Research
Microsoft Research Unveils CARE-X for Radiology VLMs
Microsoft Researchhigh confidence
Why it matters
- →CARE-X addresses the need for both generative and structured outputs in radiology AI systems.
- →The model's reinforcement learning approach enhances clinical correctness, crucial for real-world applications.
- →CARE-X's validation on real-world data highlights its potential for practical clinical use.
Microsoft Research has developed CARE-X, a vision-language model aimed at improving radiology interpretation. CARE-X combines generative and structured prediction capabilities to support diverse clinical tasks, offering both free-text reasoning and deterministic outputs. The model uses reinforcement learning to enhance clinical correctness and has been tested on real-world clinical data. Although not a commercial product, CARE-X represents a significant advancement in creating AI systems that can better support radiology workflows.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1AI Co-Clinician Development Announced by DeepMind
Google DeepMind · April 30, 2026 · Background
- 2Boston Children's Hospital Enhances Diagnoses with AI
OpenAI · May 29, 2026 · Background
- 3Microsoft and Mayo Clinic Develop AI Health Model
Matt Wolfe · June 5, 2026 · Background
- 4Google Research Explores AI in Dermatology Assistance
Google Research Blog · June 12, 2026 · Background
- 5Microsoft's Echoverse Enhances AI Training Environments
Microsoft Research · July 30, 2026 · Background
- 6Study Reveals AI's Varied Impact on Medical Diagnosis
MIT News AI · August 4, 2026 · Background
- 7PRISM2 Model Enhances Pathology Slide Interpretation
AI News · August 5, 2026 · Background
- 8MIT Study: AI Health Tools Must Adapt to User Expertise
AI News · August 6, 2026 · Background
What happened next
- 9Google's AMIE AI Shows Real-Time Video Consultation
Google AI Blog · August 11, 2026 · Background
- 10Microsoft's GigaPath-Flash Models Boost Pathology Research
Microsoft Research · August 31, 2026 · Background
- 11Specialized Image Models for RPA Decision Making
Sam Witteveen · October 2, 2026 · Background
- 12Microsoft AI outperforms doctors in complex diagnostic simulation
TechCrunch AI · October 22, 2026 · Background
More in Research
© Cole MedinResearchagents
Anthropic study: Agents sway expert judgment 86% of time
Anthropic’s latest research exposes a quiet but dangerous flaw in agentic workflows: experts follow AI recommendations 86% of the time, often adopting the agent's reasoning as their own. This isn't just about accuracy; it's about cognitive capture, where human oversight dissolves into passive compliance. The study shows that even when users believe they are steering, the agent’s framing dictates the outcome. Practitioners must now actively counter this bias by forcing agents to justify deviations or prototype alternatives before committing to a path. This shift demands a new discipline in how we interact with coding assistants. We can no longer assume our intent drives the result; the model's suggestion often becomes the default truth. The real work is ensuring we remain the architects, not just the approvers.
Cole Medin
© WIRED AIResearchother
AI-Augmented Infostealer 'Volta-Autodoxer' Targets High-Value Victims
Cisco Talos has uncovered a new infostealer strain that actively uses commercial LLMs to profile victims and prioritize high-value targets. Dubbed Volta-Autodoxer, the malware collects credentials and browsing data, then feeds this into models like Claude Opus 4.6 via OpenRouter to generate structured intelligence dossiers. This marks a shift from passive data theft to active, AI-driven triage, allowing attackers to bypass guardrails with fallback models like Kimi K2 or Gemini. The capability foreshadows a future where lower-sophistication criminals can execute sophisticated, targeted attacks at scale.
WIRED AI
© Matt WolfeResearchresearch
OpenAI Disproves Exponential Time Hypothesis
OpenAI researchers published findings disproving the Exponential Time Hypothesis, a major result in computational complexity theory.
Matt Wolfe