Lukas Aichberger

According to our database, Lukas Aichberger authored at least 12 papers between 2023 and 2026.

Collaborative distances:

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

2026

Unlocking the Working Memory of Large Language Models for Latent Reasoning.

Lukas Aichberger, Sepp Hochreiter

CoRR, May, 2026

Annotations Mitigate Post-Training Mode Collapse.

Jacob Mitchell Springer, Madhu Advani, Lukas Aichberger, Arwen Bradley, Eran Malach, Omid Saremi, Sinead Williamson, Preetum Nakkiran, Etai Littwin, Aditi Raghunathan

CoRR, May, 2026

Uncertainty Quantification for LLM Function-Calling.

Zihuiwen Ye, Lukas Aichberger, Michael Kirchhof, Sinead Williamson, Luca Zappella, Yarin Gal, Arno Blaas, Adam Golinski

CoRR, April, 2026

2025

It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents.

Karolina Korgul, Yushi Yang, Arkadiusz Drohomirecki, Piotr Blaszczyk, Will Howard, Lukas Aichberger, Chris Russell, Philip H. S. Torr, Adam Mahdi, Adel Bibi

CoRR, December, 2025

Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation.

Mykyta Ielanskyi, Kajetan Schweighofer, Lukas Aichberger, Sepp Hochreiter

CoRR, October, 2025

Attacking Multimodal OS Agents with Malicious Image Patches.

Lukas Aichberger, Alasdair Paren, Yarin Gal, Philip Torr, Adel Bibi

CoRR, March, 2025

On Information-Theoretic Measures of Predictive Uncertainty.

Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi, Sepp Hochreiter

Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2025

Improving Uncertainty Estimation through Semantically Diverse Language Generation.

Lukas Aichberger, Kajetan Schweighofer, Mykyta Ielanskyi, Sepp Hochreiter

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Rethinking Uncertainty Estimation in Natural Language Generation.

Lukas Aichberger, Kajetan Schweighofer, Sepp Hochreiter

CoRR, 2024

Semantically Diverse Language Generation for Uncertainty Estimation in Language Models.

Lukas Aichberger, Kajetan Schweighofer, Mykyta Ielanskyi, Sepp Hochreiter

CoRR, 2024

2023

Introducing an Improved Information-Theoretic Measure of Predictive Uncertainty.

Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi, Sepp Hochreiter

CoRR, 2023

Quantification of Uncertainty with Adversarial Models.

Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi, Günter Klambauer, Sepp Hochreiter

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023