16 citations · 21 across the 21 of their papers we have counts for
24 papers
ClasSAE: Class-Aligned Sparse Autoencoders via Differentiable Feature-Class Affinity
Jakub Stępień, Marcin Mazur, Jacek Tabor +1
Sparse Autoencoders (SAEs) began as an unsupervised tool for decomposing neural representations into sparse, interpretable features, and are increasingly used not only for passive…
Prof-K: Probabilistic One-Pass Filtering for Efficient Top-k Selection
Tadeusz Dziarmaga, Witold Sikora, Łukasz Struski +2
Top-k selection is a fundamental computational primitive with applications spanning databases, information retrieval, signal processing, and modern machine learning workloads, incl…
Floating Radiance Networks
Krzysztof Byrski, Rafał Tobiasz, Grzegorz Wilczyński +5
Recent advances in neural scene representations enable photorealistic novel-view synthesis, yet most methods remain tightly coupled to a single rendering paradigm, limiting their v…
ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
Piotr Borycki, Magdalena Trędowicz, Jacek Tabor +2
Ante-hoc interpretability methods based on prototypes provide highly accurate explanations by utilizing the intuitive "this looks like that" reasoning paradigm. On the other hand,…
Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning
Patryk Krukowski, Jacek Tabor, Przemysław Spurek +2
Data-free continual learning (DFCIL) relies on model inversion to synthesize pseudo-samples and mitigate catastrophic forgetting. However, existing inversion methods are fundamenta…
SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders
Jakub Stępień, Marcin Mazur, Jacek Tabor +1
Sparse Autoencoders (SAEs) have become an important tool in mechanistic interpretability, helping to analyze internal representations in both Large Language Models (LLMs) and Visio…
DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models
Alicja Polowczyk, Agnieszka Polowczyk, Piotr Borycki +3
Despite impressive results from recent text-to-image models like FLUX, visual and anatomical artifacts remain a significant hurdle for practical and professional use. Existing meth…
InTAct: Interval-based Task Activation Consolidation for Continual Learning
Patryk Krukowski, Jan Miksa, Piotr Helm +3
Continual learning is a fundamental challenge in artificial intelligence that requires networks to acquire new knowledge while preserving previously learned representations. Despit…
UnGuide: Learning to Forget with LoRA-Guided Diffusion Models
Agnieszka Polowczyk, Alicja Polowczyk, Dawid Malarz +4
Recent advances in large-scale text-to-image diffusion models have heightened concerns about their potential misuse, especially in generating harmful or misleading content. This un…
EPIC: Explanation of Pretrained Image Classification Networks via Prototype
Piotr Borycki, Magdalena Trędowicz, Szymon Janusz +4
Explainable AI (XAI) methods generally fall into two categories. Post-hoc approaches generate explanations for pre-trained models and are compatible with various neural network arc…
CEC-MMR: Cross-Entropy Clustering Approach to Multi-Modal Regression
Krzysztof Byrski, Jacek Tabor, Przemysław Spurek +1
In practical applications of regression analysis, it is not uncommon to encounter a multitude of values for each attribute. In such a situation, the univariate distribution, which…
Classifier-free Guidance with Adaptive Scaling
Dawid Malarz, Artur Kasymov, Maciej Zięba +2
Classifier-free guidance (CFG) is an essential mechanism in contemporary text-driven diffusion models. In practice, in controlling the impact of guidance we can see the trade-off b…
RaySplats: Ray Tracing based Gaussian Splatting
Krzysztof Byrski, Marcin Mazur, Jacek Tabor +4
3D Gaussian Splatting (3DGS) is a process that enables the direct creation of 3D objects from 2D images. This representation offers numerous advantages, including rapid training an…
FreSh: Frequency Shifting for Accelerated Neural Representation Learning
Adam Kania, Marko Mihajlovic, Sergey Prokudin +2
Implicit Neural Representations (INRs) have recently gained attention as a powerful approach for continuously representing signals such as images, videos, and 3D shapes using multi…
Make Interval Bound Propagation great again
Patryk Krukowski, Daniel Wilczak, Jacek Tabor +2
In various scenarios motivated by real life, such as medical data analysis, autonomous driving, and adversarial training, we are interested in robust deep networks. A network is ro…
GeoGuide: Geometric guidance of diffusion models
Mateusz Poleski, Jacek Tabor, Przemysław Spurek
Diffusion models are among the most effective methods for image generation. This is in particular because, unlike GANs, they can be easily conditioned during training to produce el…
PrAViC: Probabilistic Adaptation Framework for Real-Time Video Classification
Magdalena Trędowicz, Marcin Mazur, Szymon Janusz +3
Video processing is generally divided into two main categories: processing of the entire video, which typically yields optimal classification outcomes, and real-time processing, wh…
NegGS: Negative Gaussian Splatting
Artur Kasymov, Bartosz Czekaj, Marcin Mazur +2
One of the key advantages of 3D rendering is its ability to simulate intricate scenes accurately. One of the most widely used methods for this purpose is Gaussian Splatting, a nove…
ProPML: Probability Partial Multi-label Learning
Łukasz Struski, Adam Pardyl, Jacek Tabor +1
Partial Multi-label Learning (PML) is a type of weakly supervised learning where each training instance corresponds to a set of candidate labels, among which only some are true. In…
Deepfake for the Good: Generating Avatars through Face-Swapping with Implicit Deepfake Generation
Georgii Stanishevskii, Jakub Steczkiewicz, Tomasz Szczepanik +3
Numerous emerging deep-learning techniques have had a substantial impact on computer graphics. Among the most promising breakthroughs are the rise of Neural Radiance Fields (NeRFs)…
GaMeS: Mesh-Based Adapting and Modification of Gaussian Splatting
Joanna Waczyńska, Piotr Borycki, Sławomir Tadeja +2
Gaussian Splatting (GS) is a novel, state-of-the-art technique for rendering points in a 3D scene by approximating their contribution to image pixels through Gaussian distributions…
Gaussian Splatting with NeRF-based Color and Opacity
Dawid Malarz, Weronika Smolak, Jacek Tabor +2
Neural Radiance Fields (NeRFs) have demonstrated the remarkable potential of neural networks to capture the intricacies of 3D objects. By encoding the shape and color information w…
MeVGAN: GAN-based Plugin Model for Video Generation with Applications in Colonoscopy
Łukasz Struski, Tomasz Urbańczyk, Krzysztof Bucki +4
Video generation is important, especially in medicine, as much data is given in this form. However, video generation of high-resolution data is a very demanding task for generative…
Cramer-Wold AutoEncoder
Szymon Knop, Jacek Tabor, Przemysław Spurek +3
We propose a new generative model, Cramer-Wold Autoencoder (CWAE). Following WAE, we directly encourage normality of the latent space. Our paper uses also the recent idea from Slic…