026), 2026
Wydawca: ACM
DOI: 10.1145/3810988.3812662

Reconsidering Fairness Through Unawareness From the Perspective of Model Multiplicity

Autorzy: Benedikt Höltgen, Nuria Oliver
Opublikowane w: Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMo 25)), 2025
Wydawca: ACM
DOI: 10.1145/3757887.3763007

Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery

Autorzy: Rypeść, Grzegorz; Marczak, Daniel; Cygert, Sebastian; Trzciński, Tomasz; Twardowski, Bartłomiej
Opublikowane w: The 18th European Conference on Computer Vision (ECCV)
Wydawca: Springer Science+Business Media
DOI: 10.5281/ZENODO.13833979

Riemannian Multinomial Logistics Regression for SPD Neural Networks

Autorzy: Chen, Ziheng; Song, Yue; Liu, Gaowen; Rao Kompella, Ramana; Wu, Xiao-Jun; Sebe, Nicu
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Wydawca: IEEE
DOI: 10.1109/CVPR52733.2024.01617

Distributed Multi-Agent Bandits Over Erdós-Rényi Random Networks

Autorzy: Jingyuan Liu, Hao Qiu, Lin Yang, Mengfan Xu
Opublikowane w: NeurIPS
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2510.22811

Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning

Autorzy: Pier Giuseppe Sessa; Pierre Laforgue; N. Cesa Bianchi; Andreas Krause
Opublikowane w: Advances in Neural Information Processing Systems 36, 2023
Wydawca: NeurIPS
DOI: 10.48550/arxiv.2308.01744

Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation

Autorzy: Barsellotti, Luca; Amoroso, Roberto; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
Opublikowane w: CVF/IEEE International Conference on Computer Vision and Pattern Recognitiom (CVPR)
Wydawca: IEEE
DOI: 10.1109/CVPR52733.2024.00354

Fully-Geometric Cross-Attention for Point Cloud Registration

Autorzy: Wang, Weijie; Mei, Guofeng; Zhang, Jian; Sebe, Niculae; Lepri, Bruno; Poiesi, Fabio
Opublikowane w: 2025 International Conference on 3D Vision (3DV), 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2502.08285

MassSpecGym: A benchmark for the discovery and identification of molecules

Autorzy: 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
Opublikowane w: Advances in Neural Information Processing Systems 37, 2024, ISSN 1049-5258
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2410.23326

SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting

Autorzy: Mengjiao Ma, Qi Ma, Yue Li, Jiahuan Cheng, Runyi Yang, Bin Ren, Nikola Popovic, Mingqiang Wei, Nicu Sebe, Luc Van Gool, Theo Gevers, Martin R. Oswald, Danda Pani Paudel
Opublikowane w: NeurIPS 2025, 2025
Wydawca: NeurIPS 2025
DOI: 10.48550/ARXIV.2506.08710

MagMax: Leveraging Model Merging for Seamless Continual Learning

Autorzy: Marczak, Daniel; Twardowski, Bartłomiej; Trzciński, Tomasz; Cygert, Sebastian
Opublikowane w: The 18th European Conference on Computer Vision (ECCV)
Wydawca: Springer
DOI: 10.5281/ZENODO.13850756

Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers

Autorzy: Dipam Goswami; Bartlomiej Twardowski; Joost van de Weijer 0001
Opublikowane w: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024, ISSN 2160-7516
Wydawca: IEEE
DOI: 10.48550/ARXIV.2404.06622

FedDiverse: Tackling Data Heterogeneity in Federated Learning with Diversity-Driven Client Selection

Autorzy: Németh, Gergely; Fanì, Eros; Ng, Yeat Jeng; Caputo, Barbara; Lozano, Miguel Angel; Oliver, Nuria; Quadrianto, Novi
Opublikowane w: 2025 3rd International Conference on Federated Learning Technologies and Applications (FLTA), 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2504.11216

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

Autorzy: Yan Shu, Hangui Lin, Yexin Liu, Yan Zhang, Gangyan Zeng, Yan Li, Yu Zhou, Ser-Nam Lim, Harry Yang, Nicu Sebe
Opublikowane w: NeurIPS 2025, 2025
Wydawca: NeurIPS
DOI: 10.5281/ZENODO.19207312

AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale

Autorzy: Adam Pardyl, Michał Wronka, Maciej Wołczyk, Kamil Adamczewski, Tomasz Trzciński, Bartosz Zieliński
Opublikowane w: Lecture Notes in Computer Science, Computer Vision – ECCV 2024, 2024
Wydawca: Springer Nature Switzerland
DOI: 10.1007/978-3-031-72664-4_7

Fashion-RAG: Multimodal Fashion Image Editing via Retrieval-Augmented Generation

Autorzy: Fulvio Sanguigni, Davide Morelli, Marcella Cornia, Rita Cucchiara
Opublikowane w: International Joint Conference on Neural Networks (IJCNN), 2025
Wydawca: IEEE
DOI: 10.1109/IJCNN64981.2025.11229186

Online Bayesian Persuasion Without a Clue

Autorzy: Francesco Bacchiocchi; Matteo Bollini; Matteo Castiglioni; Alberto Marchesi 0001; Nicola Gatti 0001
Opublikowane w: Advances in Neural Information Processing Systems 37, 2024, ISSN 1049-5258
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2411.06141

Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers

Autorzy: Pardyl, Adam; Kurzejamski, Grzegorz; Olszewski, Jan; Trzciński, Tomasz; Zieliński, Bartosz
Opublikowane w: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2309.13353

Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments

Autorzy: Barsellotti, Luca; Bigazzi, Roberto; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
Opublikowane w: Thirty-Eighth Annual Conference on Neural Information Processing Systems
Wydawca: NeurIPS
DOI: 10.5281/ZENODO.14031716

Automatic Gain Tuning for Humanoid Robots Walking Architectures Using Gradient-Free Optimization Techniques

Autorzy: Sartore C.; Rando M.; Romualdi G.; Molinari C.; Rosasco L.; Pucci D.
Opublikowane w: 2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids), 2024
Wydawca: IEEE
DOI: 10.48550/ARXIV.2409.18649

OpenBias: Open-set Bias Detection in Generative Models

Autorzy: D'Inca, Moreno; Peruzzo, Elia; Mancini, Massimiliano; Xu, Dejia; Goel, Vidit; Xu, Xingqian; Wang, Zhangyang; Shi, Humphrey; Sebe, Nicu
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Wydawca: IEEE
DOI: 10.1109/CVPR52733.2024.01162

UVMap-ID: A Controllable and Personalized UV Map Generative Model

Autorzy: Weijie Wang, Jichao Zhang, Chang Liu, Xia Li, Xingqian Xu, Humphrey Shi, Nicu Sebe, Bruno Lepri
Opublikowane w: Proceedings of the 32nd ACM International Conference on Multimedia, 2024
Wydawca: ACM
DOI: 10.1145/3664647.3680861

The Role of Transparency in Repeated First-Price Auctions with Unknown Valuations

Autorzy: Nicolo Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Federico Fusco, Stefano Leonardi
Opublikowane w: Proceedings of the 56th Annual ACM Symposium on Theory of Computing, Numer 49, 2024
Wydawca: ACM
DOI: 10.1145/3618260.3649658

CURE2026: Communicating Uncertainty to foster Realistic Expectations via Human-Centered Design

