뉴스 & 기능
Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
| Xuchao Zhang, Molly Xia, Mayukh Das, Anson Bastos, Rujia Wang, Chetan Bansal, 그리고 Saravan Rajmohan
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.
Understanding the brain with AI-driven explanations and experiments
| Chandan Singh 그리고 Jianfeng Gao
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.
뉴스에서 | Microsoft Azure Blog
Announcing Microsoft Discovery general availability and Microsoft Discovery app preview
Today at Microsoft Build, we are announcing that Microsoft Discovery is now generally available for all organizations, providing a comprehensive platform for building and governing agentic AI workflows across scientific and engineering disciplines. We are also introducing the Microsoft Discovery app in…
Data Formulator 0.7: AI-powered data analytics for enterprise data
| Chenglong Wang, Scott Tsukamaki, Michel Galley, 그리고 Jianfeng Gao
Data Formulator introduces AI-powered analytics for enterprise data workflows. Data teams can easily bring enterprise data into an AI-ready workspace where users can explore, analyze, and visualize data with AI agents to turn raw data into actionable insights.
Vega: Zero-knowledge proofs for digital identity in the age of AI
| Srinath Setty
Vega turns a full credential into a single proof, sharing only what is needed and nothing more, with performance that works in real apps.
Further Notes on Our Recent Research on AI Delegation and Long-Horizon Reliability
| Philippe Laban, Tobias Schnabel, 그리고 Jennifer Neville
Our recent paper, “LLMs Corrupt Your Documents When You Delegate”, has generated discussion about the reliability of AI systems in delegated workflows. We appreciate the interest in this work and want to clarify several important points about what the paper…
mimalloc: A new, high-performance, scalable memory allocator for the modern era
| Daan Leijen
mimalloc is an open-source, modern, scalable memory allocator that is a drop-in replacement for malloc and free. It is relatively small (~12K lines), with clear internal data structures, and is easy to build and integrate into other projects. It provides…
GridSFM: A new, small foundation model for the electric grid
| Weiwei Yang, Andrea Britto Mattos Lima, Thiago Vallin Spina, Spencer Fowers, 그리고 Baosen Zhang
Introducing GridSFM, a small foundation model that can predict AC optimal power flow in milliseconds, boosting efficiency and unlocking cost savings. Learn how GridSFM gives grid operators direct visibility into congestion, stability, and system health.
Building realistic electric transmission grid dataset at scale: a pipeline from open dataset
| Andrea Britto Mattos Lima, Thiago Vallin Spina, Weiwei Yang, Spencer Fowers, Ruslan Nagimov, 그리고 Baosen Zhang
Microsoft Research is excited to release an open dataset of approximate transmission topology of the U.S. power grid derived from publicly available data. The ability to study transmission-level power grid behavior is essential for modern power systems research. Analyses of…