relAI work at ICML 2026

News

We are happy to announce that relAI will be represented in Seoul, South Korea, from July 6 to 11 at the Forty-Third International Conference on Machine Learning (ICML2026)!. ICML is widely recognized as one of the top three most influential conferences in machine learning and artificial intelligence research.

📖 About relAI Publications at ICML

  • relAI contributes fourteen publications to the conference, including nine in the main track.
  • relAI PhD student Emre Kavak will present a Spotlight paper (ranked in the top 2.2%).
  • Five relAI papers will be presented at ICML Workshops, with contributions from three relAI MSc students.

🤝Meet relAI Students

If you are attending ICML we encourage you to engage in discussions about relAI research with the following relAI students present at the conference:

You can find their research papers in the list below.

Full list of relAI publications at ICML 2026:

    Spotlight Presentation - Main Track


  1. DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation
    Emre Kavak, Tom Nuno Wolf, Christian Wachinger

    2. Posters - Main Track


  2. Certifying Graph Neural Networks Against Label and Structure Poisoning
    Lukas Gosch, Xichuan Chen, Yan Scholten, Stephan Günnemann
  3. Rank-Learner: Orthogonal Ranking of Treatment Effects
    Henri Arno, Dennis Frauen, Emil Javurek, Thomas Demeester, Stefan Feuerriegel
  4. Interpretable Self-Supervised Learning via Representer Landmarks and Nyström Approximation
    Maedeh Zarvandi, Michael Timothy, Theresa Wasserer, Debarghya Ghoshdastidar
  5. SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning
    Tzu-Yuan Huang, Armin Lederer, Dai-Jie Wu, Xiaobing Dai, Sihua Zhang, Hsiu-Chin Lin, Shao-Hua Sun, Stefan Sosnowski, Sandra Hirche
  6. Frequentist Consistency of Prior-Data Fitted Networks for Causal Inference
    Valentyn Melnychuk, Vahid Balazadeh, Stefan Feuerriegel, Rahul G. Krishnan
  7. Reading Between the Tokens: Improving Preference Predictions through Mechanistic Forecasting
    Sarah Ball, Simeon Allmendinger, Niklas Kühl, Frauke Kreuter
  8. Don't Walk the Line: Boundary Guidance for Filtered Generation
    Sarah Ball, Andreas Haupt
  9. ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior
    Florian Eichin, Yupei Du, Philipp Mondorf, Maria Matveev, Barbara Plank, Michael A. Hedderich
  10. Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization
    Vit Fojtik, Maria Matveev, Hung-Hsu Chou, Gitta Kutyniok, Johannes Maly

    Workshops

  1. Proxy Scoring Enables Benchmarking LLM Forecasters Without Waiting for Outcomes
    Julius Hege, Gitta Kutyniok
    ICML 2026, Forecasting as a New Frontier of Intelligence Workshop
  2. What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics
    Sofiia Nikolenko, Michele Papucci, Mina Rezaei, Shireen Kudukkil Manchingal
    ICML 2026, The 2nd Workshop on Epistemic Intelligence in Machine Learning
  3. Bigger Is Not Better: Inverse Scaling and Arbitration Failure in Counterfactual Visual Grounding
    Fabian Grob, Sanghwan Kim, Cordelia Schmid, Zeynep Akata
    ICML 2026, Mechanistic Interpretability Workshop
  4. On the Uncertainty in Prior-Data Fitted Network Pretraining
    Manuel Hülskamp, Julius Kobialka, Emanuel Sommer, David Rügamer
    ICML 2026, 2nd Workshop on Foundation Models for Structured Data (FMSD)
  5. ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior
    Florian Eichin, Yupei Du, Philipp Mondorf, Maria Matveev, Barbara Plank, Michael A. Hedderich
    ICML 2026, Mechanistic Interpretability Workshop

We are pleased to share relAI’s contribution to the European Embodied Robotics Week, whichtook place last week in Munich. The event was organizedby RoboTUM together with START Munich and the ESRA (European Student Robotics Association) network.

The Robotics Festival convened a diverse range of stakeholders from the European robotics and physical artificial intelligence ecosystem. Specialists, students, and robotics enthusiasts participated in city-wide events, including open houses at robotics laboratories, makerspaces, and studios throughout Munich, as well as a hackathon.

