Research

The Machine Learning group develops the next generation of artificial agents — individually intelligent, collectively aware, and socially capable. Our research spans reinforcement learning, foundation models, natural language processing, pattern recognition, and agentic intelligence.

2026

Conference

  • Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions
    Bar-Shalom, Guy and Frasca, Fabrizio and Lim, Derek and Gelberg, Yoav and Ziser, Yftah and El-Yaniv, Ran and Chechik, Gal and Maron, Haggai
    Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)
    Natural Language ProcessingTrustworthy AIGenerative AI
  • CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval
    Jiahui Geng and Qing Li and Fengyu Cai and Fakhri Karray
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    Natural Language Processing
  • From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL
    Admoni, Sahar and Hallak, Assaf and Ziser, Yftah and Ben-Porat, Omer and Amir, Ofra
    Proceedings of the International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)
    Reinforcement LearningNatural Language ProcessingGenerative AI
  • Neural Message-Passing on Attention Graphs for Hallucination Detection
    Frasca, Fabrizio and Bar-Shalom, Guy and Ziser, Yftah and Maron, Haggai
    Proceedings of the International Conference on Learning Representations (ICLR)
    Deep LearningTrustworthy AI
  • Revisiting Weight Regularization for Low-Rank Continual Learning
    Yaoyue Zheng and Yin Zhang and Joost van de Weijer and Gido M van de Ven and Shaoyi Du and Xuetao Zhang and Zhiqiang Tian
    The Fourteenth International Conference on Learning Representations
    Continual Learning

Preprint

  • An ε-Optimal Sequential Approach for Solving zs-POSGs
    Erwan Escudie and Matthia Sabatelli and Jilles Dibangoye
    Arkiv
    Agentic Intelligence
  • Credible Sets: Generative Dynamic Programming for Leader-Follower General-Sum Stochastic Games
    Jilles S. Dibangoye and Thibaut Le Marre and Ocan Sankur and François Schwarzentruber
    Arkiv
    Agentic Intelligence
  • Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability
    Sergi Masip and Gido M van de Ven and Javier Ferrando and Tinne Tuytelaars
    CoRR, vol. abs/2601.22012
    Continual Learning

2025

Journal

  • Ahmed Abdelrahman and Matias Valdenegro-Toro and Maren Bennewitz and Paul G Plöger
    Int. J. Robotics Res., vol. 44(5), pp. 768–804
    AbsHTMLPattern Recognition
  • Hamed Hemati and Lorenzo Pellegrini and Xiaotian Duan and Zixuan Zhao and Fangfang Xia and Marc Masana and Benedikt Tscheschner and Eduardo E. Veas and Yuxiang Zheng and Shiji Zhao and Shao-Yuan Li and Sheng-Jun Huang and Vincenzo Lomonaco and Gido M. van de Ven
    Neural Networks, vol. 183, pp. 106920
    AbsHTMLContinual Learning
  • Dating ancient manuscripts using radiocarbon and AI-based writing style analysis
    Mladen Popovic and Maruf A. Dhali and Lambert Schomaker and Johannes van der Plicht and Kaare Lund Rasmussen and Jacopo La Nasa and Ilaria Degano and Maria Perla Colombini and Eibert Tigchelaar
    PloS one, vol. 20(6), pp. e0323185
    Pattern Recognition
  • Davide Cipollini and Hugh Greatorex and Michele Mastella and Elisabetta Chicca and Lambert Schomaker
    Neuromorph. Comput. Eng., vol. 5(2), pp. 24002
    AbsHTMLPattern Recognition
  • Out of sight, but not out of mind: Key issues regarding seafloor macrolitter monitoring
    Georg Hanke and Miquel Canals and Ryota Nakajima and Melanie Bergmann and Francois Galgani and Daoji Li and George Papatheodorou and Christopher Kim Pham and Diva J Amon and Michela Angiolillo and Matias Valdenegro-Toro
    Marine Pollution Bulletin, vol. 221, pp. 118500
    Deep Learning
  • Joshua T. Vogelstein and Jayanta Dey and Hayden S. Helm and Will LeVine and Ronak D. Mehta and Tyler M. Tomita and Haoyin Xu and Ali Geisa and Qingyang Wang and Gido M. van de Ven and Chenyu Gao and Weiwei Yang and Bryan Tower and Jonathan Larson and Christopher M. White and Carey E. Priebe
    IEEE Trans. Pattern Anal. Mach. Intell., vol. 47(11), pp. 10033–10046
    AbsHTMLContinual Learning
  • Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning
    Aleksandar Todorov and Juan Cardenas-Cartagena and Rafael Fernandes Cunha and Marco Zullich and Matthia Sabatelli
    Trans. Mach. Learn. Res., vol. 2025
    Reinforcement LearningContinual Learning

