Following this puts new work involving it at the top of your briefing, with a note saying why it is there. Links are taken from the source record, never inferred.
This is a methods paper proposing a novel data poisoning technique for amplifying membership inference attacks on vision-language models; it presents a computational approach without clinical, patient, or real-world health outcomes.
This is an unrefereed preprint describing a novel computational method for LLM safety assessment; it has not undergone peer review and the claims rest on algorithmic performance metrics rather than clinical or validated real-world outcomes.
A methodological paper proposing a novel training framework for LRM safety with empirical results on synthetic jailbreak robustness, but lacking peer review, clinical or real-world validation, and independent confirmation.