/2026-09-14T00:00:00+00:00/posts/2026-09-14T00:00:00+00:00/posts/papers/training-small-llms-from-scratch-lessons-from-zagreus-and-nesso/2026-09-14T00:00:00+00:00/posts/papers/feda4fair-client-level-federated-datasets-for-fairness-evaluation/2026-06-25T00:00:00+00:00/posts/papers/rashomon-sets-and-model-multiplicity-in-federated-learning/2026-06-25T00:00:00+00:00/talks/2026-05-27T00:00:00+00:00/posts/stories/tmp_7/2026-02-24T00:00:00+00:00/posts/papers/interpreting-federated-learning-by-aggregating-shap-explanations/2026-01-01T00:00:00+00:00/posts/stories/2025/2025-12-26T00:00:00+00:00/posts/stories/5/2025-11-16T00:00:00+00:00/posts/papers/an-interpretable-data-driven-unsupervised-approach-for-the-prevention-of-forgotten-items/2025-10-21T00:00:00+00:00/posts/stories/4/2025-10-19T00:00:00+00:00/posts/papers/enhancing-local-explanations-with-gan-based-neighborhood-generation/2025-10-05T00:00:00+00:00/posts/papers/a-benchmark-for-client-level-fairness-in-federated-learning/2025-06-30T00:00:00+00:00/posts/papers/differentially-private-fastshap-for-federated-learning-model-explainability/2025-06-30T00:00:00+00:00/posts/papers/benefits-of-the-federation-analyzing-the-impact-of-fair-federated-learning-at-the-client-level/2025-06-23T00:00:00+00:00/posts/papers/puffle-balancing-privacy-utility-and-fairness-in-federated-learning/2024-10-19T00:00:00+00:00/posts/papers/enhancing-privacy-and-utility-in-federated-learning-a-hybrid-p2p-and-server-based-approach-with-differential-privacy-protection/2024-07-08T00:00:00+00:00/posts/papers/semantic-enrichment-of-explanations-of-ai-models-for-healthcare/2023-10-09T00:00:00+00:00/posts/papers/explaining-black-boxes-in-federated-learning/2023-07-26T00:00:00+00:00/posts/stories/3/2022-06-11T00:00:00+00:00/posts/stories/2/2022-01-07T00:00:00+00:00/posts/stories/1/2021-12-31T00:00:00+00:00/picks//talks/xai_23//uses//about-me//pics//research//now/