activity
20242026
collaborators

11 papers

cs.LG2026

In-Context Density Estimation for Tabular Data

Patryk Marszałek, Jacek Tabor, Marek Śmieja

Density estimation underlies many unsupervised tasks on tabular data such as anomaly detection, out-of-distribution detection, and data augmentation. Although all these problems re…

cs.CV2026

Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models

Piotr Kubaty, Patryk Marszałek, Łukasz Struski +3

Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract interpretable features, they r…

cs.LG2026

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…

cs.LG2026

SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data

Kacper Jurek, Wojciech Batko, Marek Śmieja +3

Learning from scarce labeled data with a larger pool of unlabeled samples, known as semi-supervised few-shot learning (SS-FSL), remains critical for applications involving tabular…

cs.LG2025

ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data

Patryk Marszałek, Tomasz Kuśmierczyk, Witold Wydmański +2

Clustering tabular data remains a significant open challenge in data analysis and machine learning. Unlike for image data, similarity between tabular records often varies across da…

cs.CV2025

Beyond [cls]: Exploring the true potential of Masked Image Modeling representations

Marcin Przewięźlikowski, Randall Balestriero, Wojciech Jasiński +2

Masked Image Modeling (MIM) has emerged as a promising approach for Self-Supervised Learning (SSL) of visual representations. However, the out-of-the-box performance of MIMs is typ…