Publications

Core Tokensets for Data-efficient Sequential Training of Transformers

Authors: Subarnaduti Paul, Manuel Brack, Patrick Schramowski, Kristian Kersting, Martin Mundt

Preprint: arXiv:2410.05800, October 2024

Distribution-Aware Replay for Continual MRI Segmentation

Authors: Nick Lemke, Camila González, Anirban Mukhopadhyay, Martin Mundt

To be published in: MICCAI Workshop on Personalized Incremental Learning in Medicine, Lecture Notes in Computer Science (LNCS), Springer, 2024

Masked Autoencoders are Efficient Continual Federated Learners

Authors: Subarnaduti Paul, Lars-Joel Frey, Roshni Kamath, Kristian Kersting, Martin Mundt

Accepted at: Conference on Lifelong Learning Agents (CoLLAs), 2024

Continual Learning: Applications and the Road Forward

Authors: Eli Verwimp, Shai Ben-David, Matthias Bethge, Andrea Cossu, Alexander Gepperth, Tyler L. Hayes, Eyke Hüllermeier, Christopher Kanan, Dhireesha Kudithipudi, Christoph H. Lampert, Martin Mundt, Razvan Pascanu, Adrian Popescu, Andreas S. Tolias, Joost van de Weijer, Bing Liu, Vincenzo Lomonaco, Tinne Tuytelaars, Gido M. van de Ven

Published in: Transactions on Machine Learning Research (TMLR), April 2024

Where is the Truth? The Risk of Getting Confounded in a Continual World

Authors: Florian Peter Busch, Roshni Kamath, Rupert Mitchell, Wolfgang Stammer, Kristian Kersting, Martin Mundt

Preprint: arXiv:2402.06434, February 2024

Self-Expanding Neural Networks

Authors: Rupert Mitchell, Robin Menzenbach, Kristian Kersting, Martin Mundt

Preprint: arXiv:2307.04526, February 2024

BOWLL: A Deceptively Simple Open World Lifelong Learner

Authors: Roshni Kamath, Rupert Mitchell, Subarnaduti Paul, Kristian Kersting, Martin Mundt

Preprint: arXiv:2402.04814, February 2024

Deep Classifier Mimicry without Data Access

Authors: Steven Braun, Martin Mundt, Kristian Kersting

Published in: International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. Awarded student paper highlight!

Adaptive Rational Activations to Boost Deep Reinforcement Learning

Authors: Quentin Delfosse, Patrick Schramowski, Martin Mundt, Alejandro Molina, Kristian Kersting

Accepted at: International Conference on Learning Representations (ICLR), 2024. Selected as spotlight presentation!

Designing a Hybrid Neural System to Learn Real-world Crack Segmentation from Fractal-based Simulation

Authors: Achref Jaziri, Martin Mundt, Andres Fernandez Rodriguez, Visvanathan Ramesh

Published in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 8636-8646, 2024

Continual Causality: A Retrospective of the Inaugural AAAI-23 Bridge Program

Authors: Martin Mundt, Keiland W. Cooper, Devendra Singh Dhami, Adèle Ribeiro, James Seale Smith, Alexis Bellot, Tyler L. Hayes

Published in: Proceedings of Machine Learning Research (PMLR), Volume 208, Pages 1-10, 2023

Probabilistic Circuits That Know What They Don’t Know

Authors: Fabrizio Ventola*, Steven Braun*, Zhongjie Yu, Martin Mundt, Kristian Kersting (* equal contribution)

Published in: 39th Conference on Uncertainty in Artificial Intelligence (UAI), 2023. Selected for oral presentation!

Queer In AI: A Case Study in Community-Led Participatory AI

Authors: Organizers of Queer in AI, Anaelia Ovalle, Arjun Subramonian, Ashwin Singh, Claas Voelcker, Danica J. Sutherland, Davide Locatelli, Eva Breznik, Filip Klubička, Hang Yuan, Hetvi J, Huan Zhang, Jaidev Shriram, Kruno Lehman, Luca Soldaini, Maarten Sap, Marc Peter Deisenroth, Maria Leonor Pacheco, Maria Ryskina, Martin Mundt, Milind Agarwal, Nyx McLean, Pan Xu, A Pranav, Raj Korpan, Ruchira Ray, Sarah Mathew, Sarthak Arora, St John, Tanvi Anand, Vishakha Agrawal, William Agnew, Yanan Long, Zijie J. Wang, Zeerak Talat, Avijit Ghosh, Nathaniel Dennler, Michael Noseworthy, Sharvani Jha, Emi Baylor, Aditya Joshi, Natalia Y. Bilenko, Andrew McNamara, Raphael Gontijo-Lopes, Alex Markham, Evyn Dǒng, Jackie Kay, Manu Saraswat, Nikhil Vytla, Luke Stark

Published in: ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT) 2023. FAccT 2023 Best Paper Award!

Benchmarking the Second Generation of Intel SGX for Machine Learning Workloads

Authors: Adrian Lutsch, Gagandeep Singh, Martin Mundt, Ragnar Mogk, Carsten Binnig

Published in: Proceedings of BTW 2023, Lecture Notes in Informatics (LNI)

FEATHERS: Federated Architecture and Hyperparameter Search

Authors: Jonas Seng, Pooja Prasad, Martin Mundt, Devendra Singh Dhami, Kristian Kersting

Accepted at: AutoML Conference, Workshop Track, 2024

A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning

Authors: Martin Mundt, Yongwon Hong, Iuliia Pliushch, Visvanathan Ramesh

Published in: Neural Networks, Volume 160, March 2023, Pages 306-336

Return of the normal distribution: Flexible deep continual learning with variational auto-encoders

Authors: Yongwon Hong*, Martin Mundt*, Sungho Park, Yungjung Uh, Hyeran Byun
(* authors contributed equally)

Published in: Neural Networks, Volume 154, October 2022, Pages 397-412

When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics

Authors: Iuliia Pliushch, Martin Mundt, Nicolas Lupp, Visvanathan Ramesh

Published in: European Conference on Computer Vision (ECCV), 2022

Towards Coreset Learning in Probabilistic Circuits

Authors: Martin Trapp, Steven Lang, Aastha Shah, Martin Mundt, Kristian Kersting, Arno Solin

Published in: 5th Workshop on Tractable Probabilistic Modeling (TPM) at 38th Conference on Uncertainty in Artificial Intelligence (UAI), 2022

CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability

Authors: Martin Mundt, Steven Lang, Quentin Delfosse, Kristian Kersting

Published in: International Conference on Learning Representations (ICLR), 2022

Unified Probabilistic Deep Continual Learning Through Generative Replay and Open Set Recognition

Authors: Martin Mundt, Iuliia Pliushch, Sagnik Majumder, Yongwon Hong, Visvanathan Ramesh

Published in: Journal of Imaging, Volume 8, Issue 4, 2022
Special Issue on Continual Learning in Computer Vision: Theory and Applications

Selected as the issue cover of J.Imaging 8(4)