Autorzy: Gajcin, J., Jeromela, J., Wester, J., Schömbs, S., Kleanthous, S., Natesan Ramamurthy, K., Hauptmann, H., & Amin, R. M.
Opublikowane w: ACM Conference on Intelligent User Interfaces (IUI), 2026
Wydawca: ACM
DOI: 10.1145/3742414.3794961

ChronoGraph: A Real-World Graph-Based Multivariate Time Series Dataset

Autorzy: Lutu, Adrian Catalin; Pintilie, Ioana; Burceanu, Elena; Manolache, Andrei
Opublikowane w: NeurIPS 2025 Workshop (Recent Advances in Time Series Foundation Models: Have We Reached the 'BERT Moment'?), 2025
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2509.04449

Linear Bandits with Memory

Autorzy: CLERICI, GIULIA; Laforgue, Pierre; Cesa-Bianchi, Nicolò Antonio
Opublikowane w: Transactions on Machine Learning Research, ISSN 2835-8856
Wydawca: TMLR
DOI: 10.5281/ZENODO.13880461

Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning

Autorzy: Goswami, Dipam; Soutif–Cormerais, Albin; Yuyang, Liu; Sandesh, Kamath; Twardowski, Bartłomiej; van de Weijer, Joost
Opublikowane w: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, ISSN 2575-7075
Wydawca: IEEE
DOI: 10.5281/ZENODO.12544248

Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery

Autorzy: Haiyang Zheng; Nan Pu; Wenjing Li; Nicu Sebe; Zhun Zhong
Opublikowane w: Advances in Neural Information Processing Systems 37, 2024, ISSN 1049-5258
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2410.19213

RAG as a Content-Analysis Assistant: Auditing SDG Discourse in Online Videos

Autorzy: Cristian Safta, Victor Bros, Daniel Gatica-Perez
Opublikowane w: ICMR, ICDAR workshop, 2026
Wydawca: ACM
DOI: 10.1145/3810987.3815539

Observing the Impact of AI in the Progress of Sustainable Development Goal 11

Autorzy: Joao Pita Costa, Leonardo Barrionuevo, Maša Kovič Dine
Opublikowane w: Proceedings of the 23rd IADIS International Conference e-Society 2025, 2025
Wydawca: IADIS Press
DOI: 10.70314/IS.2025.ES.4

Structural Group Unfairness: Measurement and Mitigation by means of the Effective Resistance

Autorzy: A. Arnaiz-Rodriguez, G. Curto and N. Oliver
Opublikowane w: WWW 2024 workshop on Trustworthy Learning on Graphs (TrustLOG)
Wydawca: ACM

Optimizing Resource Consumption in Diffusion Models through Hallucination Early Detection

Autorzy: Betti, Federico; Baraldi, Lorenzo; Baraldi, Lorenzo; Cucchiara, Rita; Sebe, Nicu
Opublikowane w: European Conference on Computer Vision Workshops
Wydawca: Springer
DOI: 10.5281/ZENODO.14031722

Pseudo-SD: Pseudo Controlled Stable Diffusion for Semi-Supervised and Cross-Domain Semantic Segmentation

Autorzy: Dong Zhao, Qi Zang, Shuang Wang, Nicu Sebe, Zhun Zhong
Opublikowane w: ICCV 2025, 2025
Wydawca: IEEE
DOI: 10.5281/ZENODO.19218403

Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion

Autorzy: Szatkowski, Filip; Wójcik, Bartosz; Piórczyński, Mikołaj; Scardapane, Simone
Opublikowane w: The Thirty-Eighth Annual Conference on Neural Information Processing Systems, 2024
Wydawca: NeurIPS
DOI: 10.5281/ZENODO.14409485

SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from a Spectral Perspective

Autorzy: Xu, Zipeng; Xing, Songlong; Sangineto, Enver; Sebe, Nicu
Opublikowane w: 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024, 2024
Wydawca: IEEE
DOI: 10.48550/arxiv.2303.09270

The Simpler The Better: An Entropy-Based Importance Metric To Reduce Neural Networks' Depth

Autorzy: V. Quétu, Z. Liao, E. Tartaglione
Opublikowane w: Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML-PKDD), 2024
Wydawca: Springer
DOI: 10.1007/978-3-031-70365-2_6

Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding

Autorzy: Jinlong Li; Cristiano Saltori; Fabio Poiesi; Nicu Sebe
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Wydawca: IEEE
DOI: 10.1109/CVPR52734.2025.01806

Building an African Water Observatory from Open Data and AI

Autorzy: J. Pita Costa, M. Zaouini, M. Polzer, G. Corzo Perez, M. Crnko, D. Orlic and M. Jermol
Opublikowane w: HHAI 2024 WORKSHOP, 2024
Wydawca: ZENODO
DOI: 10.5281/zenodo.14900575

LumiGauss: Relightable Gaussian Splatting in the Wild

Autorzy: Joanna Kaleta; Kacper Kania; Tomasz Trzcinski; Marek Kowalski
Opublikowane w: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2408.04474

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

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

MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning

Autorzy: """Nedungadi, Vishal; Kariryaa, Ankit; Oehmcke, Stefan; Belongie, Serge; Igel, Christian; Lang, Nico """
Opublikowane w: European Conference on Computer Vision (ECCV), 2024
Wydawca: ECCV
DOI: 10.48550/ARXIV.2405.02771

Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generation

Autorzy: Dimitrios Karageorgiou, Symeon Papadopoulos, Ioannis Kompatsiaris, Efstratios Gavves
Opublikowane w: European Conference on Computer Vision 2026
Wydawca: CVF/IEEE
DOI: 10.48550/ARXIV.2607.15849

Face Age Verification Vulnerabilities Under Simple Appearance Manipulations

Autorzy: Ioannis Sarridis, Ioannis Kompatsiaris, Symeon Papadopoulos
Opublikowane w: BIAS Workshop, ECML PKDD 2026, 2026
Wydawca: Springer

A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems

Autorzy: Thibaut Germain, Rémi Flamary, Vladimir R Kostic, Karim Lounici
Opublikowane w: International Conference on Learning Representations
Wydawca: ZENODO
DOI: 10.5281/ZENODO.19222493

LESS: Label-Efficient and Single-Stage Referring 3D Segmentation

Autorzy: Xuexun Liu, Xiaoxu Xu, Jinlong Li, Qiudan Zhang, Xu Wang, Nicu Sebe, Lin Ma
Opublikowane w: Neural Information Processing Systems (NeurIPS), 2023
Wydawca: NeurIPS
DOI: 10.48550/arXiv.2410.13294

Market making without regret

Autorzy: Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Luigi Foscari, Vinayak Pathak
Opublikowane w: Proceedings of the 38th Annual Conference on Learning Theory (COLT).
Wydawca: PMLR

Bridging Explainability and Embeddings: BEE Aware of Spuriousness

Autorzy: Cristian Daniel Păduraru, Antonio Bărbălau, Radu Filipescu, Andrei Liviu Nicolicioiu, Elena Burceanu
Opublikowane w: ICLR 2026, 2026
Wydawca: ICLR
DOI: 10.48550/ARXIV.2410.18970

Till the Layers Collapse: Compressing a Deep Neural Network Through the Lenses of Batch Normalization Layers.

