Adrians Skapars

According to our database, Adrians Skapars authored at least 8 papers between 2024 and 2026.

Collaborative distances:

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

2026

Do Linear Probes Generalize Better in Persona Coordinates?

Prasad Mahadik, Adrians Skapars

CoRR, May, 2026

2025

The Impact of Off-Policy Training Data on Probe Generalisation.

Nathalie Kirch, Samuel Dower, Adrians Skapars, Ekdeep Singh Lubana, Dmitrii Krasheninnikov

CoRR, November, 2025

GPT, But Backwards: Exactly Inverting Language Model Outputs.

Adrians Skapars, Edoardo Manino, Youcheng Sun, Lucas C. Cordeiro

CoRR, July, 2025

Worst-Case Symbolic Constraints Analysis and Generalisation with Large Language Models.

Daniel Koh, Yannic Noller, Corina S. Pasareanu, Adrians Skapars, Youcheng Sun

CoRR, June, 2025

SaFliTe: Fuzzing Autonomous Systems via Large Language Models.

Taohong Zhu, Adrians Skapars, Fardeen Mackenzie, Declan Kehoe, William Newton, Suzanne M. Embury, Youcheng Sun

Proceedings of the Towards Autonomous Robotic Systems - 26th Annual Conference, 2025

2024

Transformers Use Causal World Models in Maze-Solving Tasks.

Alex F. Spies, William Edwards, Michael I. Ivanitskiy, Adrians Skapars, Tilman Räuker, Katsumi Inoue, Alessandra Russo, Murray Shanahan

CoRR, 2024

Was it Slander? Towards Exact Inversion of Generative Language Models.

Adrians Skapars, Edoardo Manino, Youcheng Sun, Lucas C. Cordeiro

CoRR, 2024

Enriching the Metadata of Community-Generated Digital Content through Entity Linking: An Evaluative Comparison of State-of-the-Art Models.

Youcef Benkhedda, Adrians Skapars, Viktor Schlegel, Goran Nenadic, Riza Batista-Navarro

Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, 2024