Společný seminář katedry teoretické informatiky a matematické logiky MFF UK a oddělění umělé inteligence ústavu informatiky AV ČR
Organized jointly by the Department of Theoretical Computer Science and Mathematical Logic, Faculty of Mathemeatics and Physics of the Charles University, and by the Department of Artificial Intelligence, Institute of Computer Science of the Czech Academy of Sciences
Kontakt: / Contact:
Martin Holeňa
www.cs.cas.cz/~martin
+420 266 052 921
martin@cs.cas.cz
skype martinholena
Andreas Opedal. Systematic Analysis of the Arithmetic Reasoning Capabilities of LLMs
Andreas will present his work on large language models’ ability to generalize to complex proofs and make human-like mistakes on arithmetic word problems, which uses a symbolic world-model framework that formalizes reasoning in terms of proof trees.
Přehled seminářů v roce 2025 / List of seminars in 2025
22. 5. |
Victor Letzelter |
Learning under ambiguity through multiple hypotheses and quantization | |
24. 4. |
Jelle Hüntelmann |
Learning to be uncertain: Of soft labels and soft losses | |
10. 4. |
Marcel Kühn |
Anti-Correlated Noise in Epoch-Based Stochastic Gradient Descent and its Implications | |
27. 3. |
Andreas Opedal |
Systematic Analysis of the Arithmetic Reasoning Capabilities of LLMs | |
13. 3. |
Antoni Kowalczuk |
Image Autoregressive Models Leak More Training Data Than Diffusion Models |
|
27. 2. |
Thomas Kleine Buening |
Strategic Interactive Decision-Making |
Přehled seminářů v roce 2024 / List of seminars in 2024
19. 12. |
Peter Blohm |
Probably Approximately Global Robustness Certification |
|
5. 12. |
Vlad Yorsh |
Structured State-Space Neural-Network Models |
|
21. 11. |
Jonas Hübotter |
Transductive Active Learning for Fine-Tuning Large (Language) Models |
|
7. 11. |
Krzysztof Kacprzyk |
AI4Science: Discovering Governing Equations and Beyond |
|
10. 10. |
Ondřej Tichý |
Bayesian Regression and Its Application to Atmospheric Emissions Estimation |
|
23. 5. |
Pierre Nicolay |
Kinematic-Aware Neural Network for Dynamics Modeling |
|
25. 4. |
Balint Gyevnar |
How Do We make Explainable AI Work for People? |
|
11. 4. |
Alex Goodall |
Theory and Applications of Approximate Model-based Shielding for Safe Reinforcement Learning |
|
28. 3. |
Simon Rittel |
Bayesian Causal Structure Learning |
|
14. 3. |
Oliver Sutton |
Can Adversarial Robustness Be Certified for Classifiers Learning High Dimensional Data? |
|
29. 2. |
Michal Znalezniak |
Contrastive Hierarchical Clustering |
|
1. 2. |
Tomáš Pevný |
Tractable Probabilistic Models for Hierarchical Data |
Archiv: / Archive: 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023