15 papers
What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks
Magdalena TrÄdowicz, Åukasz Struski, Arkadiusz Lewicki +4
Saliency maps are most useful when they identify the image regions that are sufficient to preserve a model's behaviour. We introduce SEAMS, a sufficiency-based saliency method that…
SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs
MikoÅaj Zasada, Åukasz Struski, Jacek Tabor +1
Sparse Mixture-of-Experts (MoE) architectures enable scaling LLM parameters under a fixed inference budget by activating only a small subset of experts via top- routing. While t…
LAPLEX: The FFT of Learnable Laplace Kernels
Åukasz Struski, Hanna Blazhko, Piotr Kubaty +1
Fast linear algebra in deep learning usually comes with a choice: fixed geometry and exact computation, as in the Fourier transform, or adaptive geometry paid for by dense paramete…
Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models
Piotr Kubaty, Patryk MarszaÅek, Åukasz 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…
ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
Piotr Borycki, Magdalena TrÄdowicz, 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, PrzemysÅaw 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…