Follow
Victoria Krakovna
Victoria Krakovna
Other namesViktoriya Krakovna
Senior Research Scientist at DeepMind
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
Gemini: a family of highly capable multimodal models
G Team, R Anil, S Borgeaud, Y Wu, JB Alayrac, J Yu, R Soricut, ...
arXiv preprint arXiv:2312.11805, 2023
9682023
AI safety gridworlds
J Leike, M Martic, V Krakovna, PA Ortega, T Everitt, A Lefrancq, L Orseau, ...
arXiv preprint arXiv:1711.09883, 2017
3332017
Reinforcement Learning with a Corrupted Reward Channel
T Everitt, V Krakovna, L Orseau, M Hutter, S Legg
IJCAI AI & Autonomy, 2017
1252017
Specification gaming: the flip side of AI ingenuity
V Krakovna, J Uesato, V Mikulik, M Rahtz, T Everitt, R Kumar, Z Kenton, ...
https://deepmind.com/blog/article/Specification-gaming-the-flip-side-of-AI …, 2020
108*2020
Reward tampering problems and solutions in reinforcement learning: A causal influence diagram perspective
T Everitt, M Hutter, R Kumar, V Krakovna
Synthese 198 (Suppl 27), 6435-6467, 2021
922021
Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models
V Krakovna, F Doshi-Velez
ICML Workshop on Human Interpretability (WHI 2016), arXiv preprint arXiv …, 2016
862016
Penalizing side effects using stepwise relative reachability
V Krakovna, L Orseau, R Kumar, M Martic, S Legg
arXiv preprint arXiv:1806.01186, 2018
602018
Avoiding Side Effects By Considering Future Tasks
V Krakovna, L Orseau, R Ngo, M Martic, S Legg
NeurIPS 2020, arXiv preprint arXiv:2010.07877, 2020
462020
Goal misgeneralization: Why correct specifications aren't enough for correct goals
R Shah, V Varma, R Kumar, M Phuong, V Krakovna, J Uesato, Z Kenton
arXiv preprint arXiv:2210.01790, 2022
452022
Specification gaming examples in AI
V Krakovna
tinyurl.com/specification-gaming, 2018
42*2018
Modeling AGI safety frameworks with causal influence diagrams
T Everitt, R Kumar, V Krakovna, S Legg
arXiv preprint arXiv:1906.08663, 2019
242019
Measuring and avoiding side effects using relative reachability
V Krakovna, L Orseau, M Martic, S Legg
arXiv preprint arXiv:1806.01186, 2018
202018
Evaluating Frontier Models for Dangerous Capabilities
M Phuong, M Aitchison, E Catt, S Cogan, A Kaskasoli, V Krakovna, ...
arXiv preprint arXiv:2403.13793, 0
15*
REALab: An embedded perspective on tampering
R Kumar, J Uesato, R Ngo, T Everitt, V Krakovna, S Legg
arXiv preprint arXiv:2011.08820, 2020
132020
Power-seeking can be probable and predictive for trained agents
V Krakovna, J Kramar
arXiv preprint arXiv:2304.06528, 2023
11*2023
Memory-bounded left-corner unsupervised grammar induction on child-directed input
C Shain, W Bryce, L Jin, V Krakovna, F Doshi-Velez, T Miller, W Schuler, ...
Proceedings of COLING 2016, the 26th International Conference on …, 2016
10*2016
Avoiding tampering incentives in deep RL via decoupled approval
J Uesato, R Kumar, V Krakovna, T Everitt, R Ngo, S Legg
arXiv preprint arXiv:2011.08827, 2020
82020
The ethics of advanced ai assistants
I Gabriel, A Manzini, G Keeling, LA Hendricks, V Rieser, H Iqbal, ...
arXiv preprint arXiv:2404.16244, 2024
72024
Interpretable selection and visualization of features and interactions using bayesian forests
V Krakovna, J Du, JS Liu
Statistics and its Interface 2018 (Volume 11 Number 3), arXiv preprint arXiv …, 2015
6*2015
A generalized-zero-preserving method for compact encoding of concept lattices
M Skala, V Krakovna, J Kramár, G Penn
Proceedings of the 48th annual meeting of the Association for Computational …, 2010
62010
The system can't perform the operation now. Try again later.
Articles 1–20