Dr. Gabriel Kalweit
Postdoc
Institut für Informatik
Albert-Ludwigs-Universität
Georges-Koehler-Allee 201, Room 00-019
79110 Freiburg im Breisgau
Email: 
Preprints
- Mansour Alyahyay, Gabriel Kalweit, Maria Kalweit, Golan Karvat, Julian Ammer, Artur Schneider, Ahmed Adzemovic, Andreas Vlachos, Joschka Boedecker and Ilka Diester. Mechanisms of Premotor-Motor Cortex Interactions during Goal Directed Behavior. 2023. biorxiv
- Jens Rahnfeld, Mehdi Naouar, Gabriel Kalweit, Joschka Boedecker, Estelle Dubruc and Maria Kalweit. A Comparative Study of Explainability Methods for Whole Slide Classification of Lymph Node Metastases using Vision Transformers. 2024. medrxiv
- Yannick Vogt, Mehdi Naouar, Maria Kalweit, Cornelius Miething, Justus Duyster, Joschka Boedecker and Gabriel Kalweit. BetterBodies: Reinforcement Learning guided Diffusion for Antibody Sequence Design. arxiv
Publications
2024
- Paul Schmidt-Barbo, Gabriel Kalweit, Mehdi Naouar, Lisa Paschold, Edith Willscher, Christoph Schultheiss, Bruno Markl, Stefan Dirnhofer, Alexandar Tzankov, Mascha Binder and Maria Kalweit. Detection of disease-specific signatures in B cell repertoires of lymphomas using machine learning. In PLOS Computational Biology.
- Maria Kalweit and Gabriel Kalweit. Warum wir neu lernen müssen, mit Maschinen zu sprechen – eine Momentaufnahme der Generativen KI im Januar 2024. In Ordnung der Wissenschaft. web
- Gabriel Kalweit, Anusha Klett, Mehdi Naouar, Jens Rahnfeld, Yannick Vogt, Diana Laura Infante Ramirez, Rebecca Berger, Jesus Duque Afonso, Tanja Nicole Hartmann, Marie Follo, Michael Luebbert, Roland Mertelsmann, Evelyn Ullrich, Joschka Boedecker and Maria Kalweit. Unsupervised Feature Extraction from a Foundation Model Zoo for Cell Similarity Search in Oncological Microscopy Across Devices. Accepted at the ICML 2024 Workshop on Foundation Models in the Wild.
- Hao Zhu, Brice De La Crompe, Gabriel Kalweit, Artur Schneider, Maria Kalweit, Ilka Diester and Joschka Boedecker. Multi-intention Inverse Q-learning for Interpretable Behavior Representation. Accepted at TMLR, 2024. web
2023
- Gabriel Kalweit, Maria Kalweit, Ignacio Mastroleo, Joschka Bödecker und Roland Mertelsmann. Künstliche Intelligenz in der Krebstherapie. Ordnung der Wissenschaft, 2023. web
- Mehdi Naouar, Gabriel Kalweit, Ignacio Mastroleo, Philipp Poxleitner, Marc Metzger, Joschka Boedecker and Maria Kalweit. Robust Tumor Detection from Coarse Annotations via Multi-Magnification Ensembles. Oral at Digital Oncology, Hannover 2023. arxiv
- Mehdi Naouar, Gabriel Kalweit, Anusha Klett, Yannick Vogt, Paula Silvestrini, Diana Infante, Roland Mertelsmann, Joschka Boedecker and Maria Kalweit. CellMixer: Annotation-free Semantic Cell Segmentation of Heterogeneous Cell Populations. Oral at NeurIPS 2023 Workshop on Medical Imaging.
- Yannick Vogt, Mehdi Naouar, Maria Kalweit, Cornelius Miething, Justus Duyster, Roland Mertelsmann, Gabriel Kalweit and Joschka Boedecker. Stable Online and Offline Reinforcement Learning for Antibody CDRH3 Design. NeurIPS 2023 Workshop on Machine Learning in Structural Biology.
2022
- Maria Kalweit, Gabriel Kalweit, Moritz Werling and Joschka Boedecker. Deep Surrogate Q-Learning for Autonomous Driving. ICRA 2022.
- Jessica Borja-Diaz*, Oier Mees*, Gabriel Kalweit, Lukas Hermann, Joschka Boedecker and Wolfram Burgard. Affordance Learning from Play for Sample-Efficient Policy Learning. ICRA 2022.
- Gabriel Kalweit, Maria Kalweit, Joschka Boedecker. Robust and Data-efficient Q-learning by Composite Value-estimation. TMLR 2022.
- Erick Rosete-Beas*, Oier Mees*, Gabriel Kalweit, Joschka Boedecker and Wolfram Burgard. Latent Plans for Task-Agnostic Offline Reinforcement Learning. CoRL 2022.
