Differences

This shows you the differences between two versions of the page.

--- aira:start [2025/12/02 13:08] – [2025-11-27] mzk
+++ aira:start [2025/12/15 13:55] (current) – [Schedule Autumn 2025] mtm
@@ Line 21: / Line 21: @@
 ===== Schedule Autumn 2025 =====
+  * **[RESEARCH TRACK] 2025.12.18**: Maciej Zięba, Associate Professor @ Wrocław University of Technology, [[#section20251218|Normalizing Flows - fundamental concepts and applications in counterfactual explanations.]]
+    * Meeting link:[[https://teams.microsoft.com/meet/34011375285219?p=OD1aOgi4cwK5D4JUBN|MS Teams]]
+    * Recording:  TDA
+    * Presentation slides:  TDA
+  * **[PHD TRACK] 2025.12.11**: Anna Sofia Lippolis, PhD Candidate @ University of Bologna, [[#section20251211|Enhancing Knowledge Engineering with LLMs.]]
+    * Meeting link: [[https://teams.microsoft.com/meet/35848296892369?p=0t3yTogmgGOsSwYeDO|MS Teams]]
+    * Recording: [[https://ujchmura.sharepoint.com/:v:/t/Section_495645_1/IQDOFSfeEBkISrAKy1_qRsl3AVGI18eysApxCWWdZqbUjnM?e=vHo3Li|View]]
+    * Presentation slides: TDA
   * **[PHD TRACK] 2025.12.04**: Bartłomiej Małkus, PhD Candidate @ Jagiellonian University, [[#section20251204|Towards Explainable Meta-Models for Ensembles of Financial Alphas.]]
-    * Meeting link: TDA
+    * Meeting link: [[https://teams.microsoft.com/meet/33172349128262?p=yBHWXyoke6oH4OVDl4|MS Teams]]
     * Recording:  TDA
     * Presentation slides:  TDA
@@ Line 30: / Line 40: @@
     * Meeting link: [[https://teams.microsoft.com/meet/39537797907603?p=jjjJD0gjg5LcGl6eL9|MS Teams]]
     * Recording:  [[https://ujchmura.sharepoint.com/:v:/t/Section_495645_1/IQDqGs_UjUSkRIm82hi1-KgBAc4MLc-EjcVPaewZ6sYskI4?e=qTmdDd|View]]
-    * Presentation slides:  TDA
+    * Presentation slides:  {{:aira:slides-aleksander-mendyk-2025-11-27.pdf|Download}}
   * **[RESEARCH TRACK] 2025.11.13**: Tomáš Kliegr with the research team @ Prague University of Economics and Business, [[#section20251113|RAG research, LLMs as digital twins, Rule Learning in relational data - perspectives in AI Research .]]
@@ Line 491: / Line 501: @@
+==== 2025-12-18 ====
+<WRAP column 15%>
+{{ :aira:maciej-zieba-foto.png?200| }}
+</WRAP>
+<WRAP column 75%>
+**Speaker**: Maciej Zięba, Associate Professor @ Wrocław University of Technology
+**Title**: Normalizing Flows - fundamental concepts and applications in counterfactual explanations.
+**Abstract**:
+During the talk, I will begin with a brief introduction to generative flow-based models. Then, I will present practical examples demonstrating how this class of models can be applied in real-world scenarios. I will introduce flows as probabilistic regression models, highlighting their versatility as plug-in components and their generative capabilities for point clouds. I will also discuss how we applied flow-based models to a few-shot regression problem. Finally, I will illustrate how normalizing flows can be used to address counterfactual explanation tasks.
+**Biogram**:
+Maciej Zięba is a research scientist at Tooploox and an Associate Professor at Wroclaw University of Science and Technology, where he received a Ph.D. degree in computer science and a master's degree in economics. He also obtained a master's degree in computer science at the Blekinge Institute of Technology in Sweden. In 2017, he was a visiting scholar at the University of Wollongong (Australia). His research is directed towards deep learning, especially generative models and representation learning. He was the co-author of a variable number of research papers published in influential journals and presented at the top ML conferences, including NeurIPS, AAAI, ICML, CVPR, and ICLR. He is also leading genwro.ai research group (https://genwro.ai.pwr.edu.pl/) at Wroclaw University of Science and Technology.
+</WRAP>
+<WRAP clear></WRAP>
+==== 2025-12-11 ====
+<WRAP column 15%>
+{{ :aira:anna-lippolis-foto.png?200| }}
+</WRAP>
+<WRAP column 75%>
+**Speaker**: Anna Sofia Lippolis, PhD Candidate @ University of Bologna
+**Title**: Enhancing Knowledge Engineering with LLMs.
+**Abstract**:
+The development and spread of Large Language Models (LLMs) are having a growing impact on the world of the Semantic Web, profoundly transforming the field of Knowledge Engineering. This field, traditionally characterized by a high degree of manual work and collaboration between technical professionals and domain experts, faces various challenges related to scalability and the continuous evolution of knowledge. In this context, LLMs are emerging in several areas, from law to medicine, as tools that support researchers: from the automatic generation of ontologies to the assessment of the quality and semantic coverage of conceptual models, and even the exploration of analogical reasoning, through which it is possible to identify structural correspondences between different domains. This talk will present current research directions on collaboration between LLMs and researchers for knowledge modeling, within a critical overview of the opportunities offered by these tools for the future of the Semantic Web.
+**Biogram**:
+Anna Sofia Lippolis (she/her) is a PhD student at the University of Bologna, Italy, affiliated with the National Research Council’s Institute for Cognitive Sciences and Technologies (Rome, Italy). Her work investigates how semantic technologies intersect with Digital Humanities research and how AI can automate knowledge-engineering practices.
+</WRAP>
+<WRAP clear></WRAP>
 ==== 2025-12-04 ====
@@ Line 505: / Line 556: @@
 **Abstract**:
 One branch of systematic trading research studies large libraries of formulaic alphas: small predictive models built from price and volume data. In practice, these alphas are combined into an ensemble whose composition changes with market conditions. From an ML perspective, this can be viewed as a meta-model that selects and weights weak experts based on their characteristics and the current environment.
-In this talk I will introduce this setting with minimal financial background (cross-sectional returns, information coefficient, long–short factor portfolios), and then reframe it in familiar ML terms. I will show how individual alphas can be treated as models with their own structural and behavioural features, and how this enables clustering them into ""families"" and reasoning about dynamic ensemble construction. Finally, I will sketch the idea of an explainable meta-model that maps alpha features and market descriptors to ensemble decisions, and highlight open methodological questions and possible research directions.
+In this talk I will introduce this setting with minimal financial background (cross-sectional returns, information coefficient, long–short factor portfolios), and then reframe it in familiar ML terms. I will show how individual alphas can be treated as models with their own structural and behavioural features, and how this enables clustering them into "families" and reasoning about dynamic ensemble construction. Finally, I will sketch the idea of an explainable meta-model that maps alpha features and market descriptors to ensemble decisions, and highlight open methodological questions and possible research directions.
 **Biogram**: