Location: Saarbrücken
Contact: ELIZA-sek@cs.uni-saarland.de
Jilles Vreeken is tenured faculty at the CISPA Helmholtz Center for Information Security, honorary professor at Saarland University, and fellow of the European Laboratory for Learning and Intelligent Systems (ELLIS). He obtained his Ph.D. in 2009 from Utrecht University, was a post-doctoral researcher at Antwerp University until 2013, and both independent research group leader (W2) at Saarland University and senior researcher at the Max Planck Institute for Informatics until 2018. His research focuses on developing well-founded theory and efficient methods that give clear and actionable insight into large, complex data and models. In more general terms, he likes data mining, machine learning, and causal inference.
Iza is a PhD student at Saarland University. Her research lies at the intersection of natural language processing and computational psycholinguistics. She explores how language models can both implement and inform theories of human language processing. Her work examines correlations between model behavior (e.g., word probabilities) and human data such as eye movements during reading.
Batuhan Koyuncu is currently a Ph.D. candidate in Computer Science at Saarland University, affiliated with the ELLIS Ph.D. program and co-advised by Prof. Isabel Valera and Prof. Ole Winther. His research lies at the intersection of deep generative modeling and probabilistic methods for spatial and time-series data. Recently, his work has focused on developing interpretable and scalable architectures for nowcasting and forecasting, with applications in macroeconomics and personalized healthcare. Among his most influential publications is “Variational Mixture of Hyper Generators for Learning Distributions Over Functions” (ICML 2023, with Sanchez-Martin, Peis, Olmos, and Valera), which introduced a flexible generative framework for modeling function distributions. This line of research continues with “Hyper-Transforming Latent Diffusion Models” (ICML 2025, with Peis, Valera, and Frellsen), extending the capabilities of generative models over functions through structured diffusion-based techniques.
I am Sneha Chetani, a passionate researcher in machine learning and deep neural networks, currently working as a research assistant. I thrive on learning new concepts, exploring innovative ideas, and contributing to exciting developments in the field.
I am an ELIZA Master’s student in the Department of Language Science and Technology at Universität des Saarlandes. I previously earned a Ph.D. in Mathematics from Gauhati University, Assam, India, under the supervision of Prof. H. K. Saikia. Before joining Universität des Saarlandes, I held teaching and research positions at various institutions in India.
My current research interests lie in exploring the interpretability of language and vision models through their underlying mathematical frameworks. Prior to this, I studied the convergence properties of an optimizer based on Heun’s method, in collaboration with Ms. Sukannya Purkayastha. This work was presented at the 12th NeurIPS Workshop on Optimization for Machine Learning (2020).
In 2017, I was awarded a fellowship by the Indian Academy of Sciences to conduct research at the Indian Statistical Institute, Kolkata. In 2024, I was selected for the Research-Oriented Master’s Scholarship by the Konrad Zuse School of Excellence in Learning and Intelligent Systems (ELIZA).
My name is Tim and I am a graduate student at Saarland University, Germany. I am broadly interested in the field of artificial intelligence and machine learning. Ultimately, I would love to contribute to the development of artificial general intelligence (AGI) systems.
I have a vast theoretical foundation in machine learning, covering general principles, deep learning, reinforcement learning, optimization, trustworthiness, and explainability. I also have some basic knowledge of structural causal models, causal discovery, and variational inequality methods (e.g., used in multi-agent systems and GANs). On the symbolic side of AI, I know about heuristic exploration of search spaces, SAT and SMT solving, deductive verification, and model checking. Regarding programming, I have extensive experience in Python, especially in PyTorch, and related libraries like PyTorch Lightning and Weights & Biases. I have also used languages like C, C++, Java, and JavaScript throughout my studies.
Currently I am working with Prof. Isabel Valera and Prof. Jilles Vreeken on time series analysis and attention-based models.