Machine Learning and Modelling Seminar

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.

Organizer

Martin Holeňa
+420 266 052 921
martin@cs.cas.cz
skype martinholena

Thursday 14:00 in the lecture room S8, Malostranské náměstí 2.

We shall start the sommer semester of our seminar on Thursday February 27.

[Permanent Link]

Years

Upcoming Talks

  • Victor Letzelter:

    Learning under ambiguity through multiple hypotheses and quantization

    22.05.2025 14:00Lecture room 8, Faculty of Mathematics and Physics, Malostranské náměstí 2

  • Jelle Hüntelmann:

    Learning to be uncertain: Of soft labels and soft losses

    24.04.2025 14:00Lecture room 8, Faculty of Mathematics and Physics, Malostranské náměstí 2

  • Marcel Kühn:

    Anti-Correlated Noise in Epoch-Based Stochastic Gradient Descent and its Implications

    10.04.2025 14:00Lecture room 8, Faculty of Mathematics and Physics, Malostranské náměstí 2

  • Andreas Opedal:

    Systematic Analysis of the Arithmetic Reasoning Capabilities of LLMs

    27.03.2025 14:00Lecture room 8, Faculty of Mathematics and Physics, Malostranské náměstí 2

    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.

Recent Talks

  • Antoni Kowalczuk:

    Image Autoregressive Models Leak More Training Data Than Diffusion Models

    13.03.2025 14:00Lecture room 8, Faculty of Mathematics and Physics, Malostranské náměstí 2

    Antoni will show that Image autoregressive models, which recently outperformed diffusion models on image generation, are significantly more prone to privacy attacks

  • Thomas Kleine Buening:

    Strategic Interactive Decision-Making

    27.02.2025 14:00Lecture room 8, Faculty of Mathematics and Physics, Malostranské náměstí 2

    Thomas will talk about the role of incentives in machine learning through reinforcement learning and mechanism design principles, highlighting works on contextual bandits with manipulated contexts and reinforcement learning from human feedback with strategic preferences