Seminars - page 3

The DIG team holds a seminar about every two weeks with speakers either from the team, or invited.

You can add the seminars to your calendar with this ics file, and get emails about future seminars by subscribing to our mailing-list.

If you would like to present your work at our seminar, please contact Nils.

Upcoming Seminars

Towards Conflict-Aware LLM Reasoning Grounded in Open Multilingual Knowledge Graphs

Tuesday, September 08, 2026 11:45, 4A301

Laura Balbi (University of Lisbon)

Large Language Models (LLMs) increasingly operate in settings where they must reason over heterogeneous sources of knowledgecontaining ambiguities and conflicts whose detection and interpretation requires implicit semantic understanding. Knowledge graphs provide a structured and formally defined representation of such knowledge, making them particularly valuable for studying and supporting these reasoning processes. My research investigates how well LLM-based systems detect and reason over conflicts grounded in formal knowledge graph semantics.

Read full seminar details

Structured Clinical Reasoning with Foundation Models

Tuesday, September 15, 2026 11:45, 4A301

Zhan Qu (Scads Dresden)

Foundation models have demonstrated strong capabilities across a wide range of clinical tasks, yet their application to longitudinal electronic health records (EHRs) remains limited by the difficulty of evaluating clinically grounded reasoning, maintaining consistent patient-state representations over time, and predicting future clinical events within large, weakly structured outcome spaces. My research addresses these challenges by introducing structured methods for clinical AI across evaluation, inference, and prediction. I develop an ontology-grounded evaluation framework that jointly assesses factual correctness and patient-contextual grounding, enabling systematic identification of clinically meaningful reasoning errors beyond conventional accuracy metrics. I further investigate protocol-constrained longitudinal reasoning through persistent patient-state representations that evolve with incoming clinical evidence, improving temporal consistency, calibration, and interpretability over extended patient trajectories. Finally, I reformulate longitudinal prediction as reasoning within structured hypothesis spaces by combining medical coding hierarchies with data-driven temporal and cross-modal associations to construct patient-specific candidate outcomes before inference. Together, these studies demonstrate how explicit clinical structure can be incorporated throughout the clinical AI pipeline, integrating biomedical knowledge, longitudinal patient states, and structured hypothesis spaces to improve the reliability, interpretability, and clinical grounding of foundation models for longitudinal decision support.

Read full seminar details

Past Seminars

ProvSQL: Provenance and Probabilistic Querying in Uncertain Databases

Tuesday, April 08, 2025 11:45, 4A125

Pratik Karmakar (None)

Probabilistic databases provide a powerful framework for managing and querying uncertain data, enabling principled reasoning under uncertainty. ProvSQL extends PostgreSQL to support provenance tracking and probability computation in probabilistic databases, leveraging provenance circuits to efficiently compute probabilities and Shapley-based data valuations. In this talk, we introduce ProvSQL, demonstrate its capabilities, and explore a key use case—content based image retrieval from the COCO dataset. We show how probabilistic query evaluation and data valuation techniques enhance explainability and trust in AI-driven decision-making.

Read full seminar details

Tabular foundation models: priors for numbers and strings

Tuesday, March 25, 2025 11:45, 4A301

Gaël Varoquaux (INRIA)

Deep-learning typically does not outperform tree-based models on tabular data. Often this may be explained by the small size of such datasets. For images, sound, text, the solution has be pretrained models, leading to foundation models, adapted and reused for many tasks. I will discuss the challenges to bring these ideas to tabular learning, and the progress that we have made, building priors for tables, ie columns of different natures, with numbers and strings.

Read full seminar details

Neuro-symbolic approaches for the knowledge graph lifecycle

Tuesday, March 18, 2025 11:45, 4A301

Pierre Monnin (INRIA)

In the Web of Data, an increasing number of knowledge graphs (KGs) are concurrently published, edited, and accessed by human and software agents. Their wide adoption makes essential the tasks of their lifecycle: construction, refinement (e.g., matching, link prediction), mining, and usage to support applications (e.g., explainable AI, recommender systems). However, all these tasks require facing the inherent heterogeneity of KGs, e.g., in terms of granularities, vocabularies, and completeness. Besides, scalability issues arise due to their increasing size and combinatorial nature. In my talk, I will present my research on neuro-symbolic approaches for the KG lifecycle, intertwining domain knowledge from ontologies, deductive reasoning, analogical reasoning, and machine learning models. Throughout my presentation, I will show that such approaches enhance models by improving their semantic awareness, frugality, and the semantic interpretability of their latent representation space.

Read full seminar details