7 papers
Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models
Sergi Masip, Alicja Dobrzeniecka, Jonathan Swinnen +4
Traditionally, continual learning has assumed access to labeled data, yet many real-world applications -- such as lifelong robotics -- require models to adapt continuously from unl…
Beyond Classification: Dynamic Adapter Routing for Continual Multimodal Retrieval
Alicja Dobrzeniecka, Filip Szatkowski, Sebastian Cygert +2
While retrieval is a core function of vision-language models, continually updating these models for retrieval tasks remains critically underexplored. Existing work often approaches…
ImmuVis: Hyperconvolutional Foundation Model for Imaging Mass Cytometry
Dawid Uchal, Marcin Możejko, Krzysztof Gogolewski +12
We present ImmuVis, a family of efficient foundation models for imaging mass cytometry (IMC), a high-throughput multiplex imaging technology that handles molecular marker measureme…
Artificial Authority: From Machine Minds to Political Alignments. An Experimental Analysis of Democratic and Autocratic Biases in Large-Language Models
Natalia Ożegalska-Åukasik, Szymon Åukasik
Political beliefs vary significantly across different countries, reflecting distinct historical, cultural, and institutional contexts. These ideologies, ranging from liberal democr…
PL-Guard: Benchmarking Language Model Safety for Polish
Aleksandra KrasnodÄbska, Karolina Seweryn, Szymon Åukasik +1
Despite increasing efforts to ensure the safety of large language models (LLMs), most existing safety assessments and moderation tools remain heavily biased toward English and othe…
Kolmogorov-Arnold networks for metal surface defect classification
Maciej Krzywda, Mariusz WermiÅski, Szymon Åukasik +1
This paper presents the application of Kolmogorov-Arnold Networks (KAN) in classifying metal surface defects. Specifically, steel surfaces are analyzed to detect defects such as cr…