- Thomas Hügle, Leo Caratsch, Matteo Caorsi, Jules Maglione, Alexandre Dumusc, Diana Dan, Marc Blanchard, Gabriel Kalweit and Maria Kalweit. Automated Recognition and Monitoring of Dorsal Finger Folds by a Convolutional Neural Network as a Potential Digital Biomarker for Joint Swelling in Patients with Rheumatoid Arthritis. Accepted at Digital Biomarkers, 2022
2021
- Branka Mirchevska, Maria Hügle, Gabriel Kalweit, Moritz Werling, Joschka Boedecker. Amortized Q-learning with Model-based Action Proposals for Autonomous Driving on Highways. ICRA 2021. arxiv Video
- Maria Hügle, Ulrich A Walker, Axel Finckh, Ruediger Mueller, Gabriel Kalweit, Almut Scherer, Joschka Boedecker, Thomas Hügle. Personalized Prediction of Disease Activity in Patients with Rheumatoid Arthritis Using an Adaptive Deep Neural Network. PLOS ONE.
- Maria Kalweit, Gabriel Kalweit and Joschka Boedecker. AnyNets: Adaptive Deep Neural Networks for Medical Data with Missing Values. IJCAI 2021 Workshop on Artificial Intelligence for Function, Disability, and Health. web
- Maria Kalweit, Gabriel Kalweit, Moritz Werling and Joschka Boedecker. Deep Surrogate Q-Learning for Autonomous Driving. IJCAI 2021 Workshop on Artificial Intelligence for Autonomous Driving. web video
- Gabriel Kalweit, Maria Kalweit, Mansour Alyahyay, Zoe Jaeckel, Florian Steenbergen, Stefanie Hardung, Ilka Diester and Joschka Boedecker. NeuRL: Closed-form Inverse Reinforcement Learning for Neural Decoding. ICML 2021 Workshop on Computational Biology. web
- Gabriel Kalweit, Maria Huegle, Moritz Werling and Joschka Boedecker. Q-learning with Long-term Action-space Shaping to Model Complex Behavior for Autonomous Lane Changes. IROS 2021.
- Jessica Borja-Diaz, Oier Mees, Gabriel Kalweit, Lukas Hermann, Joschka Boedecker and Wolfram Burgard. Affordance learning from play for sample-efficient policy learning. NeurIPS 2021 Workshop on Robot Learning.
2020
- Gabriel Kalweit*, Maria Huegle*, Moritz Werling and Joschka Boedecker. Deep Inverse Q-learning with Constraints. NeurIPS 2020. arxiv Video Project Page
- Maria Huegle, Gabriel Kalweit, Moritz Werling and Joschka Boedecker. Dynamic Interaction-Aware Scene Understanding for Reinforcement Learning in Autonomous Driving. ICRA 2020. arxiv Video Project Page
- Oier Mees*, Markus Merklinger*, Gabriel Kalweit and Wolfram Burgard. Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video. CVPR 2020 Workshop on Learning from Unlabeled Videos.
- Oier Mees*, Markus Merklinger*, Gabriel Kalweit and Wolfram Burgard. Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video. ICRA 2020 (Nominated for Best Paper Award in Cognitive Robotics). arxiv Project Page Dataset Video
- Maria Hügle, Gabriel Kalweit, Thomas Hügle and Joschka Boedecker. A Dynamic Deep Neural Network For Multimodal Clinical Data Analysis. AAAI 2020 Workshop on Health Intelligence. Explainable AI in Healthcare and Medicine. Studies in Computational Intelligence, Springer (2020). web Project Page
2019
- Maria Huegle*, Gabriel Kalweit*, Branka Mirchevska, Moritz Werling and Joschka Boedecker. Dynamic Input for Deep Reinforcement Learning in Autonomous Driving. IROS 2019. arxiv Project Page Video
- Gabriel Kalweit, Maria Huegle and Joschka Boedecker. Composite Q-Learning. Combining Learning and Reasoning – Towards Human-Level Robot Intelligence. PDF
- Markus Merklinger, Oier Mees, Gabriel Kalweit and Wolfram Burgard. Adversarial Skill Networks: Unsupervised Skill Learning from Video.
