2023-06-22, 12:15, https://uw-edu-pl.zoom.us/j/92107522918
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 challenging and has been under-explor...
2023-06-15, 12:15, https://uw-edu-pl.zoom.us/j/92107522918
Gracjan Góral (Uniwersytet Warszawski)
Language Models in Question Answering Tests - Sematic, Syntax (Error), and Permutation Challenges
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 permutation, mainly focusing on the GPT-3 models. Moreover, the seminar explo...
2023-06-01, 12:15, https://uw-edu-pl.zoom.us/j/92107522918
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 this presentation, I will discuss one of the pote...
2023-05-25, 12:15, https://uw-edu-pl.zoom.us/j/92107522918
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 presentation, I will introduce and explain basic concepts from causality theory and...
2023-05-18, 12:15, https://uw-edu-pl.zoom.us/j/92107522918
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 for bounding boxes and mask scoring for...
2023-04-20, 12:15, https://uw-edu-pl.zoom.us/j/92107522918
Hubert Baniecki (Uniwersytet Warszawski)
Hubert will talk about a very recent paper that has impressive instance segmentation results. https://arxiv.org/abs/2304.02643 ...
2023-04-13, 12:15, https://uw-edu-pl.zoom.us/j/92107522918
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 certain atoms are missing or only alpha...
2023-03-30, 12:15, https://uw-edu-pl.zoom.us/j/92107522918
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. ...
2023-01-19, 12:15, 5050
Michal Nauman (Uniwersytet Warszawski)
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 and action samples used in estimation. Finally, we will compare vario...
2022-12-08, 12:15, https://uw-edu-pl.zoom.us/j/97528316706
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 causal language modeling schema. This work shows that current code gene...