collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

PRISM: Powerful Time Series to Image (TS2I) Representations for Multivariate Anomaly Detection

Mateusz Smendowski, Kamil Faber, Piotr Nawrocki +2

Time series anomaly detection (TSAD) underpins applications in predictive maintenance, finance, and cloud computing, however performance remains sensitive to representation choices…

cs.LG2026

Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios

Kamil Faber, Mateusz Smendowski, Roberto Corizzo

Continual anomaly detection (CAD) studies how models can adapt to evolving data distributions while retaining performance on previously observed regimes. CAD benchmarks, however, d…

cs.LG2026

Correcting Performance Estimation Bias in Imbalanced Classification with Minority Subconcepts

Taylor Maxson, Roberto Corizzo, Yaning Wu +2

Class-level evaluation can conceal substantial performance disparities across subconcepts within the same class, causing models that perform well on average to fail on specific sub…

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.LG2025

xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection

Kamil Faber, Marcin Pietroń, Dominik Żurek +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…

cs.LG2025

TinySubNets: An efficient and low capacity continual learning strategy

Marcin Pietroń, Kamil Faber, Dominik Żurek +1

Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effe…