Sotabase

Career

· Research Scientist, AI Security Institute

Publications (111)

Understanding the Effects of RLHF on LLM Generalisation and Diversity
International Conference on Learning Representations · 2023
281
cited
A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
Journal of Artificial Intelligence Research · 2021
227
cited
A Survey of Generalisation in Deep Reinforcement Learning
arXiv.org · 2021
191
cited
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
NeurIPS Datasets and Benchmarks · 2021
105
cited
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
arXiv.org · 2023
96
cited
An Epidemic of Yellow Fever In the Nuba Mountains, Anglo-Egyptian Sudan.
1941
52
cited
Studies in leishmaniasis in the Anglo-Egyptian Sudan
1940
42
cited
Open Problems in Machine Unlearning for AI Safety
arXiv.org · 2025
41
cited
Generalization to New Sequential Decision Making Tasks with In-Context Learning
International Conference on Machine Learning · 2023
37
cited
Studies in leishmaniasis in the Anglo-Egyptian Sudan. XI. Phlebotomus in relation to leishmaniasis in the Sudan.
Transactions of the Royal Society of Tropical Medicine and Hygiene · 1955
37
cited
Studies in leishmaniasis in the Anglo-Egyptian Sudan. II.—The skin and lymph glands in kala-azar
1940
35
cited
Studies in Leishmaniasis in the Anglo-Egyptian Sudan. V.-Cutaneous and Mucocutaneous Leishmaniasis.
1942
35
cited
Genes and people in the Caspian Littoral: a population genetic study in Northern Iran.
American Journal of Physical Anthropology · 1977
34
cited
Preliminary notes on dermal leishmaniasis in the Anglo-Egyptian Sudan
1938
27
cited
Studies in leishmaniasis in the Anglo-Egyptian Sudan. Part I.—Epidemiology and general considerations
1939
27
cited
How Do Large Language Monkeys Get Their Power (Laws)?
International Conference on Machine Learning · 2025
26
cited
Notes on the Phlebotominae of the Anglo-Egyptian Sudan.
Annals of Tropical Medicine and Parasitology · 1954
26
cited
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
arXiv.org · 2024
26
cited
Studies in leishmaniasis in the Anglo-Egyptian Sudan; further observations on the sandflies (Phlebotomus) of the Sudan.
Transactions of the Royal Society of Tropical Medicine and Hygiene · 1947
25
cited
The Use of Certain Aromatic Diamidines in the Treatment of Kala-Azar
1940
24
cited
Sotabase
Robert Kirk | Researcher Profile | Sotabase | Sotabase