alphaFeedback
YI

Yasin Ibrahim

cs.LGcs.AIcs.CV3D brain MRIAnomaly detectionBraincs.CLcs.HCImage Interpretation, Computer-AssistedImaging, Three-Dimensional

On Valency

published · living versions
W_f7a8nd2h·v1 · currentpublished
Counterfactual Marginalisation: Framework for Evaluating Robustness to Nuisance Variables
with Hermione Warr, Robin J. Evans, Konstantinos Kamnitsas
1 version

Preprints & journals

10 papers in the corpus · 2024–2026
To do(xx) or not to do(xx): Medical Image Counterfactuals for Dataset Augmentation2609.14124v1 · Yasin Ibrahim, Robin J. Evans, Konstantinos Kamnitsas2026 · 0 citationsarXiv
Counterfactual Marginalisation: Framework for Evaluating Robustness to Nuisance Variables2609.10778v1 · Yasin Ibrahim, Hermione Warr, Robin J. Evans et al.2026 · 0 citationsarXivon Valency
Error Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models2608.30021v2 · Hermione Warr, Harry Anthony, Lilli J Freischem et al.2026 · 0 citationsarXiv
IterMask3D: Unsupervised anomaly detection and segmentation with test-time iterative mask refinement in 3D brain MRI.40945172 · Liang, Ziyun, Guo, Xiaoqing, Xu, Wentian et al.2025 · 3 citationsMedical image analysis. 2026;107(Pt A):103763
Specialised or Generic? Tokenization Choices for Radiology Language Models2508.09952v1 · Hermione Warr, Wentian Xu, Harry Anthony et al.2025 · 0 citationsarXiv
Identity-Free Deferral For Unseen Experts2502.10533v3 · Joshua Strong, Pramit Saha, Yasin Ibrahim et al.2025 · 0 citationsarXiv
Quality Control for Radiology Report Generation Models via Auxiliary Auditing Components2407.21638v1 · Hermione Warr, Yasin Ibrahim, Daniel R. McGowan et al.2024 · 1 citationarXiv
Semi-Supervised Learning for Deep Causal Generative Models2403.18717v2 · Yasin Ibrahim, Hermione Warr, Konstantinos Kamnitsas2024 · 4 citationsarXiv
Career total: 10 works. 10 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.