Autorzy: Liao, Zhu; Hezbri, Nour; Quétu, Victor; Nguyen, Van-Tam; Tartaglione, Enzo
Opublikowane w: Proceedings of the AAAI Conference on Artificial Intelligence, 2025
Wydawca: AAAI
DOI: 10.48550/ARXIV.2412.15077

Multi-focal Conditioned Latent Diffusion for Person Image Synthesis

Autorzy: Jiaqi Liu; Jichao Zhang; Paolo Rota; Nicu Sebe
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Wydawca: IEEE
DOI: 10.1109/CVPR52734.2025.01493

Causal Graphical Models for Vision-Language Compositional Understanding

Autorzy: Parascandolo, Fiorenzo; Moratelli, Nicholas; Sangineto, Enver; Baraldi, Lorenzo; Cucchiara, Rita
Opublikowane w: ICLR, 2025
Wydawca: ICLR
DOI: 10.48550/ARXIV.2412.09353

Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization

Autorzy: Compagnoni, Alberto; Caffagni, Davide; Moratelli, Nicholas; Baraldi, Lorenzo; Cornia, Marcella; Cucchiara, Rita
Opublikowane w: British Machine Vision Conference (BMVC), 2025
Wydawca: BMVA
DOI: 10.5281/ZENODO.186953644

Federated Generalized Category Discovery

Autorzy: Pu, Nan; Li, Wenjing; Ji, Xingyuan; Qin, Yalan; Sebe, Nicu; Zhong, Zhun
Opublikowane w: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Wydawca: IEEE
DOI: 10.5281/ZENODO.12627450

Weighted Ensemble Models Are Strong Continual Learners

Autorzy: Imad Eddine Marouf, Subhankar Roy, Enzo Tartaglione, Stéphane Lathuilière
Opublikowane w: Lecture Notes in Computer Science, Computer Vision – ECCV 2024, 2024
Wydawca: Springer Nature Switzerland
DOI: 10.1007/978-3-031-73209-6_18

On the Minimax Regret for Online Learning with Feedback Graphs

Autorzy: Eldowa, Khaled; Esposito, Emmanuel; Cesari, Tommaso; Cesa-Bianchi, Nicolò
Opublikowane w: Neural Information Processing Systems (NeurIPS) 2023
Wydawca: NeurIPS
DOI: 10.5281/ZENODO.13880646

Agent-Designed Contracts: How to Sell Hidden Actions

Autorzy: Martino Bernasconi; Matteo Castiglioni; Andrea Celli
Opublikowane w: Proceedings of the 25th ACM Conference on Economics and Computation, 2024
Wydawca: ACM
DOI: 10.1145/3670865.3673640

Sparsity-agnostic linear bandits with adaptive adversaries.

Autorzy: Tianyuan, Jin; Jang, Kyoungseok; Cesa-Bianchi, Nicolò
Opublikowane w: Neural Information Processing Systems
Wydawca: NEURIPS
DOI: 10.48550/ARXIV.2406.01192

PSDNorm: Temporal Normalization for Deep Learning in Sleep Staging

Autorzy: Theo Gnassounou, Antoine Collas, Rémi Flamary, Alexandre Gramfort
Opublikowane w: International Conference on Learning Representations
Wydawca: Zenodo
DOI: 10.5281/ZENODO.19222799

Superpowering Open-Vocabulary Object Detectors for X-ray Vision

Autorzy: Pablo Garcia-Fernandez, Lorenzo Vaquero, Mingxuan Liu, Feng Xue, Daniel Cores, Nicu Sebe, Manuel Mucientes, Elisa Ricci
Opublikowane w: ICCV 2025, 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2503.17071

Feature-Based Online Bilateral Trade

Autorzy: Gaucher, Solenne; Bernasconi, Martino; Castiglioni, Matteo; Celli, Andrea; Perchet, Vianney
Opublikowane w: International Conference on Learning Representations (ICLR), 2024
Wydawca: ICLR
DOI: 10.48550/ARXIV.2405.18183

Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees

Autorzy: Bressan M.; Sozio M.
Opublikowane w: Proceedings of Machine Learning Research (PMLR), 2024, ISSN 2640-3498
Wydawca: PMLR
DOI: 10.48550/ARXIV.2302.03994

Any-Resolution AI-Generated Image Detection by Spectral Learning

Autorzy: Karageorgiou, Dimitrios; Papadopoulos, Symeon; Kompatsiaris, Ioannis (Yiannis); Gavves, Efstratios
Opublikowane w: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2411.19417

Time Can Invalidate Algorithmic Recourse

Autorzy: Giovanni De Toni; Stefano Teso; Bruno Lepri; Andrea Passerini
Opublikowane w: Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, 2025
Wydawca: ACM
DOI: 10.48550/ARXIV.2410.08007

LESS: Label-Efficient and Single-Stage Referring 3D Segmentation

Autorzy: Xuexun Liu; Xiaoxu Xu; Jinlong Li 0003; Qiudan Zhang; Xu Wang 0006; Nicu Sebe; Lin Ma 0002
Opublikowane w: Advances in Neural Information Processing Systems 37, 2024, ISSN 1049-5258
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2410.13294

Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery

Autorzy: Grzegorz Rypeść, Daniel Marczak, Sebastian Cygert, Tomasz Trzciński, Bartłomiej Twardowski
Opublikowane w: Lecture Notes in Computer Science, Computer Vision – ECCV 2024, 2024
Wydawca: Springer Nature Switzerland
DOI: 10.1007/978-3-031-73247-8_19

An Online Learning Theory of Brokerage

Autorzy: Bolić, Nataša; Cesari, Tommaso; Colomboni, Roberto
Opublikowane w: AAMAS, 2024
Wydawca: IFAAMAS
DOI: 10.48550/arXiv.2310.12107

Towards Optimal Trade-offs in Knowledge Distillation for CNNs and Vision Transformers at the Edge

Autorzy: John Violos, Symeon Papadopoulos, Ioannis Kompatsiaris
Opublikowane w: 32nd EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO)
Wydawca: IEEE Xplore
DOI: 10.5281/ZENODO.12510505

What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models

Autorzy: Lorenzo Baraldi, Davide Bucciarelli, Federico Betti, Marcella Cornia, Lorenzo Baraldi, Nicu Sebe, Rita Cucchiara
Opublikowane w: ICCV 2025, 2025
Wydawca: ICCV 2025 IEEE
DOI: 10.48550/ARXIV.2505.20405

Efficient Algorithms for Learning Monophonic Halfspaces in Graphs

Autorzy: Bressan, Marco; Esposito, Emmanuel; Thiessen, Maximilian
Opublikowane w: Proceedings of Machine Learning Research
Wydawca: PMLR
DOI: 10.48550/ARXIV.2405.00853

SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining

Autorzy: Yue Li, Qi Ma, Runyi Yang, Huapeng Li, Mengjiao Ma, Bin Ren, Nikola Popovic, Nicu Sebe, Ender Konukoglu, Theo Gevers, Luc Van Gool, Martin R. Oswald, Danda Pani Paudel
Opublikowane w: ICCV 2025, 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2503.18052

A Large-scale Dataset of Gaussian Splats and their Self-Supervised Pretraining

Autorzy: Qi Ma, Yue Li, Bin Ren, Nicu Sebe, Ender Konukoglu, Theo Gevers, Luc Van Gool, Danda Pani Paudel
Opublikowane w: International Conference on 3D Vision (3DV), 2025
Wydawca: IEEE
DOI: 10.1109/3DV66043.2025.00019

Masked Clustering Prediction for Unsupervised Point Cloud Pre-training

Autorzy: Masked Clustering Prediction for Unsupervised Point Cloud Pre-training Bin Ren, Xiaoshui Huang, Mengyuan Liu, Hong Liu, Fabio Poiesi, Nicu Sebe, Guofeng Mei
Opublikowane w: AAAI 2026, 2026
Wydawca: IEEE
DOI: 10.1609/AAAI.V40I11.37824

