Login / Signup
Jan Wehner
Publication Activity (10 Years)
Years Active: 2012-2024
Publications (10 Years): 5
Top Topics
Trajectory Data
Reward Function
Security Flaws
Fine Tune
Top Venues
CoRR
J. Heuristics
ICTAI
</>
Publications
</>
Domenic Rosati
,
Jan Wehner
,
Kai Williams
,
Lukasz Bartoszcze
,
David Atanasov
,
Robie Gonzales
,
Subhabrata Majumdar
,
Carsten Maple
,
Hassan Sajjad
,
Frank Rudzicz
Representation noising effectively prevents harmful fine-tuning on LLMs.
CoRR
(2024)
Jan Wehner
,
Frans A. Oliehoek
,
Luciano Cavalcante Siebert
Explaining Learned Reward Functions with Counterfactual Trajectories.
CoRR
(2024)
Domenic Rosati
,
Jan Wehner
,
Kai Williams
,
Lukasz Bartoszcze
,
Jan Batzner
,
Hassan Sajjad
,
Frank Rudzicz
Immunization against harmful fine-tuning attacks.
CoRR
(2024)
Jan Wehner
,
Michael Sioutis
,
Diedrich Wolter
On robust vs fast solving of qualitative constraints.
J. Heuristics
29 (4-6) (2023)
Jan Wehner
,
Michael Sioutis
,
Diedrich Wolter
On Robust Vs Fast Solving of Qualitative Constraints.
ICTAI
(2021)
Rinat Mustafin
,
Jan Wehner
,
Wolfgang Sattler
,
Kristian Gohlke
T.F.O.: tangible flying objects.
Tangible and Embedded Interaction
(2012)