The event ended with a summit featuring talks and panels from leaders in embodied intelligence. relAI was represented in the panel discussion “Dexterity and Manipulation for robotics”  by relAI Fellow Prof. Khadiv.

relAI is proud to announce an outstanding achievement – a first author publication of Moritz Knolle, one of relAI’s PhD students, in Nature journal.

Medical AI models are increasingly utilized in applications such as diagnosing and remotely treating patients. While these models have proven valuable to both practitioners and patients, concerns remain about the privacy of patients whose information is used to train these AI systems. This issue has been examined by relAI PhD student Moritz Knolle, in a study published this week in Nature. The analysis revealed privacy vulnerabilities in medical AI models, emphasizing the importance of reliable AI research in medicine and healthcare 🩺.

🔍 Check the summary below and the article to learn more about the study!.

Summary of the article

Individuals whose data are used to train medical AI models may be at risk of being identified in cyber-attacks, according to a Nature paper published this week. Underrepresented groups may face disproportionately higher risks of having their data compromised, the study indicates. The researchers find these individuals are not accounted for in current risk assessments and call for further mitigation and strict access control. 

Medical AI models may improve global health outcomes, especially in areas in which specialized expertise is not available. Yet, the sensitive data used to train these models may be exposed to privacy attacks. Membership inference attacks (MIAs) are used by attackers to determine whether an individual’s data were used to train a model. From these attacks, a patient’s medical data and private information can be determined. Previous research on data risk has been determined by whole datasets, and does not take an individual’s risk into account.

Moritz Knolle and colleagues conduct a privacy audit to focus on individual privacy risk, finding that medical AI models may pose a privacy risk to individual data contributors. Using seven large datasets made up of real-world clinical data, including medical images, electrocardiograms and electronic health records, the authors determine the most vulnerable among data-contributing patients. They find that at an individual level, those targeted by the MIAs were successfully done so with almost no error. At a group level, those identified as underrepresented in datasets include people with rare diseases, people from a minority racial group or, socioeconomic status, or those having the less-common gender. With more distinctive data that are encoded by AI models, these groups and individuals are found to be more vulnerable and disproportionately exposed to privacy attacks. The authors find the instances of successful MIAs attacks rise with model capacity and size. 

These findings show privacy attacks, such as MIA, are more effective at successfully targeting on an individual level than currently thought. The authors conclude that privacy risk assessment must now take individual risk into account, and vulnerable models be further protected."

👉 Link to article: https://www.nature.com/articles/s41586-026-10688-0

🎉 Congratulations to relAI PhD student Moritz Knolle, relAI Fellow Daniel Rückert, former relAI Fellow Georgios Kaissis, and co-authors for the fantastic work!

We are proud to announce that relAI director Gitta Kutyniok has been appointed Vice President of the Berlin-Brandenburg Academy of Sciences and Humanities (BBAW). Her term will begin on October 1, 2026.

The Berlin-Brandenburg Academy of Sciences and Humanities has a remarkable 325-year history of bringing together brilliant scholars and scientists from various backgrounds and disciplines, including 82 Nobel Prize winners. This Academy plays a vital role in our society by not only advancing research in the humanities but also addressing critical scientific and social issues through collaboration. We deeply value its mission to foster understanding and dialogue between the scientific community and the broader society, as this connection is essential for tackling the challenges we face together.

🎉 Congratulations!

As our current Coordinator is taking an exciting 👏 next step in their academic career to transition into a professorship 🎓, a wonderful opportunity has opened to join our team.

If you are interested in working at our innovative and interdisciplinary school, where you can help shape the research and education of the next generation of experts in reliable AI, we encourage you to check out the job posting.

If you meet the qualifications and would like to apply, please submit your application by June 14, 2026.

Coordinator of the Konrad Zuse School of Excellence in Reliable Artificial Intelligence (m/f/d)

The Konrad Zuse School of Excellence in Reliable Artificial Intelligence (relAI), founded in 2022, is one of three DAAD funded AI schools in Germany. relAI is a joint endeavor of TUM and LMU and has quickly become an international lighthouse for education and research in reliable AI in Germany. More than 100 MSc and doctoral researchers participate simultaneously, supervised by more than 50 professors. Our network includes international AI centers, non-university research organizations and various industrial partners. relAI opens up career paths in academia and industry to talented young researchers from around the world. The coordination office of this graduate school is located at and embedded in the infrastructure of the Munich Data Science Institute (MDSI) – an Integrative Research Institute at the Technical University of Munich (TUM) with an interdisciplinary and cross-faculty focus in the field of data science, machine learning and A

As the Coordinator of relAI you will be responsible for managing school-wide and extra-school activities.