The software complexity of nations

Autorzy: Sándor Juhász, Johannes Wachs, Jermain Kaminski, César A. Hidalgo
Opublikowane w: Research Policy, 2026
Wydawca: Elsevier
DOI: 10.1016/J.RESPOL.2026.105422

When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses

Autorzy: Antoine Moulin, Emmanuel Esposito, Dirk van der Hoeven
Opublikowane w: NeurIPS, 2025
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2506.01722

Augmenting the availability of historical GDP per capita estimates through machine learning

Autorzy: Philipp Koch; Viktor Stojkoski; César A. Hidalgo
Opublikowane w: Proceedings of the National Academy of Sciences, 2024, ISSN 1091-6490
Wydawca: National Academy of Sciences
DOI: 10.48550/ARXIV.2505.09399

Novel Class Discovery for Ultra-Fine-Grained Visual Categorization

Autorzy: Liu, Yu; Cai, Yaqi; Jia, Qi; Qiu, Binglin; Wang, Weimin; Pu, Nan
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Wydawca: IEEE
DOI: 10.1109/CVPR52733.2024.01674

FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation

Autorzy: Dong Zhao; Jinlong Li; Shuang Wang; Mengyao Wu; Qi Zang; Nicu Sebe
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Wydawca: IEEE
DOI: 10.1109/CVPR52734.2025.01401

Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models

Autorzy: Poppi, Samuele; Poppi, Tobia; Cocchi, Federico; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
Opublikowane w: European Conference on Computer Vision
Wydawca: Springer
DOI: 10.5281/ZENODO.14015236

SMoSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks

Autorzy: Vincze, Mátyás; Ferrarotti, Laura; Custode, Leonardo Lucio; Lepri, Bruno; Iacca, Giovanni
Opublikowane w: Proceedings of the AAAI Conference on Artificial Intelligence, 2025, ISSN 2374-3468
Wydawca: AAAI Press
DOI: 10.48550/ARXIV.2412.13053

Robust Novelty Detection Through Style-Conscious Feature Ranking

Autorzy: Stefan Smeu, Elena Burceanu, Emanuela Haller, Andrei Liviu Nicolicioiu
Opublikowane w: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
Wydawca: IEEE
DOI: 10.1109/WACV61041.2025.00720

Hyperbolic Safety-Aware Vision-Language Models

Autorzy: Poppi, Tobia; Kasarla, Tejaswi; Mettes, Pascal; Baraldi, Lorenzo; Cucchiara, Rita
Opublikowane w: CVF/IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)
Wydawca: CVF/IEEE
DOI: 10.48550/ARXIV.2503.12127

Multi-Agent Contract Design beyond Binary Actions

Autorzy: Federico Cacciamani; Martino Bernasconi; Matteo Castiglioni; Nicola Gatti 0001
Opublikowane w: Proceedings of the 25th ACM Conference on Economics and Computation, 2024
Wydawca: ACM
DOI: 10.1145/3670865.3673633

Sparsity-Agnostic Linear Bandits with Adaptive Adversaries

Autorzy: Tianyuan Jin; Kyoungseok Jang; N. Cesa Bianchi
Opublikowane w: Advances in Neural Information Processing Systems 37, 2024, ISSN 1049-5258
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2406.01192

Wasserstein-Aligned Hyperbolic Multi-View Clustering

Autorzy: Rui Wang, Yuting Jiang, Xiaoqing Luo, Xiao-Jun Wu, Nicu Sebe, Ziheng Chen
Opublikowane w: AAAI 2026, 2026
Wydawca: IEEE
DOI: 10.1609/AAAI.V40I31.39851

Learning invariant representations of time-homogeneous stochastic dynamical systems

Autorzy: Kostic, Vladimir, R; Novelli, Pietro; Grazzi, Riccardo; Lounici, Karim; Pontil, Massimiliano
Opublikowane w: ICLR 2024, May 2024, Vienna (AUSTRIA), Austria, 2024
Wydawca: ICLR
DOI: 10.48550/arxiv.2307.09912

Sum-max submodular bandits

Autorzy: Pasteris, Stephen; Rumi, Alberto; Vitale, Fabio; Cesa-Bianchi, Nicolò
Opublikowane w: 27thInternational Conference on Artifi-cial Intelligence and Statistics (AISTATS) 2024, 2024
Wydawca: PMLR
DOI: 10.5281/zenodo.13881304

Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages

Autorzy: Farina, Matteo; Mancini, Massimiliano; Iacca, Giovanni; Ricci, Elisa
Opublikowane w: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2503.11609

Stochastic Shortest Path with Sparse Adversarial Costs

Autorzy: Emmeran Johnson, Alberto Rumi, Ciara Pike-Burke, Patrick Rebeschini
Opublikowane w: NeurIPS, 2025
Wydawca: NeurIPS

Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning

Autorzy: Rypeść, Grzegorz; Cygert, Sebastian; Trzcinski, Tomasz; Twardowski, Bartłomiej
Opublikowane w: Advances in Neural Information Processing Systems 37, 2024, ISSN 1049-5258
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2409.18265

A Theory of Interpretable Approximations

Autorzy: Bressan, Marco; Cesa-Bianchi, Nicolò; Esposito, Emmanuel; Mansour, Yishay; Moran, Shay; Thiessen, Maximilian
Opublikowane w: 37th Annual Conference on Learning Theory (COLT) 2024
Wydawca: PMLR
DOI: 10.48550/ARXIV.2406.10529

Towards a General Attention Framework on Gyrovector Spaces for Matrix Manifolds

Autorzy: Rui Wang, Chen Hu, Xiaoning Song, Xiao-Jun Wu, Nicu Sebe, Ziheng Chen
Opublikowane w: NeurIPS 2025, 2025
Wydawca: NeurIPS
DOI: 10.5281/ZENODO.19207209

MAVias: Mitigate any Visual Bias

Autorzy: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Opublikowane w: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2412.06632

Towards generalisable and calibrated audio deepfake detection with self-supervised representations

Autorzy: Octavian Pascu, Adriana Stan, Dan Oneata, Elisabeta Oneata, Horia Cucu
Opublikowane w: Interspeech 2024
Wydawca: ISCA
DOI: 10.5281/ZENODO.12526793

Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery

Autorzy: Zheng, H., Pu, N., Li, W., Sebe, N., & Zhong, Z.
Opublikowane w: Neural Information Processing Systems (NeurIPS)
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2410.19213

Robust covariance estimation with missing values and cell-wise contamination

Autorzy: Lounici, Karim; Pacreau, Gregoire
Opublikowane w: Neural Information Processing Systems (NeurIPS), 2023
Wydawca: NeurIPS
DOI: 10.48550/arxiv.2306.00752

OpenBias: Open-Set Bias Detection in Text-to-Image Generative Models

Autorzy: D'Incà, Moreno; Peruzzo, Elia; Mancini, Massimiliano; Xu, Dejia; Goe, Vidit; Xu, Xingqian; Wang, Zhangyang; Shi, Humphrey; Sebe, Nicu
Opublikowane w: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Wydawca: IEEE
DOI: 10.48550/ARXIV.2404.07990

Evaluating the Prompt Steerability of Large Language Models

Autorzy: Miehling, Erik; Desmond, Michael; Natesan Ramamurthy, Karthikeyan; Daly, Elizabeth; Dognin, Pierre; Rios, Jesus; Bouneffouf, Djallel; Liu, Miao
Opublikowane w: Pluralistic Alignment Workshop
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2411.12405

AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation

Autorzy: Sojka Damian, Twardowski Bartlomiej, Trzcinski Tomasz, Cygert Sebastian
Wydawca: BMVC

Federated Generalized Category Discovery

Autorzy: Pu, N.; Li, W.; Ji, X.; Qin, Y.; Sebe, N.; Zhong, Z.
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Wydawca: IEEE
DOI: 10.5281/ZENODO.11865219

No-Regret Learning in Bilateral Trade via Global Budget Balance

Autorzy: Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Federico Fusco
Opublikowane w: Proceedings of the 56th Annual ACM Symposium on Theory of Computing, 2024
Wydawca: ACM
DOI: 10.1145/3618260.3649653

Divide and not forget: Ensemble of selectively trained experts in Continual Learning

Autorzy: Rypeść, Grzegorz; Cygert, Sebastian; Khan, Valeriya; Trzciński, Tomasz; Zieliński, Bartosz; Twardowski, Bartłomiej
Opublikowane w: International Conference on Learning Representations, 2024
Wydawca: ICLR
DOI: 10.48550/arxiv.2401.10191

Structural Group Unfairness: Measurement and Mitigation by Means of the Effective Resistance

Autorzy: Adrian Arnaiz-Rodriguez, Georgina Curto, Nuria Oliver
Opublikowane w: Vol. 19 (2025): Proceedings of the Nineteenth International AAAI Conference on Web and Social Media, 2025
Wydawca: AAAI
DOI: 10.1609/ICWSM.V19I1.35805

Unlearning Vision Transformers without Retaining Data via Low-Rank Decompositions

Autorzy: Poppi, Samuele; Sarto, Sara; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
Opublikowane w: IEEE Intelligent Systems
Wydawca: IEEE
DOI: 10.5281/ZENODO.14031683

DeCLIP: Decoding CLIP Representations for Deepfake Localization

Autorzy: Stefan Smeu; Elisabeta Oneata; Dan Oneata
Opublikowane w: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
Wydawca: IEEE
DOI: 10.48550/ARXIV.2409.08849

Reducing inference energy consumption using dual complementary CNNs

Autorzy: Michail Kinnas, John Violos, Ioannis Kompatsiaris, Symeon Papadopoulos
Opublikowane w: Future Generation Computer Systems, Numer 165, 2024, ISSN 0167-739X
Wydawca: Elsevier BV
DOI: 10.1016/j.future.2024.107606

FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations

Autorzy: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numer 47, 2025, ISSN 0162-8828
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TPAMI.2024.3487254

T2TD: Text-3D Generation Model Based on Prior Knowledge Guidance

Autorzy: Weizhi Nie; Ruidong Chen; Weijie Wang; Bruno Lepri; Nicu Sebe
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, ISSN 1939-3539
Wydawca: IEEE
DOI: 10.48550/ARXIV.2305.15753

Cortico-Muscular Phase Connectivity During an Isometric Knee Extension Task in People With Early Parkinson’s Disease

Autorzy: Nina Omejc; Tomislav Stankovski; Manca Peskar; Miloš Kalc; Paolo Manganotti; Klaus Gramann; Sašo Džeroski; Uros Marusic
Opublikowane w: IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2025, ISSN 1558-0210
Wydawca: IEEE
DOI: 10.1109/TNSRE.2025.3527578

Spatial-Temporal Graph Mamba for Music-Guided Dance Video Synthesis

Autorzy: Hao Tang; Ling Shao; Zhenyu Zhang; Luc Van Gool; Nicu Sebe
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, ISSN 1939-3539
Wydawca: IEEE
DOI: 10.48550/ARXIV.2507.06689

Automatica

Autorzy: Caldarelli E.; Chatalic A.; Colome A.; Molinari C.; Ocampo-Martinez C.; Torras C.; Rosasco L.
Opublikowane w: Automatica, 2025, ISSN 0005-1098
Wydawca: Elsevier Ltd
DOI: 10.48550/ARXIV.2403.02811

IEEE Transactions on Pattern Analysis and Machine Intelligence

Autorzy: D'Incà, Moreno; Peruzzo, Elia; Mancini, Massimiliano; Xu, Xingqian; Shi, Humphrey; Sebe, Niculae
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, ISSN 0162-8828
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.48550/ARXIV.2408.16700

An Improved Uniform Convergence Bound with Fat-Shattering Dimension

Autorzy: Colomboni, Roberto; Esposito, Emmanuel; Paudice, Andrea
Opublikowane w: Information Processing Letters, 2025, ISSN 1872-6119
Wydawca: Elsevier
DOI: 10.1016/J.IPL.2024.106539

Cognition and context-aware decision-making systems for a sustainable planet: a survey on recent advancements, applications and open challenges

Autorzy: John Violos, Georgios Mamanis, Ioannis Kompatsiaris, Symeon Papadopoulos
Opublikowane w: SPRINGER NATURE Discover Sustainability, 2025, ISSN 2662-9984
Wydawca: SPRINGER NATURE
DOI: 10.1007/S43621-025-00954-Y

PLoS ONE

Autorzy: Victor Bros, Daniel Gatica-Perez
Opublikowane w: PLOS One, 2025, ISSN 1932-6203
Wydawca: Public Library of Science
DOI: 10.1371/JOURNAL.PONE.0328059

Pattern Recognition

Autorzy: Samuel Felipe dos Santos, Rodrigo Berriel, Thiago Oliveira-Santos, Nicu Sebe, Jurandy Almeida
Opublikowane w: Pattern Recognition, 2025, ISSN 0031-3203
Wydawca: Pergamon Press
DOI: 10.1016/J.PATCOG.2025.111714

Personalized algorithmic recourse with preference elicitation

Autorzy: G. De Toni, P. Viappiani, S. Teso, B. Lepri, and A. Passerini
Opublikowane w: Transactions on Machine Learning Research, ISSN 2835-8856
Wydawca: TMLR
DOI: 10.48550/ARXIV.2205.13743

Adaptive Log-Euclidean Metrics for SPD Matrix Learning

Autorzy: Ziheng Chen, Yue Song, Tianyang Xu, Zhiwu Huang, Xiao-Jun Wu, Nicu Sebe
Opublikowane w: IEEE Transactions on Image Processing, Numer 33, 2024, ISSN 1057-7149
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TIP.2024.3451930

Intercity connectivity and urban innovation

Autorzy: Xiaofan Liang, César A. Hidalgo, Pierre-Alexandre Balland, Siqi Zheng, Jianghao Wang
Opublikowane w: Computers, Environment and Urban Systems, Numer 109, 2024, ISSN 0198-9715
Wydawca: Elsevier BV
DOI: 10.1016/J.COMPENVURBSYS.2024.102092

IEEE Transactions on Pattern Analysis and Machine Intelligence

Autorzy: Tang, Hao; Shao, Ling; van Gool, Luc; Sebe, Nicu
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numer 46(6):4298-4313, 2024, ISSN 0162-8828
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.1109/TPAMI.2024.3355248

Regret Analysis of Bilateral Trade with a Smoothed Adversary

Autorzy: Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Federico Fusco, Stefano Leonardi
Opublikowane w: Journal of Machine Learning Research, ISSN 1533-7928
Wydawca: JMLR
DOI: 10.5281/ZENODO.13897756

What is beautiful is still good: the attractiveness halo effect in the era of beauty filters