Conference

  • Ghosh, Shaona and Bhattacharjee, Amrita and Ziser, Yftah and Parisien, Christopher
    Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 35128–35148
    AbsHTMLNatural Language ProcessingTrustworthy AIGenerative AI
  • A Study on the Faithfulness of Feature Attribution Explanations in Pruned Vision-Based Multi-Task Learning
    Xenia Demetriou and Sophie Sananikone and Vojislav Tobias Westmoreland and Matthia Sabatelli and Marco Zullich
    Joint Proceedings of the xAI 2025 Late-breaking Work, Demos and Doctoral Consortium co-located with the 3rd World Conference on eXplainable Artificial Intelligence (xAI 2025), Istanbul, Turkey, July 9-11, 2025, pp. 121–128
    Trustworthy AIDeep Learning
  • Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
    Alessandro Pierro and Steven Abreu and Jonathan Timcheck and Philipp Stratmann and Andreas Wild and Sumit Bam Shrestha
    Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025
    Deep Learning
  • Eric Brouwer and Jan Erik van Woerden and Gertjan J. Burghouts and Matias Valdenegro-Toro and Marco Zullich
    Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2025 - Volume 2: VISAPP, Porto, Portugal, February 26-28, 2025, pp. 114–125
    AbsHTMLPattern Recognition
  • Steven Abreu and Jason Eshraghian
    IEEE International Symposium on Circuits and Systems, ISCAS 2025, London, United Kingdom, May 25-28, 2025, pp. 1–6
    AbsHTMLNatural Language ProcessingGenerative AI
  • Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
    Bar-Shalom, Guy and Frasca, Fabrizio and Galron, Yaniv and Ziser, Yftah and Maron, Haggai
    Advances in Neural Information Processing Systems
    Deep LearningTrustworthy AI
  • Leendert Johannes Tanis and Rafael Fernandes Cunha and Marco Zullich
    Proceedings of the 20th International Conference on the Foundations of Digital Games, pp. 1–7
    AbsHTMLReinforcement LearningTrustworthy AI
  • Matias Valdenegro-Toro and Marco Zullich
    Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2025 - Volume 3: VISAPP, Porto, Portugal, February 26-28, 2025, pp. 188–199
    AbsHTMLDeep LearningTrustworthy AI
  • Classification and Prediction of Wafer Yield Using Gradient Boosting Algorithms: A Focus on Lithography Inline Parameters
    Mohammed Nizamul Islam and Md Tarekul Islam and Maruf A. Dhali
    2025 IEEE 4th International Conference on Computing and Machine Intelligence (ICMI), pp. 1–6
    Pattern Recognition
  • Valentin-Adrian Serbanescu and Maruf A. Dhali
    Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2025, Porto, Portugal, February 23-25, 2025, pp. 749–756
    AbsHTMLPattern Recognition
  • Riccardo Bovo and Steven Abreu and Karan Ahuja and Eric J Gonzalez and Li-Te Cheng and Mar Gonzalez-Franco
    IEEE Conference Virtual Reality and 3D User Interfaces, VR 2025, Saint Malo, France, March 8-12, 2025, pp. 708–717
    AbsHTMLAgentic IntelligenceGenerative AI
  • Wenci Xin and Mingrui Nie and Zhexin Xie and Cecilia Laschi
    8th IEEE International Conference on Soft Robotics, RoboSoft 2025, Lausanne, Switzerland, April 22-26, 2025, pp. 1–6
    AbsHTMLReinforcement Learning
  • Interpretable Function Approximation with Gaussian Processes in Value-Based Model-Free Reinforcement Learning
    Matthijs van der Lende and Matthia Sabatelli and Juan Cardenas-Cartagena
    Northern Lights Deep Learning Conference, The Arctic University, Troms\o, Norway, 7-9 January 2025, pp. 141–154
    Reinforcement LearningTrustworthy AI
