1 citations · 1 across the 4 of their papers we have counts for
8 papers
Fast LapSum: Exact Differentiable Top-k at Million Scale
Łukasz Struski, Joanna Wojciechowicz, Jakub Antczak +3
The top- operation is a fundamental building block of modern sparse computation, enabling token routing, expert activation, memory selection, and attention pruning. Yet standard…
Interpretability-Guided Soft Pruning of Attention Heads in Vision Transformers
Kamil KsiÄ Å¼ek, Piotr SuszyÅski, MichaÅ Jan WÅodarczyk +2
Vision foundation models, such as DINOv2, learn highly expressive representations but rely on massive, opaque architectures that demand substantial computational power and memory.…
SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense
Patryk Krukowski, Åukasz Gorczyca, Piotr Helm +2
Continual learning under adversarial conditions remains an open problem, as existing methods often compromise either robustness, scalability, or both. We propose a novel framework…
HyConEx: Hypernetwork classifier with counterfactual explanations for tabular data
Patryk MarszaÅek, Kamil KsiÄ Å¼ek, Oleksii Furman +3
In recent years, there has been a growing interest in explainable AI methods. In addition to making accurate predictions, we also want to understand what the model's decision is ba…
HINT: Hypernetwork Approach to Training Weight Interval Regions in Continual Learning
Patryk Krukowski, Anna Bielawska, Kamil KsiÄ Å¼ek +3
Recently, a new Continual Learning (CL) paradigm was presented to control catastrophic forgetting, called Interval Continual Learning (InterContiNet), which relies on enforcing int…
FeNeC: Enhancing Continual Learning via Feature Clustering with Neighbor- or Logit-Based Classification
Kamil KsiÄ Å¼ek, Hubert JastrzÄbski, 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…