Autorzy: Aditya Gulati; Marina Martinez-Garcia; Daniel Fernandez; Miguel Angel Lozano; Bruno Lepri; Nuria Oliver
Opublikowane w: Royal Society Open Science, 2024, ISSN 2054-5703
Wydawca: The Royal Society
DOI: 10.21203/RS.3.RS-4698268/V1

Physical partisan proximity outweighs online ties in predicting US voting outcomes

Autorzy: Tonin, Marco; Lepri, Bruno; Tizzoni, Michele
Opublikowane w: PNAS Nexus, 2025, ISSN 2752-6542
Wydawca: Oxford University
DOI: 10.48550/ARXIV.2407.12146

Anti-Forgetting Adaptation for Unsupervised Person Re-Identification

Autorzy: Hao Chen 0061; François Brémond; Nicu Sebe; Shiliang Zhang
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, ISSN 1939-3539
Wydawca: IEEE
DOI: 10.32388/O3VW3J

Deep Learning-Based Object Pose Estimation: A Comprehensive Survey

Autorzy: Jian Liu; Wei Sun; Hui Yang; Zhiwen Zeng; Chongpei Liu; Jin Zheng; Xingyu Liu; Hossein Rahmani; Nicu Sebe; Ajmal Mian
Opublikowane w: International Journal of Computer Vision, 2026, ISSN 1573-1405
Wydawca: Springer
DOI: 10.48550/ARXIV.2405.07801

Probabilistic grammars for modeling dynamical systems from coarse, noisy, and partial data

Autorzy: Nina Omejc; Boštjan Gec; Jure Brence; Ljupčo Todorovski; Sašo Džeroski
Opublikowane w: Machine Learning, Special Numer on Discovery Science 2024, 2024, ISSN 1573-0565
Wydawca: Springer
DOI: 10.21203/rs.3.rs-2678362/v1

Clarity in complexity: how aggregating explanations resolves the disagreement problem

Autorzy: Oana Mitruț; Gabriela Moise; Alin Moldoveanu; Florica Moldoveanu; Marius Leordeanu; Livia Petrescu
Opublikowane w: Artificial Intelligence Review, 2024, ISSN 1573-7462
Wydawca: Springer
DOI: 10.1007/s10462-024-10952-7

A New Formulation for Zeroth-Order Optimization of Adversarial EXEmples in Malware Detection

Autorzy: Marco Rando; Luca Demetrio; Lorenzo Rosasco; Fabio Roli
Opublikowane w: IEEE Transactions on Information Forensics and Security, 2025, ISSN 1556-6021
Wydawca: IEEE
DOI: 10.48550/ARXIV.2405.14519

Generative AI Literacy: Twelve Defining Competencies

Autorzy: Annapureddy, Ravinithesh; Fornaroli, Alessandro; Gatica-Perez, Daniel
Opublikowane w: ACM Digital Government: Research and Practice, 2024, ISSN 2639-0175
Wydawca: ACM
DOI: 10.1145/3685680

Learning Neural Free-Energy Functionals with Pair-Correlation Matching

Autorzy: Jacobus Dijkman, Marjolein Dijkstra, René van Roij, Max Welling, Jan-Willem van de Meent, Bernd Ensing
Opublikowane w: Physical Review Letters, Numer 134, 2025, ISSN 0031-9007
Wydawca: American Physical Society (APS)
DOI: 10.1103/PHYSREVLETT.134.056103

Cooperative Online Learning with Feedback Graphs

Autorzy: Cesa-Bianchi, Nicolò; Cesari, Tommaso; Della Vecchia, Riccardo
Opublikowane w: Transactions on Machine Learning Research, 2024, ISSN 2835-8856
Wydawca: TMLR
DOI: 10.48550/arXiv.2106.04982

Nature Communications

Autorzy: Camps Valls, Gustau; Fernández Torres, Miguel-Ángel; Cohrs, Kai-Hendrik; Prapas, Ioannis; Pérez Aracil, Jorge; Gonzalez Calabuig, Maria; Pellicer Valero, Oscar José; Kondylatos, Spyros; Salcedo Sanz, Sancho; Williams, Tristan
Opublikowane w: Nature Communications, 2025, ISSN 2041-1723
Wydawca: Nature Publishing Group
DOI: 10.1038/S41467-025-56573-8

H2OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers

Autorzy: Wenhao Li, Mengyuan Liu, Hong Liu, Pichao Wang, Shijian Lu, Nicu Sebe
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026, ISSN 1939-3539
Wydawca: IEEE
DOI: 10.1109/TPAMI.2025.3608284

Explainable Earth Surface Forecasting Under Extreme Events

Autorzy: Oscar J. Pellicer-Valero, Miguel-Ángel Fernández-Torres, Chaonan Ji, Miguel D. Mahecha, Gustau Camps-Valls
Opublikowane w: Earth's Future, 2025, ISSN 2328-4277
Wydawca: John Wiley & Sons, Ltd
DOI: 10.1029/2024EF005446

Computer Vision and Image Understanding

Autorzy: Liu, Yu; Li, Jianghao; Zhang, Yanyi; Jia, Qi; Wang, Weimin; Pu, Nan; Sebe, Nicu
Opublikowane w: Computer Vision and Image Understanding, 2024, ISSN 1077-3142
Wydawca: Academic Press
DOI: 10.1016/J.CVIU.2024.104197

MolMix: A Simple Yet Effective Baseline for Multimodal Molecular Representation Learning

Autorzy: Andrei Manolache; Dragos Tantaru; Mathias Niepert
Opublikowane w: CoRR, 2024, ISSN 2331-8422
Wydawca: arXiv
DOI: 10.48550/ARXIV.2410.07981

Unveiling Spectral Attention Redundancy With Explainable AI

Autorzy: Chen Ma, Oscar J. Pellicer-Valero, Kai-Hendrik Cohrs, Jiaqi Yao, Junjun Jiang, Huayi Li, Gustau Camps-Valls
Opublikowane w: IEEE Geoscience and Remote Sensing Letters, Numer 23, 2026, ISSN 1545-598X
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/LGRS.2026.3654396

Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback

Autorzy: Adam Dahlgren Lindström; Leila Methnani; Lea Krause; Petter Ericson; Íñigo Martinez de Rituerto de Troya; Dimitri Coelho Mollo; Roel Dobbe
Opublikowane w: Ethics and Information Technology, 2025, ISSN 1572-8439
Wydawca: Springer Nature
DOI: 10.1007/S10676-025-09837-2

Grounded Video Caption Generation

Autorzy: Evangelos Kazakos; Cordelia Schmid; Josef Sivic
Opublikowane w: CoRR, 2024, ISSN 2331-8422
Wydawca: arXiv
DOI: 10.48550/ARXIV.2411.07584

Selecting Images With Entropy for Frugal Knowledge Distillation

Autorzy: Michail Kinnas, John Violos, Nikolaos Ioannis Karapiperis, Ioannis Kompatsiaris
Opublikowane w: IEEE Access, Numer 13, 2025, ISSN 2169-3536
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/ACCESS.2025.3540384

Vision + X: A Survey on Multimodal Learning in the Light of Data

Autorzy: Ye Zhu, Yu Wu, Nicu Sebe, Yan Yan
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numer 46, 2024, ISSN 0162-8828
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TPAMI.2024.3420239

Understanding political divisiveness using online participation data from the 2022 French and Brazilian presidential elections

