Visual perturbations decouple actions from identical rationales in VLAs
Alpamayo and InstructVLA show TNAS steering shifts actions 4.64x-47.8x more than text perturbations while preserving rationales.
Stories per day · 30 days
Relatedapache1apache-cocoon1clinical-ai1command-injection1healthcare1information-disclosure1legrand1mai-dxo1microsoft1pdu1raritan1steering1vla1vlm1
6 stories, newest first · one card per story
Stories tagged #diagnostics
Raritan PX3 PDU 4.3.14 diagnostics allow command injection
A low-privilege authenticated diagnostics request can run OS commands in the web-service context.
Microsoft says MAI-DxO beat generalist doctors on hard cases
In a simulation of complex NEJM cases, MAI-DxO was correct 83% of the time versus 36% for generalists.
Apache Cocoon diagnostic interfaces exposed without login (CVE-2026-108089)
Every Cocoon version lets an unauthenticated user trigger caches and read verbose debug and profile data.
DiaVLo: Diagnosing Behaviours of Vision-Language Models
DiaVLo diagnoses vision-language model behaviours, comparing desired and observed actions and estimating influential concepts.
Performance of Clinical AI System and Physicians and Frontier Language Models in primary care diagnostics
Clinical AI system Doctorina achieved 82.0% primary-care diagnostic concordance versus 57.0% for physicians across 150 synthetic consultations.