3 papers
cs.LG2026
TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning
Dominik Żurek, Kamil Faber, Marcin Pietron +2
Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on previously learned tasks. This s…
cs.LG2026
Rethinking the Harmonic Loss via Non-Euclidean Distance Layers
Maxwell Miller-Golub, Collin Coil, Kamil Faber +4
Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded weight growth, and inefficiencie…
cs.LG2025
xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection
Kamil Faber, Marcin PietroÅ, Dominik Å»urek +1
The recently proposed xLSTM is a powerful model that leverages expressive multiplicative gating and residual connections, providing the temporal capacity needed for long-horizon fo…