  • Shao, Shun and Ziser, Yftah and Zhao, Zheng and Qiu, Yifu and Cohen, Shay B and Korhonen, Anna
    Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 29230–29255
    AbsHTMLNatural Language ProcessingTrustworthy AI
  • Josh Bruegger and Diana Ioana Catana and Vanja Macovaz and Matias Valdenegro-Toro and Matthia Sabatelli and Marco Zullich
    Artificial Intelligence in Music, Sound, Art and Design - 14th International Conference, EvoMUSART 2025, Held as Part of EvoStar 2025, Trieste, Italy, April 23-25, 2025, Proceedings, pp. 34–50
    AbsHTMLPattern Recognition
  • Andrei Voinea and Robin Kock and Maruf A. Dhali
    Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2025, Porto, Portugal, February 23-25, 2025, pp. 757–763
    AbsHTMLPattern Recognition
  • Keyi Li and Chengxi Bai and Jie Wang and Muralidharan Mohanakrishnan and Zhexin Xie and Cecilia Laschi
    8th IEEE International Conference on Soft Robotics, RoboSoft 2025, Lausanne, Switzerland, April 22-26, 2025, pp. 1–6
    AbsHTMLReinforcement Learning
  • Abhishek Ramanathapura Satyanarayana and Maruf A. Dhali
    Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2025, Porto, Portugal, February 23-25, 2025, pp. 741–748
    AbsHTMLPattern Recognition
  • Optimally Solving Simultaneous-Move Dec-POMDPs: The Sequential Central Planning Approach
    Johan Peralez and Aurelien Delage and Jacopo Castellini and Rafael F. Cunha and Jilles S. Dibangoye
    The 39th Annual AAAI Conference on Artificial Intelligence
    Agentic Intelligence
  • Rares Adrian Oancea and Stan van der Linde and Willem de Kok and Matthia Sabatelli and Sebastian Feld
    Innovations for Community Services - 25th International Conference, I4CS 2025, Munich, Germany, June 11-13, 2025, Proceedings, pp. 189–208
    AbsHTMLReinforcement Learning
  • Ömer Tarik Özyilmaz and Matt Coler and Matias Valdenegro-Toro
    26th Annual Conference of the International Speech Communication Association, Interspeech 2025, Rotterdam, The Netherlands, 17-21 August 2025
    AbsHTMLPattern Recognition
  • Policy Optimized Text-to-Image Pipeline Design
    Gadot, Uri and Gal, Rinon and Ziser, Yftah and Chechik, Gal and Mannor, Shie
    Advances in Neural Information Processing Systems
    Deep LearningGenerative AI
  • Lisa Koopmans and Maruf A. Dhali and Lambert Schomaker
    Document Analysis and Recognition - ICDAR 2025 - 19th International Conference, Wuhan, China, September 16-21, 2025, Proceedings, Part III, pp. 391–407
    AbsHTMLPattern RecognitionGenerative AI
  • Maniraj Sai Adapa and Marco Zullich and Matias Valdenegro-Toro
    Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2025 - Volume 2: VISAPP, Porto, Portugal, February 26-28, 2025, pp. 367–374
    AbsHTMLDeep LearningTrustworthy AI
  • Juan Cardenas-Cartagena and Massimiliano Falzari and Marco Zullich and Matthia Sabatelli
    Proceedings of the 17th International Conference on Agents and Artificial Intelligence, ICAART 2025 - Volume 1, Porto, Portugal, February 23-25, 2025, pp. 859–869
    AbsHTMLReinforcement LearningTrustworthy AI
  • World model agents with change-based intrinsic motivation
    Jeremias Ferrao and Rafael Cunha
    2025 Northern Lights Deep Learning Conference (NLDL)
    Reinforcement Learning
  • ε-Optimally Solving Simultaneous-Move Zero-Sum POSGs
    Erwan Escudie and Matthia Sabatelli and Jilles Dibangoye
    Neural Information Processing Systems, NeurIPS
    Agentic Intelligence

