Search Results for author: Arnas Uselis

Found 6 papers, 6 papers with code

Diffusion Classifiers Understand Compositionality, but Conditions Apply

1 code implementation23 May 2025 Yujin Jeong, Arnas Uselis, Seong Joon Oh, Anna Rohrbach

To address this, we present a comprehensive study of the discriminative capabilities of diffusion classifiers on a wide range of compositional tasks.

Diagnostic

CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally

1 code implementation5 Feb 2025 Darina Koishigarina, Arnas Uselis, Seong Joon Oh

We find that the correct attribute-object binding information is already present in individual text and image modalities.

Attribute cross-modal alignment

Task-Synchronized Recurrent Neural Networks

1 code implementation11 Apr 2022 Mantas Lukoševičius, Arnas Uselis

We propose an elegant straightforward alternative approach where instead the RNN is in effect resampled in time to match the time of the data or the task at hand.

Efficient implementations of echo state network cross-validation

1 code implementation19 Jun 2020 Mantas Lukoševičius, Arnas Uselis

The second level of optimization also makes the (ii) part remain constant irrespective of large $k$, as long as the dimension of the output is low.

One-Shot Learning Time Series +1

Localized convolutional neural networks for geospatial wind forecasting

1 code implementation12 May 2020 Arnas Uselis, Mantas Lukoševičius, Lukas Stasytis

They can be added to any convolutional layers, easily end-to-end trained, introduce minimal additional complexity, and let CNNs retain most of their benefits to the extent that they are needed.

Translation

Efficient Cross-Validation of Echo State Networks

1 code implementation22 Aug 2019 Mantas Lukoševičius, Arnas Uselis

Thus in many situations $k$-fold cross-validation of ESNs can be done for virtually the same time complexity as a simple single split validation.

One-Shot Learning Time Series +1

Cannot find the paper you are looking for? You can Submit a new open access paper.