Jakub Hoscilowicz

According to our database, Jakub Hoscilowicz authored at least 12 papers between 2023 and 2026.

Collaborative distances:

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

2026

Steerability of Instrumental-Convergence Tendencies in LLMs.

Jakub Hoscilowicz

CoRR, January, 2026

Adversarial Confusion Attack: Disrupting Multimodal Large Language Models.

Jakub Hoscilowicz, Artur Janicki

Proceedings of the 34th European Symposium on Artificial Neural Networks, 2026

2025

ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents.

Jakub Hoscilowicz, Artur Janicki

Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2025

Large Language Models as Carriers of Hidden Messages.

Jakub Hoscilowicz, Pawel Popiolek, Jan Rudkowski, Jedrzej Bieniasz, Artur Janicki

Proceedings of the 22nd International Conference on Security and Cryptography, 2025

TinyClick: Single-Turn Agent for Empowering GUI Automation.

Pawel Pawlowski, Krystian Zawistowski, Wojciech Lapacz, Adam Wiacek, Marcin Skorupa, Sebastien Postansque, Jakub Hoscilowicz

Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025

2024

ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents.

Jakub Hoscilowicz, Bartosz Maj, Bartosz Kozakiewicz, Oleksii Tymoshchuk, Artur Janicki

CoRR, 2024

Hiding Text in Large Language Models: Introducing Unconditional Token Forcing Confusion.

Jakub Hoscilowicz, Pawel Popiolek, Jan Rudkowski, Jedrzej Bieniasz, Artur Janicki

CoRR, 2024

Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages.

Jakub Hoscilowicz, Pawel Pawlowski, Marcin Skorupa, Marcin Sowanski, Artur Janicki

CoRR, 2024

NL-ITI: Optimizing Probing and Intervention for Improvement of ITI Method.

Jakub Hoscilowicz, Adam Wiacek, Jan Chojnacki, Adam Cieslak, Leszek Michon, Vitalii Urbanevych, Artur Janicki

CoRR, 2024

Non-Linear Inference Time Intervention: Improving LLM Truthfulness.

Jakub Hoscilowicz, Adam Wiacek, Jan Chojnacki, Adam Cieslak, Leszek Michon, Artur Janicki

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Unconditional Token Forcing: Extracting Text Hidden Within LLM.

Jakub Hoscilowicz, Pawel Popiolek, Jan Rudkowski, Jedrzej Bieniasz, Artur Janicki

Proceedings of the 19th Conference on Computer Science and Intelligence Systems, 2024

2023

Can We Use Probing to Better Understand Fine-Tuning and Knowledge Distillation of the BERT NLU?

Jakub Hoscilowicz, Marcin Sowanski, Piotr Czubowski, Artur Janicki

Proceedings of the 15th International Conference on Agents and Artificial Intelligence, 2023