You are not logged in | Log in
Return to the list of seminars

Seminarium "Machine Learning"


List of talks

  • June 22, 2023, 12:15 p.m.
    Jakub Świątkowski (Uniwersytet Warszawski, Amazon)
    Cross-lingual Prosody Transfer for Expressive Machine Dubbing
    In this seminar, I will present our two papers on cross-lingual prosody transfer for machine dubbing accepted to INTERSPEECH 2023. Prosody transfer is well-studied in the context of expressive speech synthesis. Cross-lingual prosody transfer, however, is …

  • June 15, 2023, 12:15 p.m.
    Gracjan Góral (Uniwersytet Warszawski)
    Error), and Permutation Challenge
    The seminar will be devoted to the role of language models in question-answering tests and highlights recent advancements in the field. We delve into the challenge faced by these models – their struggle with question …

  • June 1, 2023, 12:15 p.m.
    Konrad Staniszewski (Uniwersytet Warszawski)
    Retrieval Augmented Language Models
    Large language models store their knowledge in parameters and require costly fine-tuning to update. An interesting alternative is to provide new knowledge in the model's context. However, typical models have relatively short context lengths. In …

  • May 25, 2023, 12:15 p.m.
    Mateusz Olko (Uniwersytet Warszawski)
    Causal Machine Learning: Introduction
    Causality has the potential to transform the way we solve a large number of real-world problems. This mathematical theory, introduced by Judea Pearl, has recently paved its way into the deep learning community. In my …

  • May 18, 2023, 12:15 p.m.
    Dominik Filipiak
    Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding
    We present Polite Teacher, a simple yet effective method for the task of semi-supervised instance segmentation. The proposed architecture relies on the Teacher-Student mutual learning framework. To filter out noisy pseudo-labels, we use confidence thresholding …

  • April 20, 2023, 12:15 p.m.
    Hubert Baniecki (Uniwersytet Warszawski)
    Segment Anything
    Hubert will talk about a very recent paper that has impressive instance segmentation results.

  • April 13, 2023, 12:15 p.m.
    Mohammad Saqib (Uniwersytet Warszawski)
    Protein secondary structure assignments using ML
    Researchers seek to understand computer-generated protein models by identifying their structural components. Categorizing amino acid residues as Helix, Strand, or Coil types is the process used for this identification. This categorization can be challenging if …

  • March 30, 2023, 12:15 p.m.
    Michał Zawalski
    Reinforcement learning with latent representations
     When working with complex high-dimensional objects, it is usually beneficial to translate them into compact low-dimensional forms. In my talk, I will discuss some successful approaches that learn meaningful representations for efficient reinforcement learning.  

  • Jan. 19, 2023, 12:15 p.m.
    Michal Nauman (Uniwersytet Warszawski)
    All-Action Policy Gradients
    In this talk, we will discuss policy gradients with many action samples. We will investigate decompositions of policy gradient variance, as well as measure the variance reduction effect stemming form increasing the number of state …

  • Dec. 8, 2022, 12:15 p.m.
    Spyros Mouselinos (Uniwersytet Warszawski)
    A Simple, Yet Effective Approach to Finding Biases in Code Generation
    Recently, scores of high-performing code generation systems have surfaced. As has become a popular choice in many domains, code generation is often approached using large language models as a core, trained under the masked or …

  • Nov. 3, 2022, 12:15 p.m.
    Piotr Tempczyk (Uniwersytet Warszawski)
    One Simple Trick to Fix Your Bayesian Neural Network
    One of the most popular estimation methods in Bayesian neural networks (BNN) is mean-field variational inference (MFVI). In this work, we show that neural networks with ReLU activation function induce posteriors, that are hard to …

  • Oct. 27, 2022, 1:15 p.m.
    Patrik Reizinger (University of Tübingen)
    Embrace the Gap: VAEs Perform Independent Mechanism Analysis
    Variational autoencoders (VAEs) are a popular framework for modeling complex data distributions; they can be efficiently trained via variational inference by maximizing the evidence lower bound (ELBO), at the expense of a gap to the …

  • June 9, 2022, 12:15 p.m.
    Shadi Shafighi (Uniwersytet Warszawski)
    Tumoroscope: a probabilistic graphical model for mapping tumor clones in cancerous tissue
    Tumor cell populations are highly heterogeneous and form clones with different genotypes. Geographically distinct parts of the tumor have different genetic and phenotypic compositions. Elucidating tumor heterogeneity is hampered by the fact that there is no technology available that would …

  • June 2, 2022, 12:15 p.m.
    Sebastian Jaszczur (Uniwerystet Warszawski)
    Conditional Computation in Transformers
    Note: seminar will be in person with a follow-up lunch.   Transformer architecture is widely used in Natural Language Processing to get state of the art results. Unfortunately, such model quality is usually only possible …

  • May 26, 2022, 12:15 p.m.
    Nabil Kahouadji (Northeastern Illinois University)
    Chicago structural violence and its effects on predicting colorectal adenoma in patients receiving colonoscopy
    In our retrospective study, we evaluate associations between neighborhood-level indicators of structural violence and colorectal adenoma using University of  Illinois Health electronic medical record (EMR) data obtained from patients receiving screening colonoscopy between the year …