Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Adrians Skapars
Observed name:
Skapars, Adrians
Institution:
University of Manchester
Observed institution:
University of Manchester
OpenAlex ID:
A5115705075
SaFliTe: Fuzzing Autonomous Systems via Large Language Models
2025
·
Taohong Zhu
, Adrians Skapars
, et al.
·
Lecture notes in computer science
·
3
PDF
Transformers Use Causal World Models in Maze-Solving Tasks
2024
·
Spies, Alex F.
, Edwards, William
, et al.
·
arXiv (Cornell University)
·
1
PDF
Was it Slander? Towards Exact Inversion of Generative Language Models
2024
·
Skapars, Adrians
, Manino, Edoardo
, et al.
·
arXiv (Cornell University)
·
1
PDF
BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
2026
·
Skapars, Adrians
, Manino, Edoardo
·
arXiv (Cornell University)
PDF
Probe Generalization as Subspace Selection for OOD Deception Detection
2026
·
Yoo, Daniel
, Skapars, Adrians
·
arXiv (Cornell University)
PDF
Do Linear Probes Generalize Better in Persona Coordinates?
2026
·
Mahadik, Prasad
, Skapars, Adrians
·
arXiv (Cornell University)
PDF
The Impact of Off-Policy Training Data on Probe Generalisation
2026
·
Adrians Skapars
, Nathalie Maria Kirch
, et al.
·
Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
The Impact of Off-Policy Training Data on Probe Generalisation
2025
·
Kirch, Nathalie
, Dower, Samuel
, et al.
·
arXiv (Cornell University)
PDF
GPT, But Backwards: Exactly Inverting Language Model Outputs
2025
·
Skapars, Adrians
, Manino, Edoardo
, et al.
·
arXiv (Cornell University)
PDF
Worst-Case Symbolic Constraints Analysis and Generalisation with Large Language Models
2025
·
Koh, Daniel
, Noller, Yannic
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
14
Citation count:
5
H-index:
1
I10-index:
Year
Topic
Type