Key responsibilities:

  • Developing and organizing events and training courses, e. g. career fairs, seminars, symposia, workshops, seasonal schools, retreats and conferences
  • Reporting to the directors, the DAAD and various stakeholders
  • Serving as the primary point of contact for our fellows and for our academic and industrial partners
  • Developing and executing recruitment strategies for the school´s candidates
  • Overall responsibility for the school's budget monitoring and financial reporting in coordination with TUM’s central administration; overseeing the allocation of funds and maintaining the comprehensive records and databases of the relAI network
  • Implementation and maintenance of efficient project management structures to ensure smooth daily operations of the graduate program.
  • Coordination of the application for project continuation after 2027.

Your qualification:

We are looking for a reliable and collaborative person able to manage a broad range of tasks and responsibilities with

  • Postgraduate degree (MSc or equivalent), combined with a certain affinity for data science, machine learning and AI
  • Professional experience in project management and/or science management, ideally in coordinating university programs or graduate schools
  • Leadership skills and a good intercultural understanding, high motivation, flexibility and reliability
  • Fluent in German and English, written and spoken, negotiating skills
  • Beyond standard MS Office, experience in managing digital collaboration tools and technical infrastructures is highly desirable (e.g., mailing lists, basic SQL databases, or content management systems for website maintenance).

We offer:

  • Full responsibility from the start in an innovative environment and with real impact on the data science ecosystem at TUM and in Munich
  • International, attractive, and interdisciplinary working environment across different departments and disciplines
  • Salary according to TV-L (depending on qualification up to E13) including social benefits.

Application:

The position can start immediately, and the contract duration is initially limited until December 31, 2027; a further extension is envisioned, subject to continued project funding. As an equal opportunity and affirmative action employer, TUM explicitly encourages nominations of and applications from women as well as from all others who would bring additional diversity dimensions to the university’s research and teaching strategies. Preference will be given to disabled candidates with essentially the same qualifications. If you are interested, please apply until June 14, 2026 with a cover letter (stating also your earliest date of entry), CV and relevant certificates plus reference letters via email to  application@mdsi.tum.de (please attach a single PDF file and use the subject Coordinator relAI).

As part of your application for a position at the Technical University of Munich (TUM), you are transmitting personal data. Please note our data protection information in accordance to Art.13 General Data Protection Regulation (GDPR) for the collection and processing of personal data in the context of your application (https://portal.mytum.de/kompass/datenschutz/Bewerbung/). By submitting your application, you confirm that you have taken note of TUM´s data protection information.

Contact:
https://zuseschoolrelai.de/
Email:  coordinators@zuseschoolrelai.de 
Technische Universität München
Munich Data Science Institute
Konrad Zuse School of Excellence in Reliable AI
Walther-von-Dyck-Straße 10
85748 Garching bei München


🔮How will artificial intelligence (AI) influence the future of learning?

The 🌍 International Symposium on Future Learning 🎓, organized by the TUM Center for Educational Technologies and relAI will address this significant question, which lies at the heart of the Learning & Instruction relAI research area.  

Key Information

📅 8. June 2026 9:15 - 14:00

📍Lecture hall 605, Marsstraße 20, München

🙋‍️ Registration Link

Highlights of the symposium:

To help us plan, please make sure to RSVP via the registration link

We look forward to seeing you on June 8th!

📢 We are excited to announce that the call for applications to the MSc program 2026 of our Konrad Zuse School of Excellence in Reliable AI (relAI) is now open!

The innovative relAI MSc program is an addition to the MSc program at TUM or LMU, offering a cross-sectional training for successful education in AI. It provides a coherent, yet flexible and personalized training by enhancing scientific knowledge, professional development courses, and industrial exposure.  

Funded applicants will receive a scholarship of up to 992 EUR (depending on independent income). They are further supported by travel grants, e.g., for home travel.  

We highly encourage you to apply if you have: 

📆 Application Deadline: 15 June 2026 (23:59 AOE)

🔗 Apply now: https://zuseschoolrelai.de/application/#MSc-Program-Application

Please help us in spreading the word, especially to excellent international candidates.

