Theo dõi
Jessica Rumbelow
Jessica Rumbelow
Tên khácJessica Cooper
Leap Laboratories
Email được xác minh tại leap-labs.com
Tiêu đề
Trích dẫn bởi
Trích dẫn bởi
Năm
Believe the HiPe: Hierarchical perturbation for fast, robust, and model-agnostic saliency mapping
J Cooper, O Arandjelović, DJ Harrison
Pattern Recognition 129, 108743, 2022
202022
SolidGoldMagikarp (plus, prompt generation)
J Rumbelow, M Watkins
https://www.lesswrong.com/posts/aPeJE8bSo6rAFoLqg/solidgoldmagikarp-plus …, 2023
142023
Understanding ancient coin images
J Cooper, O Arandjelović
Recent Advances in Big Data and Deep Learning: Proceedings of the INNS Big …, 2020
142020
Learning to describe: a new approach to computer vision based ancient coin analysis
J Cooper, O Arandjelović
Sci 2 (2), 27, 2020
132020
How good is the science that informs government policy? A lesson from the UK’s response to 2020 CoV-2 outbreak
J Cooper, N Dimitriou, O Arandjelovíc
Journal of Bioethical Inquiry 18 (4), 561-568, 2021
122021
Weakly supervised learning and interpretability for endometrial whole slide image diagnosis
M Mohammadi, J Cooper, O Arandelović, C Fell, D Morrison, S Syed, ...
Experimental Biology and Medicine 247 (22), 2025-2037, 2022
112022
SolidGoldMagikarp (plus, prompt generation). 2023
J Rumbelow, M Watkins
URL: https://www. alignmentforum. org/posts/aPeJE8bSo6rAFoLqg …, 2023
62023
Lymphocyte classification from hoechst stained slides with deep learning
J Cooper, IH Um, O Arandjelović, DJ Harrison
Cancers 14 (23), 5957, 2022
62022
Believe the hipe: Hierarchical perturbation for fast and robust explanation of black box models
J Cooper, O Arandjelovic, D Harrison
arXiv preprint arXiv:2103.05108, 2021
52021
Open Problems in Mechanistic Interpretability
L Sharkey, B Chughtai, J Batson, J Lindsey, J Wu, L Bushnaq, ...
arXiv preprint arXiv:2501.16496, 2025
32025
Model agnostic interpretability
J Rumbelow
The University of St Andrews, 2024
22024
The SaTML'24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability
S Casper, J Yun, J Baek, Y Jung, M Kim, K Kwon, S Park, H Moore, ...
arXiv preprint arXiv:2404.02949, 2024
22024
SolidGoldMagikarp III: Glitch token archaelogy
J Rumbelow, M Watkins
Accessed on April 11, 2023, 2023
22023
Hoechst is all you need: Lymphocyte classification with deep learning
J Cooper, IH Um, O Arandjelović, DJ Harrison
arXiv preprint arXiv:2107.04388, 2021
22021
Why did ChatGPT say that? Prompt engineering and more, with PIZZA.
J Rumbelow
2024
Prototype Generation: Robust Feature Visualisation for Data Independent Interpretability
A Tagade, J Rumbelow
arXiv preprint arXiv:2309.17144, 2023
2023
SolidGoldMagikarp II: technical details and more recent findings
M Watkins, J Rumbelow
https://www.lesswrong.com/posts/Ya9LzwEbfaAMY8ABo/solidgoldmagikarp-ii …, 2023
2023
Hệ thống không thể thực hiện thao tác ngay bây giờ. Hãy thử lại sau.
Bài viết 1–17