arXiv AI August 6, 2026 By Siqi Li, Chuan Hong, Ziye Tian, Benjamin Sieu-Hon Leong, Koshi Nakagawa, Hideharu Tanaka, Sang Do Shin, Khuong Quoc Dai, Do Ngoc Son, Marcus Eng Hock Ong, Nan Liu, Molei Liu

Distributionally Robust Transfer Learning with Structurally Missing Covariates, with Application to Cross-National Cardiac Arrest Prediction

Read the original on arXiv AI →

arXiv:2605. 24212v2 Announce Type: replace-cross Abstract: Deploying clinical prediction models across healthcare systems often fails when key training covariates are unavailable at deployment and labeled outcomes are limited in the target domain.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 30

CalTwin: Towards Calibrated, Shift-Robust Medical World Models via Fisher-Information Regularisation

arXiv:2607. 26752v1 Announce Type: new Abstract: Medical world models aim to learn a latent state of patient or organ physiology and a transition function that forecasts how that state evolves under interventions, supporting downstream tasks from imaging-based diagnosis to digital-twin treatment planning.

By Behraj Khan, Shabir Ahmad, Syed Ahmad Chan Bukhari, Tahir Qasim Syed

multimodal

arXiv Machine Learning

1d ago

Inferential Evaluation of Surrogate-Derived Models under Covariate Shift

arXiv:2608. 15783v1 Announce Type: cross Abstract: In transfer-learning settings, a model derived from abundant surrogate labels may be deployed in a target population where gold-standard outcomes are unobserved.

By Longtian Shi, Molei Liu, Doudou Zhou

safety

arXiv AI

Jun 2

A Practical Upper Bound on Selection Bias Effects in Medical Prediction Models

arXiv:2606. 00563v1 Announce Type: cross Abstract: Selection bias is a common and often unavoidable aspect of real-world data that challenges the generalizability of machine learning models.

By Kara Liu, Maggie Wang, Russ B. Altman

safety

arXiv Machine Learning

Jun 15

Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias

arXiv:2606. 14506v1 Announce Type: cross Abstract: Understanding how a prediction model will perform in a new environment before deployment is essential to preventing harm when algorithms inform decision-making.

By Annie Ulichney, Amanda Coston

safety

arXiv Machine Learning

Jun 18

Anti-causal domain generalization: Leveraging unlabeled data

arXiv:2602. 17187v2 Announce Type: replace-cross Abstract: The problem of domain generalization concerns learning predictive models that are robust to distribution shifts when deployed in new, previously unseen environments.

By Sorawit Saengkyongam, Juan L. Gamella, Andrew C. Miller, Jonas Peters, Nicolai Meinshausen, Christina Heinze-Deml

arXiv Machine Learning

Aug 4

Learning the Pareto Frontier of Predictive Models under Distribution Shift

arXiv:2608. 00632v1 Announce Type: new Abstract: Modern machine learning pipelines increasingly rely on reusing pretrained and foundation models across downstream tasks.

By Yiming Dong, Jiwei Zhao, Yang Young Lu

fine-tuning

Related stories

CalTwin: Towards Calibrated, Shift-Robust Medical World Models via Fisher-Information Regularisation

Inferential Evaluation of Surrogate-Derived Models under Covariate Shift

A Practical Upper Bound on Selection Bias Effects in Medical Prediction Models

Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias

Anti-causal domain generalization: Leveraging unlabeled data

Learning the Pareto Frontier of Predictive Models under Distribution Shift