activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

LaPrune: Controllable Differentiable Sparsity at Million Scale

Jakub Antczak, Joanna Wojciechowicz, Łukasz Struski +1

Top- selection determines which components of a sparse model remain active. Hard selection blocks gradients, while continuous relaxations often couple mask hardness to the selec…

cs.LG2026

SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs

Mikołaj Zasada, Łukasz 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…

cs.LG2026

LAPLEX: The FFT of Learnable Laplace Kernels

Łukasz 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…

cs.LG2025

FeNeC: Enhancing Continual Learning via Feature Clustering with Neighbor- or Logit-Based Classification

Kamil Książek, Hubert Jastrzębski, Bartosz Trojan +3

The ability of deep learning models to learn continuously is essential for adapting to new data categories and evolving data distributions. In recent years, approaches leveraging f…

cs.LG2025

SEMU: Singular Value Decomposition for Efficient Machine Unlearning

Marcin Sendera, Łukasz Struski, Kamil Książek +3

While the capabilities of generative foundational models have advanced rapidly in recent years, methods to prevent harmful and unsafe behaviors remain underdeveloped. Among the pre…