Autorzy: Carlos Navarrete, Mariana Macedo, Rachael Colley, Jingling Zhang, Nicole Ferrada, Maria Eduarda Mello, Rodrigo Lira, Carmelo Bastos-Filho, Umberto Grandi, Jérôme Lang, César A. Hidalgo
Opublikowane w: Nature Human Behaviour, Numer 8, 2024, ISSN 2397-3374
Wydawca: Springer Science and Business Media LLC
DOI: 10.1038/S41562-023-01755-X

Consistency-Aware Anchor Pyramid Network for Crowd Localization

Autorzy: Liu, X.; Li, G.; Qi, Y.; van den Hengel, A.; Sebe, N.; Yang, M-H.; Huang, Q.
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence., ISSN 1939-3539
Wydawca: IEEE
DOI: 10.1109/TPAMI.2024.3392013

IEEE Access

Autorzy: Németh, G. D. , Lozano, M. A. , Quadrianto, N. , Oliver, N.
Opublikowane w: IEEE Access, 2025, ISSN 2169-3536
Wydawca: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/ACCESS.2025.3546478

RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-Distribution Detection

Autorzy: Song, Yue; Wang, Wei; Sebe, Niculae
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, ISSN 1939-3539
Wydawca: IEEE
DOI: 10.48550/ARXIV.2311.13959

RESPRECT: Speeding-up Multi-Fingered Grasping With Residual Reinforcement Learning

Autorzy: Federico Ceola; Lorenzo Rosasco; Lorenzo Natale
Opublikowane w: IEEE Robotics and Automation Letters, 2024, ISSN 2377-3766
Wydawca: IEEE
DOI: 10.48550/arxiv.2401.14858

AI needs a new philosophy of science

Autorzy: Gustau Camps-Valls
Opublikowane w: The Innovation, 2026, ISSN 2666-6758
Wydawca: Elsevier
DOI: 10.1016/J.XINN.2026.101311

Nature Communications

Autorzy: Ma, Fengmei; Wang, Heming; Tzachor, Asaf; Hidalgo, César; Schandl, Heinz; Zhang, Yue; Zhang, Jingling; Chen, Wei-Qiang; Zhao, Yanzhi; Zhu, Yong-Guan; Fu, Bojie
Opublikowane w: Nature Communications, 2025, ISSN 2041-1723
Wydawca: Springer Nature
DOI: 10.1038/S41467-025-56076-6

Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations

Autorzy: Penzo, Nicolò; Sajedinia, Maryam; Lepri, Bruno; Tonelli, Sara; Guerini, Marco
Opublikowane w: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024, ISSN 1530-9312
Wydawca: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2409.18602

Pattern Recognition Letters

Autorzy: Andrei Radu; Yue Song; Ana Neacsu; Nicu Sebe
Opublikowane w: Pattern Recognition Letters, 2026, ISSN 0167-8655
Wydawca: Elsevier
DOI: 10.1016/J.PATREC.2026.02.009

IEEE Access

Autorzy: Ciro Beneduce; Bruno Lepri; Massimiliano Luca
Opublikowane w: IEEE Access, 2025, ISSN 2169-3536
Wydawca: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.48550/ARXIV.2405.20962

Margin-Based Active Learning of Classifiers

Autorzy: Bressan, Marco; Cesa-Bianchi, Nicolò; Lattanzi, Silvio; Paudice, Andrea
Opublikowane w: Journal of Machine Learning Research, ISSN 1533-7928
Wydawca: JLMR
DOI: 10.5281/ZENODO.13880741

A Comparative Analysis of Compression and Transfer Learning Techniques in DeepFake Detection Models

Autorzy: Andreas Karathanasis; John Violos; Ioannis Kompatsiaris
Opublikowane w: MDPI Mathematics, 2025, ISSN 2227-7390
Wydawca: MDPI
DOI: 10.3390/MATH13050887

Augmentation-aware self-supervised learning with conditioned projector

Autorzy: Przewięźlikowski, Marcin; Pyla, Mateusz; Zieliński, Bartosz; Twardowski, Bartłomiej; Tabor, Jacek; Śmieja, Marek
Opublikowane w: Knowledge-Based Systems, 2024, ISSN 1872-7409
Wydawca: ELSEVIER
DOI: 10.5281/zenodo.14410199

Improved Regret Bounds for Bandits with Expert Advice

Autorzy: N. Cesa Bianchi; Khaled Eldowa; Emmanuel Esposito; Julia Olkhovskaya
Opublikowane w: Journal of Artificial Intelligence Research, 2025, ISSN 1943-5037
Wydawca: AI Access Foundation
DOI: 10.48550/ARXIV.2406.16802

Layerfold: A Python Library to Reduce the Depth of Neural Networks

Autorzy: Pilo, Giommaria; Hezbri, Nour; Pereira E Ferreira, André; Quétu, Victor; Tartaglione, Enzo
Opublikowane w: SoftwareX, 2024, ISSN 2352-7110
Wydawca: Elsevier
DOI: 10.1016/J.SOFTX.2024.102030

Multi-Class Unlearning for Image Classification via Weight Filtering

Autorzy: Poppi, Samuele; Sarto, Sara; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
Opublikowane w: IEEE Intelligent Systems, ISSN 1941-1294
Wydawca: IEEE
DOI: 10.1109/MIS.2024.3412742

HYRE: Hybrid Regressor for 3D Human Pose and Shape Estimation

Autorzy: Wenhao Li, Mengyuan Liu, Hong Liu, Bin Ren, Xia Li, Yingxuan You, Nicu Sebe
Opublikowane w: IEEE Transactions on Image Processing, Numer 34, 2025, ISSN 1057-7149
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TIP.2024.3515872

The role of immigrants, emigrants and locals in the historical formation of European knowledge agglomerations

Autorzy: Philipp Koch, Viktor Stojkoski, César A. Hidalgo
Opublikowane w: Regional Studies, Numer 58, 2024, ISSN 0034-3404
Wydawca: Informa UK Limited
DOI: 10.1080/00343404.2023.2275571

Estimating digital product trade through corporate revenue data

Autorzy: Viktor Stojkoski, Philipp Koch, Eva Coll, César A. Hidalgo
Opublikowane w: Nature Communications, Numer 15, 2024, ISSN 2041-1723
Wydawca: Springer Science and Business Media LLC
DOI: 10.1038/S41467-024-49141-Z

Spatial entropy as an inductive bias for vision transformers

Autorzy: Elia Peruzzo; Enver Sangineto; Yahui Liu; Marco De Nadai; Wei Bi; Bruno Lepri; Nicu Sebe
Opublikowane w: Machine Learning, Numer 113(9): 6945–6975, 2024, ISSN 1573-0565
Wydawca: Springer
DOI: 10.48550/arxiv.2206.04636

Stochastic zeroth order descent with structured directions

Autorzy: Marco Rando; Cesare Molinari; Silvia Villa; Lorenzo Rosasco
Opublikowane w: Computational Optimization and Applications, 2024, ISSN 1573-2894
Wydawca: Springer
DOI: 10.48550/arxiv.2206.05124

IEEE Transactions on Pattern Analysis and Machine Intelligence

Autorzy: Hao Tang, Ling Shao, Nicu Sebe, Luc Van Gool
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, ISSN 0162-8828
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.1109/TPAMI.2025.3531220

Collaboration between artificial intelligence and Earth science communities for mutual benefit

