17 citations · 17 across the 11 of their papers we have counts for
6 papers · 1 filter
MEME: Multi-entity & Evolving Memory Evaluation
Seokwon Jung, Alexander Rubinstein, Arnas Uselis +2
LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. While prior benchmarks evaluate on…
Does Data Scaling Lead to Visual Compositional Generalization?
Arnas Uselis, Andrea Dittadi, Seong Joon Oh
Compositional understanding is crucial for human intelligence, yet it remains unclear whether contemporary vision models exhibit it. The dominant machine learning paradigm is built…
Intermediate Layer Classifiers for OOD generalization
Arnas Uselis, Seong Joon Oh
Deep classifiers are known to be sensitive to data distribution shifts, primarily due to their reliance on spurious correlations in training data. It has been suggested that these…
Efficient implementations of echo state network cross-validation
Mantas Lukoševičius, Arnas Uselis
Background/introduction: Cross-Validation (CV) is still uncommon in time series modeling. Echo State Networks (ESNs), as a prime example of Reservoir Computing (RC) models, are kno…
Localized convolutional neural networks for geospatial wind forecasting
Arnas Uselis, Mantas Lukoševičius, Lukas Stasytis
Convolutional Neural Networks (CNN) possess many positive qualities when it comes to spatial raster data. Translation invariance enables CNNs to detect features regardless of their…
Efficient Cross-Validation of Echo State Networks
Mantas Lukoševičius, Arnas Uselis
Echo State Networks (ESNs) are known for their fast and precise one-shot learning of time series. But they often need good hyper-parameter tuning for best performance. For this goo…