Filip Szatkowski
5 papers · 2024–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🌍
Conference Polyglot
(3)
🐝
Cross-Pollinator
(9)
🗺️
Taxonomy Completionist
(17)
Conferences
ICML (2)
WACV (2)
NIPS (1)
Top co-authors
Keywords
continual learning
(2)
representation learning
(1)
catastrophic forgetting
(1)
knowledge distillation
(1)
classification head
(1)
mixture of expert
(1)
inference efficiency
(1)
activation sparsity
(1)
inference cost
(1)
dynamic expert selection
(1)
class incremental learning
(1)
representation shift
(1)
teacher adaptation
(1)
transformer model
(1)
model compression
(1)
stability gap
(1)
Papers
Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers
ICML 2025
Exploring the Stability Gap in Continual Learning: The Role of the Classification Head
WACV 2025
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
NIPS 2024
Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal Initialization
ICML 2024
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-Free Continual Learning
WACV 2024