Autorzy: Min Chen; Zhen Qian; Niklas Boers; Felix Creutzig; Gustau Camps-Valls; Klaus Hubacek; Christophe Claramunt; John P. Wilson; Stefano Nativi; Anthony J. Jakeman; R. Dietmar Müller; Michael Batty; Chenghu Zhou; Fahu Chen; Qiao Wang; Fan Zhang; C. Michael Barton; Josef Strobl; Michael Meadows; Carlo Ratti; Philipp Hess; Qingsong Xu; Zhixin Zhang; Qiushi Gu; A-Xing Zhu; Hui Lin; Linwang Yuan; Guonian Lü
Opublikowane w: Nature Geoscience, 2024, ISSN 1752-0908
Wydawca: Nat. Geosci.
DOI: 10.1038/S41561-024-01550-X

GraphMLP: A graph MLP-like architecture for 3D human pose estimation

Autorzy: Wenhao Li, Mengyuan Liu, Hong Liu, Tianyu Guo, Ti Wang, Hao Tang, Nicu Sebe
Opublikowane w: Pattern Recognition, Numer 158, 2024, ISSN 0031-3203
Wydawca: Elsevier BV
DOI: 10.1016/j.patcog.2024.110925

Automatic Classification and Visualization of Text Data on Rare Diseases

Autorzy: Luis Rei; Joao Pita Costa; Tanja Zdolšek Draksler
Opublikowane w: Journal of Personalized Medicine, 2024, ISSN 2075-4426
Wydawca: MDPI
DOI: 10.3390/JPM14050545

Multifidelity Gaussian Process Emulation for Atmospheric Radiative Transfer Models

Autorzy: J. Vicent Servera, L. Martino, J. Verrelst and G. Camps-Valls
Opublikowane w: Transactions on Geoscience and Remote Sensing, Numer 61, ISSN 1558-0644
Wydawca: IEEE
DOI: 10.1109/TGRS.2023.3300460

Counting Subgraphs in Somewhere Dense Graphs

Autorzy: Marco Bressan 0002; Leslie Ann Goldberg; Kitty Meeks; Marc Roth
Opublikowane w: SIAM Journal on Computing, 2024, ISSN 1095-7111
Wydawca: SIAM
DOI: 10.48550/ARXIV.2209.03402

Trading Volume Maximization with Online Learning

Autorzy: Tommaso Cesari, Roberto Colomboni
Wydawca: arXiv
DOI: 10.48550/ARXIV.2405.13102

Fair Online Bilateral Trade

Autorzy: François Bachoc, Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni
Wydawca: arXiv
DOI: 10.48550/ARXIV.2405.13919

ELIAS Pathways to Responsible and Sustainable AI – Strategic Research Agenda (SRA).

Autorzy: Sebe, Niculae; Dahlgren Lindström, Adam; Marchesi, Alberto; van Sluijs, Bob; Lepri, Bruno; Zanazzo, Cecilia; Garayeva, Aygun; Charlote, Delage; Peters, Nina; Gatica-Perez,, Daniel; Daly, Elizabeth; Sangineto, Enver; TARTAGLIONE, ENZO; Rodrigo, Esther; d'Alche, Florence; CLERICI, GIULIA; Camps Valls, Gustau; Siegrist, Isabelle; van de Meent, Jan-Willem; Pita Costa, Joao; Rosasco, Lorenzo; Baraldi, Lorenzo; Kamenska, Marcela; Leordeanu, Marius; CASTIGLIONI, MATTEO; Pfeiffer, Michael; Gatti, Nicola; Cesa-Bianchi, Nicolò Antonio; Oliver, Nuria; Kachaiev, Oleksii; Reddy Annapureddy, Ravinithesh; Džeroski, Sašo; Akis, Papadopoulos; Burceanu, Elena; Oneata, Elisabeta; Smeu,, Diana
Opublikowane w: 2025
Wydawca: ZENODO
DOI: 10.5281/ZENODO.17250219

Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels

Autorzy: Ahmad, Tamim El; Brogat-Motte, Luc; Laforgue, Pierre; d'Alché-Buc, Florence
Opublikowane w: 27th International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
Wydawca: PMLR
DOI: 10.48550/arxiv.2302.10128

Information Capacity Regret Bounds for Bandits with Mediator Feedback

Autorzy: Eldowa, Khaled; Cesa-Bianchi, Nicolò; Metelli, Alberto Maria; Restelli, Marcello
Opublikowane w: 2024
Wydawca: arXiv
DOI: 10.48550/arxiv.2402.10282

A Contextual Online Learning Theory of Brokerage

Autorzy: François Bachoc, Tommaso Cesari, Roberto Colomboni
Wydawca: arXiv
DOI: 10.48550/ARXIV.2407.01566

A Characterization Theorem for Equivariant Networks with Point-wise Activations

Autorzy: Marco Pacini; Xiaowen Dong; Bruno Lepri; Gabriele Santin
Opublikowane w: CoRR, 2024

Is Mamba Capable of In-Context Learning?

Autorzy: Grazzi, Riccardo; Siems, Julien; Schrodi, Simon; Brox, Thomas; Hutter, Frank
Opublikowane w: 2024
Wydawca: arXiv
DOI: 10.48550/arxiv.2402.03170

Judging Books by Their Cover: The Impact of Facial Attractiveness on Humans and AI

Autorzy: Aditya Gulati
Opublikowane w: 2025
Wydawca: University of Alicante

Deep Sketched Output Kernel Regression for Structured Prediction

Autorzy: Tamim El Ahmad; Junjie Yang; Pierre Laforgue; Florence d'Alché-Buc
Opublikowane w: Lecture Notes in Computer Science ISBN: 9783031703515, 2024
Wydawca: Springer
DOI: 10.48550/ARXIV.2406.09253

Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models

Autorzy: Poppi, Samuele; Poppi, Tobia; Cocchi, Federico; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
Opublikowane w: Lecture Notes in Computer Science ISBN: 9783031736674, 2024
Wydawca: Springer
DOI: 10.5281/ZENODO.14015236

Zero-Waste Machine Learning

Autorzy: Tomasz Trzcinski; Bartlomiej Twardowski; Bartosz Zielinski 0001; Kamil Adamczewski; Bartosz Wójcik
Opublikowane w: Frontiers in Artificial Intelligence and Applications ISBN: 9781643685489, 2024
Wydawca: IOS Press
DOI: 10.3233/FAIA240466

A Deep Cut Into Split Federated Self-Supervised Learning

Autorzy: Marcin Przewiezlikowski; Marcin Osial; Bartosz Zielinski 0001; Marek Smieja
Opublikowane w: Lecture Notes in Computer Science ISBN: 9783031703430, 2024
Wydawca: Springer
DOI: 10.48550/ARXIV.2406.08267

Unlearning Vision Transformers Without Retaining Data via Low-Rank Decompositions

Autorzy: Poppi, Samuele; Sarto, Sara; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
Opublikowane w: Lecture Notes in Computer Science ISBN: 9783031781216, 2024
Wydawca: Springer
DOI: 10.5281/ZENODO.14031683

Optimizing Resource Consumption in Diffusion Models Through Hallucination Early Detection

Autorzy: Betti, Federico; Baraldi, Lorenzo; Baraldi, Lorenzo; Cucchiara, Rita; Sebe, Nicu
Opublikowane w: Lecture Notes in Computer Science ISBN: 9783031919787, 2025, ISSN 1611-3349
Wydawca: Springer Cham
DOI: 10.48550/ARXIV.2409.10597

Wyszukiwanie danych OpenAIRE...

Wyniki projektu

Rezultaty

Publikacje

Pobierz Pobierz zawartość strony