Are you interested in contributing research for underserved communities? Don't miss the EEAMO Conference 2026, the 6th ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization.

relAI is excited to support the conference, which will take place from November 5 to 7, 2026. EEAMO 2026 is organized by LMU, with relAI Fellow Christoph Kern and relAI Student Clara Strasser Ceballos serving as General Chairs.

This event will showcase work across the research-to-practice pipeline, aiming to ensure that algorithmic systems serve a broadly beneficial role in society by advancing equity and expanding access to opportunities for underserved communities.

Call for papers: Important Deadlines!

📅 Abstract: May 1
📅 Paper: May 8

relAI research will be featured at the International Conference on Learning Representations (ICLR), which will take place this year at the Riocentro Convention and Event Center in Rio de Janeiro, Brazil, from April 23rd to 27th, 2026. ICLR is one of the leading conferences with significant impact and reputation in machine learning and artificial intelligence research.

relAI Publications at ICLR

Meet relAI Students

If you attend ICLR, be sure to take the opportunity to discuss relAI research with relAI students attending the conference: Sarah Ball, Cecilia Casolo, Lukas Gosch, Valentyn Melnychuk, Ole Petersen, Yusuf Sale, Yan Scholten, Jonas von Berg, and Jingpei Wu. You can find their research papers in the list below.

Full list of relAI publications at ICLR 2026:

    Main Track


  1. Efficient Credal Prediction through Decalibration
    Paul Hofman, Timo Löhr, Maximilian Muschalik, Yusuf Sale, Eyke Hüllermeier
  2. Discrete Bayesian Sample Inference for Graph Generation
    Ole Petersen, Marcel Kollovieh, Marten Lienen, Stephan Günnemann
  3. Identifiability Challenges in Sparse Linear Ordinary Differential Equations
    Cecilia Casolo, Sören Becker, Niki Kilbertus
  4. Sampling-aware Adversarial Attacks Against Large Language Models
    Tim Beyer, Yan Scholten, Leo Schwinn, Stephan Günnemann
  5. Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
    Yan Scholten, Sophie Xhonneux, Leo Schwinn, Stephan Günnemann
  6. Efficient and Sharp Off-Policy Learning under Unobserved Confounding
    Konstantin Hess, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel
  7. Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimation
    Valentyn Melnychuk, Dennis Frauen, Jonas Schweisthal, Stefan Feuerriegel
  8. GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomes
    Valentyn Melnychuk, Stefan Feuerriegel
  9. IGC-Net for conditional average potential outcome estimation over time
    Konstantin Hess, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel
  10. On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
    Sarah Ball, Greg Gluch, Shafi Goldwasser, Frauke Kreuter, Omer Reingold, Guy N. Rothblum
  11. Foundation Models for Causal Inference via Prior-Data Fitted Networks
    Yuchen Ma, Dennis Frauen, Emil Javurek, Stefan Feuerriegel
  12. An Orthogonal Learner for Individualized Outcomes in Markov Decision Processes
    Emil Javurek, Valentyn Melnychuk, Jonas Schweisthal, Konstantin Hess, Dennis Frauen, Stefan Feuerriegel
  13. The Price of Robustness: Stable Classifiers Need Overparameterization
    Jonas von Berg, Adalbert Fono, Massimiliano Datres, Sohir Maskey, Gitta Kutyniok

    Journal Track


  1. Adversarial Robustness of Graph Transformers
    Philipp Foth, Simon Geisler, Lukas Gosch, Leo Schwinn, Stephan Günnemann
    Transactions on Machine Learning Research (TMLR), Journal Track Poster - ICLR 2026, 2025
  2. Online Selective Conformal Prediction: Errors and Solutions
    Yusuf Sale, Aaditya Ramdas
    Transactions on Machine Learning Research (TMLR), Journal Track Poster - ICLR 2026, 2025

    Workshops

  1. Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning
    Ajinkya Mohgaonkar, Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Stephan Günnemann
    ICLR 2026 Workshop on Principled Design for Trustworthy AI
  2. ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward
    Jingpei Wu, Xiao Han, Weixiang Shen, Boer Zhang, Zifeng Ding, Volker Tresp
    ICLR 2026 Workshop on Logical Reasoning of Large Language Models