Workshop

  • Maruf A. Dhali and Jan Willem de Wit and Lambert Schomaker
    Document Analysis and Recognition - ICDAR 2025 Workshops - Wuhan, China, September 20-21, 2025, Proceedings, Part II, pp. 166–193
    AbsHTMLPattern Recognition
  • Boosting Accuracy and Efficiency of Budget Forcing in LLMs via Reinforcement Learning for Mathematical Reasoning
    Ravindra Aribowo Tarunokusumo and Rafael Fernandes Cunha
    SLLM – Buck The Trend: Make LLMs Specific and Reduce the cost of Intelligence at ECAI
    Reinforcement LearningGenerative AI
  • Collaborative Reinforcement Learning for Cyber Defense: Analysis of Strategies, and Policies
    Davide Rigoni and Rafael F. Cunha and Frank Fransen and Puck de Haan and Amir Javadpour and Fatih Turkmen
    1st International Workshop on Security and Privacy-Preserving AI/ML (SPAIML) at ECAI
    Reinforcement LearningAgentic Intelligence
  • Cross-Lingual Document Recommendations with Transformer-Based Representations: Evaluating Multilingual Models and Mapping Techniques
    Tsegaye Misikir Tashu and Eduard-Raul Kontos and Matthia Sabatelli and Matias Valdenegro-Toro
    Proceedings of the 31st International Conference on Computational Linguistics, COLING 2025 - Workshops, Abu Dhabi, UAE, January 19-24, 2025, pp. 39–47
    Natural Language Processing
  • Difficulty Estimation in Natural Language Tasks with Action Scores
    Aleksandar Angelov and Tsegaye Misikir Tashu and Matias Valdenegro-Toro
    Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025)
    Natural Language Processing
  • Mapping Cross-Lingual Sentence Representations for Low-Resource Language Pairs Using Pre-trained Language Models
    Andreea Ioana Tudor and Tsegaye Misikir Tashu
    Proceedings of the 31st International Conference on Computational Linguistics, COLING 2025 - Workshops, Abu Dhabi, UAE, January 19-24, 2025, pp. 249–257
    Natural Language Processing
  • No Supervision, No Problem: Pure Reinforcement Learning Improves Mathematical Reasoning in Small Language Models
    Quinten Steringa and Matthia Sabatelli and Rafael Fernandes Cunha
    SLLM – Buck The Trend: Make LLMs Specific and Reduce the cost of Intelligence at ECAI
    Reinforcement LearningGenerative AI
  • Physics-Informed Graph Neural Networks for Air Pollution Forecasting in the Netherlands
    Nikolas Assiotis and Rachel Hau and Valentijn Oldenburg and Rik Verbiest and Julian Koellermeier and Matthia Sabatelli and Juan Cardenas-Cartagena
    ECAI Workshop on Machine Learning Meets Differential Equations: From Theory to Applications, pp. 47–70
    Deep Learning
  • Seed Scheduling in Fuzz Testing as a Markov Decision Process
    Rafael F. Cunha and Luca Muller and Thomas Rooijakkers and Puck de Haan and Fatih Turkmen
    1st International Workshop on Security and Privacy-Preserving AI/ML (SPAIML) at ECAI
    Reinforcement Learning
  • Uncertainty Quantification for Gradient-based Explanations in Neural Networks
    Mihir Mulye and Matias Valdenegro-Toro
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2025, Nashville, TN, USA, June 11-15, 2025, pp. 1752–1760
    Pattern RecognitionTrustworthy AI
  • Joris Suurmeijer and Ivo Pascal de Jong and Matias Valdenegro-Toro and Andreea Ioana Sburlea
    35th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2025, Istanbul, Turkey, August 31 - Sept. 3, 2025, pp. 1–6
    AbsHTMLDeep LearningTrustworthy AIAI for Healthcare

