Microsoft Research 微软研究院

Microsoft Research 微软研究院

https://www.microsoft.com/en-us/research/
https://www.microsoft.com/en-us/research/feed/ (RSS订阅地址)

Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement

<p> Radiology AI is evolving beyond report generation. CARE-X explores a unified approach that combines flexible reasoning, calibrated predictions, and measurement-based tools for chest X-ray interpretation.</p> <p>The post <a href="https://www.microsoft.com/en-us/research/blog/introducing-care-x-towards-clinically-useful-radiology-vlms-with-auxiliary-supervision-reward-aligned-learning-and-tool-augmented-measurement/">Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement</a> appeared first on <a href="https://www.microsoft.com/en-us/research">Microsoft Research</a>.</p>

2026/8/11
阅读更多

Orchard: An open framework for scalable agentic AI

<p>Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure.</p> <p>The post <a href="https://www.microsoft.com/en-us/research/blog/orchard-an-open-framework-for-scalable-agentic-ai/">Orchard: An open framework for scalable agentic AI</a> appeared first on <a href="https://www.microsoft.com/en-us/research">Microsoft Research</a>.</p>

2026/8/3
阅读更多

Echoverse: Deep, evolving environments for computer-use agents

<p>Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and environments evolve.</p> <p>The post <a href="https://www.microsoft.com/en-us/research/blog/echoverse-deep-evolving-environments-for-computer-use-agents/">Echoverse: Deep, evolving environments for computer-use agents</a> appeared first on <a href="https://www.microsoft.com/en-us/research">Microsoft Research</a>.</p>

2026/7/30
阅读更多

EvoLib: Turning experience into evolving knowledge

<p>LLMs do not get smarter just by remembering more. EvoLib turns experience into evolving knowledge, taking reusable skills and insights that help models learn and adapt across tasks long after deployment. </p> <p>The post <a href="https://www.microsoft.com/en-us/research/blog/evolib-turning-experience-into-evolving-knowledge/">EvoLib: Turning experience into evolving knowledge</a> appeared first on <a href="https://www.microsoft.com/en-us/research">Microsoft Research</a>.</p>

2026/7/30
阅读更多

Verifying Rust cryptography in SymCrypt, from standards to code

<p>Cryptographic code supports vital protections in modern computing systems. Learn how a new method helps verify code as developers write it while preserving speed and adaptability as it gets implemented and evolves.</p> <p>The post <a href="https://www.microsoft.com/en-us/research/blog/verifying-rust-cryptography-in-symcrypt-from-standards-to-code/">Verifying Rust cryptography in SymCrypt, from standards to code</a> appeared first on <a href="https://www.microsoft.com/en-us/research">Microsoft Research</a>.</p>

2026/7/13
阅读更多

Aurora 1.5: Extending open foundation models for weather and Earth-system applications

<p>Aurora 1.5 adds 22 more variables, hourly temporal resolution, and probabilistic ensemble forecasting to the Aurora foundation model, making it more useful for real-world weather, climate, and energy applications.</p> <p>The post <a href="https://www.microsoft.com/en-us/research/blog/aurora-1-5-extending-open-foundation-models-for-weather-and-earth-system-applications/">Aurora 1.5: Extending open foundation models for weather and Earth-system applications</a> appeared first on <a href="https://www.microsoft.com/en-us/research">Microsoft Research</a>.</p>

2026/7/9
阅读更多

Flint: A visualization language for the AI era

<p>Short chart specifications are easy to write, but often produce uninspiring results. Flint is an open-source visualization language that offers a middle path, letting AI agents create expressive charts from compact, human-editable specifications.</p> <p>The post <a href="https://www.microsoft.com/en-us/research/blog/flint-a-visualization-language-for-the-ai-era/">Flint: A visualization language for the AI era</a> appeared first on <a href="https://www.microsoft.com/en-us/research">Microsoft Research</a>.</p>

2026/7/8
阅读更多

SkillOpt: Agent skills as trainable parameters

<p>AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. Learn how SkillOpt turns skill editing into a training process, making agent behavior more reliable without changing model weights.</p> <p>The post <a href="https://www.microsoft.com/en-us/research/blog/skillopt-agent-skills-as-trainable-parameters/">SkillOpt: Agent skills as trainable parameters</a> appeared first on <a href="https://www.microsoft.com/en-us/research">Microsoft Research</a>.</p>

2026/6/30
阅读更多

Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity

<p>AI agents can't remember past conversations. They must constantly reload or retrieve context, which grows less efficient as tasks get longer and more complex. Memora solves this with a scalable memory system separating what’s stored from how it's retrieved.</p> <p>The post <a href="https://www.microsoft.com/en-us/research/blog/memora-a-harmonic-memory-representation-balancing-abstraction-and-specificity/">Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity</a> appeared first on <a href="https://www.microsoft.com/en-us/research">Microsoft Research</a>.</p>

2026/6/29
阅读更多

Understanding the brain with AI-driven explanations and experiments

<p>Researchers introduce generative causal testing, which translates black box models into clear hypotheses and verifies them in the scanner, revealing what specific brain regions respond to in language.</p> <p>The post <a href="https://www.microsoft.com/en-us/research/blog/understanding-the-brain-with-ai-driven-explanations-and-experiments/">Understanding the brain with AI-driven explanations and experiments</a> appeared first on <a href="https://www.microsoft.com/en-us/research">Microsoft Research</a>.</p>

2026/6/25
阅读更多