Arnas Uselis

According to our database, Arnas Uselis authored at least 12 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models.

Arnas Uselis, Andrea Dittadi, Seong Joon Oh

CoRR, February, 2026

Half-Truths Break Similarity-Based Retrieval.

Bora Kargi, Arnas Uselis, Seong Joon Oh

CoRR, February, 2026

2025

On the rankability of visual embeddings.

Ankit Sonthalia, Arnas Uselis, Seong Joon Oh

CoRR, July, 2025

Diffusion Classifiers Understand Compositionality, but Conditions Apply.

Yujin Jeong, Arnas Uselis, Seong Joon Oh, Anna Rohrbach

CoRR, May, 2025

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

Darina Koishigarina, Arnas Uselis, Seong Joon Oh

CoRR, February, 2025

Does Data Scaling Lead to Visual Compositional Generalization?

Arnas Uselis, Andrea Dittadi, Seong Joon Oh

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Intermediate Layer Classifiers for OOD generalization.

Arnas Uselis, Seong Joon Oh

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2023

Efficient Implementations of Echo State Network Cross-Validation.

Mantas Lukosevicius, Arnas Uselis

Cogn. Comput., September, 2023

2022

Time-Adaptive Recurrent Neural Networks.

Mantas Lukosevicius, Arnas Uselis

CoRR, 2022

2020

Security analysis of KAP based on enhanced MPF.

Eligijus Sakalauskas, Aleksejus Mihalkovich, Arnas Uselis

IET Inf. Secur., 2020

Localized convolutional neural networks for geospatial wind forecasting.

Arnas Uselis, Mantas Lukosevicius, Lukas Stasytis

CoRR, 2020

2019

Efficient Cross-Validation of Echo State Networks.

Mantas Lukosevicius, Arnas Uselis

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2019 - 28th International Conference on Artificial Neural Networks, Munich, Germany, September 17-19, 2019, Proceedings, 2019