John Burden

John Burden

University of Cambridge

H-index: 6

Europe-United Kingdom

About John Burden

John Burden, With an exceptional h-index of 6 and a recent h-index of 6 (since 2020), a distinguished researcher at University of Cambridge, specializes in the field of Reinforcement Learning, Artificial Intelligence, Long-term AI Safety, AI Evaluation.

His recent articles reflect a diverse array of research interests and contributions to the field:

Your Prompt Is My Command: On Assessing the Human-Centred Generality of Multimodal Models (Abstract Reprint)

Animal-AI 3: What's New & Why You Should Care

An International Consortium for Evaluations of Societal-Scale Risks from Advanced AI

Predictable Artificial Intelligence

Inferring Capabilities from Task Performance with Bayesian Triangulation

9. From Turing’s Speculations to an Academic Discipline: A History of AI Existential Safety

Harms from increasingly agentic algorithmic systems

Rethink reporting of evaluation results in AI

John Burden Information

University

Position

___

Citations(all)

613

Citations(since 2020)

612

Cited By

8

hIndex(all)

6

hIndex(since 2020)

6

i10Index(all)

6

i10Index(since 2020)

6

Email

University Profile Page

Google Scholar

John Burden Skills & Research Interests

Reinforcement Learning

Artificial Intelligence

Long-term AI Safety

AI Evaluation

Top articles of John Burden

Your Prompt Is My Command: On Assessing the Human-Centred Generality of Multimodal Models (Abstract Reprint)

Journal of Artificial Intelligence Research

2023/6/12

Animal-AI 3: What's New & Why You Should Care

arXiv preprint arXiv:2312.11414

2023/12/18

An International Consortium for Evaluations of Societal-Scale Risks from Advanced AI

arXiv preprint arXiv:2310.14455

2023/10/22

Predictable Artificial Intelligence

arXiv preprint arXiv:2310.06167

2023/10/9

Inferring Capabilities from Task Performance with Bayesian Triangulation

arXiv preprint arXiv:2309.11975

2023/9/21

9. From Turing’s Speculations to an Academic Discipline: A History of AI Existential Safety

2023/8/23

Harms from increasingly agentic algorithmic systems

2023/6/12

Rethink reporting of evaluation results in AI

Science

2023/4/14

Beyond the imitation game: Quantifying and extrapolating the capabilities of language models

arXiv preprint arXiv:2206.04615

2022/6/9

Not a Number: Identifying Instance Features for Capability-Oriented Evaluation

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22

2022

Oases of Cooperation: An Empirical Evaluation of Reinforcement Learning in the Iterated Prisoner's Dilemma.

2022

John Burden
John Burden

H-Index: 2

How Sure to Be Safe? Difficulty, Confidence and Negative Side Effects

2022/11/18

John Burden
John Burden

H-Index: 2

Evaluating object permanence in embodied agents using the animal-AI environment

https://ceur-ws. org/Vol-3169/paper2. pdf

2022/7/25

How general-purpose is a language model? Usefulness and safety with human prompters in the wild

Proceedings of the AAAI Conference on Artificial Intelligence

2022/6/28

Safety-driven design of machine learning for sepsis treatment

Journal of Biomedical Informatics

2021/5/1

Yan Jia
Yan Jia

H-Index: 5

John Burden
John Burden

H-Index: 2

Latent Property State Abstraction For Reinforcement learning

Proceedings of the AAMAS Workshop on Adaptive Learning Agents (ALA)

2021

John Burden
John Burden

H-Index: 2

Safe reinforcement learning for sepsis treatment

2020/11/30

Yan Jia
Yan Jia

H-Index: 5

John Burden
John Burden

H-Index: 2

Uniform state abstraction for reinforcement learning

arXiv preprint arXiv:2004.02919

2020/4/6

John Burden
John Burden

H-Index: 2

Exploring ai safety in degrees: Generality, capability and control

Proceedings of the Workshop on Artificial Intelligence Safety (SafeAI 2020) co-located with 34th AAAI Conference on Artificial Intelligence (AAAI 2020)

2020/2/7

Automating abstraction for potential-based reward shaping

2020

John Burden
John Burden

H-Index: 2

See List of Professors in John Burden University(University of Cambridge)

Co-Authors

academic-engine