1 code implementation • 4 Oct 2024 • Artur Kasymov, Marcin Sendera, Michał Stypułkowski, Maciej Zięba, Przemysław Spurek
To solve this issue, we introduce AutoLoRA, a novel guidance technique for diffusion models fine-tuned with the LoRA approach.
no code implementations • 27 May 2024 • Patryk Wielopolski, Oleksii Furman, Jerzy Stefanowski, Maciej Zięba
PPCEF advances beyond existing methods by combining a probabilistic formulation that leverages the data distribution with the optimization of plausibility within a unified framework.
no code implementations • 27 May 2024 • Patryk Wielopolski, Oleksii Furman, Jerzy Stefanowski, Maciej Zięba
By offering a cohesive solution to the optimization and plausibility challenges in GCEs, our work significantly advances the interpretability and accountability of AI models, marking a step forward in the pursuit of transparent AI.
1 code implementation • 10 Dec 2023 • Piotr Miłkowski, Konrad Karanowski, Patryk Wielopolski, Jan Kocoń, Przemysław Kazienko, Maciej Zięba
It may be solved by Personalized Natural Language Processing (PNLP), where the model exploits additional information about the reader to make more accurate predictions.
1 code implementation • 14 Oct 2023 • Wojciech Kozłowski, Michał Szachniewicz, Michał Stypułkowski, Maciej Zięba
To fill this gap, we propose Dimma, a semi-supervised approach that aligns with any camera by utilizing a small set of image pairs to replicate scenes captured under extreme lighting conditions taken by that specific camera.
1 code implementation • 13 Jul 2023 • Mateusz Baran, Joanna Baran, Mateusz Wójcik, Maciej Zięba, Adam Gonczarek
This highlights the need for future work to develop more effective OOD detection approaches for the NLP problems, and our work provides a well-defined foundation for further research in this area.
1 code implementation • 11 Jul 2023 • Michał Szachniewicz, Wojciech Kozłowski, Michał Stypułkowski, Maciej Zięba
We introduce PointCAM, a novel adversarial method for learning a masking function for point clouds.
1 code implementation • 17 May 2023 • Dominik Zimny, Artur Kasymov, Adam Kania, Jacek Tabor, Maciej Zięba, Przemysław Spurek
Furthermore, we can train MultiPlaneNeRF on a large data set and force our implicit decoder to generalize across many objects.
1 code implementation • 10 Mar 2023 • Wojciech Zając, Joanna Waczyńska, Piotr Borycki, Jacek Tabor, Maciej Zięba, Przemysław Spurek
In contrast to traditional NeRF-based structures that use neural networks for RGB color and volume density modeling, our approach utilizes the FLAME mesh as a distinct density volume.
1 code implementation • 27 Jan 2023 • Adam Kania, Artur Kasymov, Jakub Kościukiewicz, Artur Górak, Marcin Mazur, Maciej Zięba, Przemysław Spurek
The recent surge in popularity of deep generative models for 3D objects has highlighted the need for more efficient training methods, particularly given the difficulties associated with training with conventional 3D representations, such as voxels or point clouds.
no code implementations • 10 Jan 2023 • Dan Bigioi, Shubhajit Basak, Michał Stypułkowski, Maciej Zięba, Hugh Jordan, Rachel McDonnell, Peter Corcoran
Taking inspiration from recent developments in visual generative tasks using diffusion models, we propose a method for end-to-end speech-driven video editing using a denoising diffusion model.
no code implementations • 6 Jan 2023 • Michał Stypułkowski, Konstantinos Vougioukas, Sen He, Maciej Zięba, Stavros Petridis, Maja Pantic
Talking face generation has historically struggled to produce head movements and natural facial expressions without guidance from additional reference videos.
no code implementations • 8 Jun 2022 • Patryk Wielopolski, Maciej Zięba
The tree-based ensembles are known for their outstanding performance in classification and regression problems characterized by feature vectors represented by mixed-type variables from various ranges and domains.
no code implementations • 16 May 2022 • Maciej Zamorski, Michał Stypułkowski, Konrad Karanowski, Tomasz Trzciński, Maciej Zięba
By using rehearsal and reconstruction as regularization methods of the learning process, our approach achieves a significant decrease of catastrophic forgetting compared to the existing solutions on several most popular point cloud datasets considering two continual learning settings: when a task is known beforehand, and in the challenging scenario of when task information is unknown to the model.