2017
- Gabriel Kalweit, Joschka Boedecker (2017) Uncertainty-driven Imagination for Continuous Deep Reinforcement Learning. CoRL 2017. PDF Video Project Page
Patents
- Maria Huegle, Gabriel Kalweit, Branka Mirchevska, Moritz Werling and Joschka Boedecker. (EP3730369A1) Selecting a Motion Action for an Automated Vehicle Considering a Variable Number of Other Road Users. web
- Moritz Werling, Branka Mirchevska, Joschka Bödecker, Maria Hügle and Gabriel Kalweit. (10 2020 106 816.6) Steuerung eines automatisierten Kraftfahrzeugs. web
- Moritz Werling, Gabriel Kalweit, Maria Hügle and Joschka Bödecker. (10 2020 121 150.3) Trainieren eines Reinforcement Learning Agenten zur Steuerung eines autonomen Systems. web
- Joschka Bödecker, Maria Hügle, Gabriel Kalweit and Moritz Werling. (WO002022033746A1) Training a Reinforcement Learning Agent to Control an Autonomous System. web
- Joschka Boedecker, Maria Huegle, Gabriel Kalweit, Moritz Werling. (US 2024/0037447 A1) Training a Reinforcement Learning Agent to Control an Autonomous System. web
Academic Activities
- Program Committee Member: NeurIPS 2021 Workshop on Deployable Decision Making in Embodied Systems web
- Volunteer: RSS 2019 web
- Chair: IROS 2021 Session "Reinforcement Learning II"
- Reviewer: ICLR, NeurIPS, CoRL, IROS, ICRA, L4DC
Teaching
- Lecturer, WS2024/25: Reinforcement Learning (Lecture)
- Co-Organizer, WS2024/25: Machine Learning in Health (Seminar)
- Lecturer, WS2023/24: Reinforcement Learning (Lecture)
- Co-Organizer, WS2023/24: Machine Learning in Health (Seminar)
- TA, WS2020/21: Reinforcement Learning (Lecture)
- TA, WS2019/20: Reinforcement Learning (Lecture)
- TA, WS2018/19: Reinforcement Learning (Lecture)
- Co-Organizer, SS2018: Hierarchical Reinforcement Learning (Seminar)
- TA, WS2017/18: Reinforcement Learning (Lecture)
- TA, WS2015/2016: Algorithm Theory (Lecture)
- Student Tutor, SS2015: Advanced Programming in Java (Programming Course)
- Student Tutor, WS2013/2014: Computer Engineering (Lecture)
- Student Tutor, SS2013: Advanced Programming in Java (Programming Course)
- Student Tutor, WS2012/2013: Computer Engineering (Lecture)
Students (Co-)Supervised
- Kerstin Ohler and Emmanuel Hofmann (Cell Tracking and Apoptosis Prediction, Master's project, together with Maria Kalweit)
- Jens Rahnfeld (Enhancing Interpretability of ViT Attention in Histopathology, Master's project, together with Maria Kalweit and Mehdi Naouar)
- Matthias Eberle (Few-shot Cell Classification via Foundation Models, Master's project, together with Maria Kalweit and Mehdi Naouar)
- Batin Muslu (Uncertainty-driven Offline model-based RL, RL Lab, together with Yannick Vogt)
- Julian Eble (RL for Graph Design, Bachelor's Project, together with Prof. Ruxandra Lasowski and Yannick Vogt)
- Mehdi Naouar (Multi-magnification Classifier Ensemble for the Classification of Whole Slide Images, Master's Thesis, together with Maria Kalweit)
- Yannick Vogt (Uncertainty-regularized Offline Reinforcement Learning, Master's Thesis, together with Jasper Hoffmann and Baohe Zhang)
- Erick Rosete Beas (Skill-Chaining Latent Behaviors with Offline Reinforcement Learning, Master's Thesis, together with Oier Mees) -- Recipient of the VDI Award 2023
- Yannick Vogt (Uncertainties in Value-function Estimation, Master's Project)
- Paulina Friemann (Modeling of Ant's Behavior via (I)RL, Master's Thesis, together with Joschka Boedecker)
- Christian Leininger (Inverse Q-learning from Images, Student Project)
- Jessica Borja (Affordance Models in Reinforcement Learning, Master's Project, together with Oier Mees)
- Alex Rose (Optimising for Unsupervised Skill Discovery, Master's Thesis, together with Maria Kalweit)
- Markus Merklinger (Unsupervised Skill Learning from Video, Master's Thesis, together with Oier Mees)
- Ashwin Raaghav (Behavioral Modeling of Rats using Inverse Reinforcement Learning, Master's Project, together with Maria Kalweit)
- Nico Ott, Hendrik Vloet (RL Framework for Sarcraft II, Lab Course, together with Maria Kalweit)
- Ahmed Abdelhadi, Sara Al-Rawi (Safe Reinforcement Learning with hybrid Action-spaces, Master's Project, together with Maria Kalweit)
- Kshitij Sirohi, Ben Wilhelm, Novian Habibie, Fabien Jenne, Dennis Raith (Audi Autonomous Driving Cup 2018, together with Johan Vertens)
- Felix Plum, Philipp Jund, Markus Merklinger, Jan Bechtold, Lior Fuks (Audi Autonomous Driving Cup 2017, together with Johan Vertens)
- Farooq Zuberi, Toshika Srivastava, Amanullah Tariq, Mathias Zink, Christian Ehrenfeld (Audi Autonomous Driving Cup 2016)