Preprint

2024

Journal

Conference

Workshop

Preprint

Tech Report

2023

Journal

Conference

  • Arthur Müller and Matthia Sabatelli
    26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023, Bilbao, Spain, September 24-28, 2023, pp. 5271–5278
    AbsHTMLReinforcement Learning
  • Bridging the reality gap of reinforcement learning based traffic signal control using domain randomization and meta learning
    Arthur Muller and Matthia Sabatelli
    2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), pp. 5271–5278
    Reinforcement Learning
  • Continual evaluation for lifelong learning: Identifying the stability gap
    Matthias De Lange and Gido M. van de Ven and Tinne Tuytelaars
    The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023
    Continual Learning
  • Ekin Fergan and Tsegaye Misikir Tashu
    10th International Conference on Behavioural and Social Computing, BESC 2023, Larnaca, Cyprus, October 30 - Nov. 1, 2023, pp. 1–7
    AbsHTMLNatural Language Processing
  • DExT: Detector Explanation Toolkit
    Deepan Chakravarthi Padmanabhan and Paul Plöger and Octavio Arriaga and Matias Valdenegro-Toro
    World Conference on Explainable Artificial Intelligence
    Deep LearningTrustworthy AI
  • Global min-max Computation for Alpha-Holder Games
    Aurélien Delage and Olivier Buffet and Jilles Steeve Dibangoye
    35th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2023, Atlanta, GA, USA, November 6-8, 2023, pp. 518–525
    Agentic Intelligence
  • Thomas Reynolds and Maruf A. Dhali and Lambert Schomaker
    Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2023, Lisbon, Portugal, February 22-24, 2023, pp. 697–706
    AbsHTMLPattern Recognition
  • LAPTNet-FPN: Multi-Scale LiDAR-Aided Projective Transform Network for Real Time Semantic Grid Prediction
    Manuel Diaz-Zapata and David Sierra González and Özgür Erkent and Christian Laugier and Jilles Dibangoye
    IEEE International Conference on Robotics and Automation, ICRA 2023, London, UK, May 29 - June 2, 2023, pp. 712–718
    Deep Learning
  • Zhiqiang Tang and Peiyi Wang and Wenci Xin and Zhexin Xie and Longxin Kan and Muralidharan Mohanakrishnan and Cecilia Laschi
    IEEE International Conference on Robotics and Automation, ICRA 2023, London, UK, May 29 - June 2, 2023, pp. 982–988
    AbsHTMLReinforcement Learning
  • Optimization of Sensor Configurations for Fault Identification in Smart Buildings
    Naveed Ahmad and Malcolm Egan and Jean-Marie Gorce and Jilles Steeve Dibangoye and Frédéric Le Mouel
    IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023, pp. 1–5
    Agentic Intelligence
  • Asmaa Haja and Bart Van Der Woude and Lambert Schomaker
    Proceedings of the 10th International Conference on Biomedical and Bioinformatics Engineering, ICBBE 2023, Kyoto, Japan, November 9-12, 2023, pp. 17–27
    AbsHTMLDeep LearningAI for Healthcare
  • Pattern Recognition and Context Prediction of COVID-19 cases in European Countries
    Arzu Tosayeva and Ermiyas Birihanu and Tsegaye Misikir Tashu
    Proceedings of the Conference Information Technologies - Applications and Theory (ITAT 2023), pp. 50–57
    Pattern RecognitionAI for Healthcare
  • Maruf A. Dhali and Thomas Reynolds and Aylar Ziad Alizadeh and Stephan H. Nijdam and Lambert Schomaker
    Pattern Recognition Applications and Methods - 12th International Conference, ICPRAM 2023, Lisbon, Portugal, February 22-24, 2023, Revised Selected Papers, pp. 124–150
    AbsHTMLPattern Recognition
  • Asmaa Haja and Ivaylo Zhelev and Lambert Schomaker
    Proceedings of the 10th International Conference on Biomedical and Bioinformatics Engineering, ICBBE 2023, Kyoto, Japan, November 9-12, 2023, pp. 1–10
    AbsHTMLDeep LearningAI for Healthcare
  • Lisa Koopmans and Maruf A. Dhali and Lambert Schomaker
    Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2023, Lisbon, Portugal, February 22-24, 2023, pp. 124–135
    AbsHTMLPattern Recognition
  • Adrian Lubitz and Matias Valdenegro-Toro and Frank Kirchner
    Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2023, Volume 2: HUCAPP, Lisbon, Portugal, February 19-21, 2023, pp. 39–46
    AbsHTMLPattern Recognition

Workshop

Preprint

Tech Report

2022

Conference

  • A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement
    Matias Valdenegro-Toro and Daniel Saromo
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
    Deep LearningTrustworthy AI
  • Self-supervised Learning for Sonar Image Classification
    Alan Preciado-Grijalva and Bilal Wehbe and Miguel Bande Firvida and Matias Valdenegro-Toro
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1499–1508
    Deep Learning

Workshop

  • A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation
    Lokesh Veeramacheneni and Matias Valdenegro-Toro
    NeurIPS 2022 Workshop on Robot Learning: Trustworthy Robotics
    Deep LearningTrustworthy AI
  • Comparison of Uncertainty Quantification with Deep Learning in Time Series Regression
    Levente Foldesi and Matias Valdenegro-Toro
    Workshop on Robustness in Sequence Modeling at NeurIPS 2022
    Deep LearningTrustworthy AI
  • Disentangled Uncertainty and Out of Distribution Detection in Medical Generative Models
    Kumud Lakara and Matias Valdenegro-Toro
    Medical Imaging Meets NeurIPS Workshop 2022
    Deep LearningTrustworthy AIAI for Healthcare
🔔

Latest Highlights

1 / 3