1 code implementation • 21 Mar 2022 • Marcin Sendera, Marcin Przewięźlikowski, Konrad Karanowski, Maciej Zięba, Jacek Tabor, Przemysław Spurek
Few-shot models aim at making predictions using a minimal number of labeled examples from a given task.
1 code implementation • NeurIPS 2021 • Marcin Sendera, Jacek Tabor, Aleksandra Nowak, Andrzej Bedychaj, Massimiliano Patacchiola, Tomasz Trzciński, Przemysław Spurek, Maciej Zięba
This makes the GP posterior locally non-Gaussian, therefore we name our method Non-Gaussian Gaussian Processes (NGGPs).
1 code implementation • 7 Oct 2021 • Patryk Wielopolski, Michał Koperski, Maciej Zięba
Generative models have gained many researchers' attention in the last years resulting in models such as StyleGAN for human face generation or PointFlow for the 3D point cloud generation.
1 code implementation • 18 Sep 2021 • Maciej Wołczyk, Magdalena Proszewska, Łukasz Maziarka, Maciej Zięba, Patryk Wielopolski, Rafał Kurczab, Marek Śmieja
Modern generative models achieve excellent quality in a variety of tasks including image or text generation and chemical molecule modeling.
1 code implementation • 11 Feb 2021 • Przemysław Spurek, Sebastian Winczowski, Maciej Zięba, Tomasz Trzciński, Kacper Kania, Marcin Mazur
This way, we can sample a mesh quad on that sphere and project it back onto the object's manifold.
no code implementations • 30 Nov 2020 • Maciej Zięba, Marcin Przewięźlikowski, Marek Śmieja, Jacek Tabor, Tomasz Trzcinski, Przemysław Spurek
Predicting future states or actions of a given system remains a fundamental, yet unsolved challenge of intelligence, especially in the scope of complex and non-deterministic scenarios, such as modeling behavior of humans.
1 code implementation • 7 Oct 2020 • Michał Stypułkowski, Kacper Kania, Maciej Zamorski, Maciej Zięba, Tomasz Trzciński, Jan Chorowski
To exploit similarities between same-class objects and to improve model performance, we turn to weight sharing: networks that model densities of points belonging to objects in the same family share all parameters with the exception of a small, object-specific embedding vector.
1 code implementation • 16 Jun 2020 • Kacper Kania, Maciej Zięba, Tomasz Kajdanowicz
On the contrary, we propose a model that extracts a CSG parse tree without any supervision - UCSG-Net.
1 code implementation • 15 Jun 2020 • Przemysław Spurek, Maciej Zięba, Jacek Tabor, Tomasz Trzciński
To that end, we devise a generative model that uses a hypernetwork to return the weights of a Continuous Normalizing Flows (CNF) target network.
2 code implementations • ICML 2020 • Przemysław Spurek, Sebastian Winczowski, Jacek Tabor, Maciej Zamorski, Maciej Zięba, Tomasz Trzciński
The main idea of our HyperCloud method is to build a hyper network that returns weights of a particular neural network (target network) trained to map points from a uniform unit ball distribution into a 3D shape.
2 code implementations • 16 Oct 2019 • Michał Stypułkowski, Maciej Zamorski, Maciej Zięba, Jan Chorowski
This paper focuses on a novel generative approach for 3D point clouds that makes use of invertible flow-based models.
no code implementations • 16 Mar 2019 • Maciej Zamorski, Adrian Zdobylak, Maciej Zięba, Jerzy Świątek
In traditional generative modeling, good data representation is very often a base for a good machine learning model.
no code implementations • 28 Nov 2018 • Maciej Zamorski, Maciej Zięba
In this work we introduce a novel approach to train Bidirectional Generative Adversarial Model (BiGAN) in a semi-supervised manner.
4 code implementations • 19 Nov 2018 • Maciej Zamorski, Maciej Zięba, Piotr Klukowski, Rafał Nowak, Karol Kurach, Wojciech Stokowiec, Tomasz Trzciński
Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds.