16 citations · 21 across the 21 of their papers we have counts for
7 papers · 1 filter
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…