Microsoft Research Lab Asia

Imagine a pair of smart glasses that detects its surroundings and speaks up at critical moments, such as when a car is approaching. That kind of split-second assistance could be transformative for people with low vision, but today’s visual AI assistants often miss those moments. The problem isn’t that the technology can’t detect its environment. The post StreamMind: AI system that responds to video in real time appeared first on Microsoft Research.

Time-series data—measurements collected at regular intervals, like stock prices or traffic flows—has become a key driver of intelligent decision-making systems across industries. From medical monitoring to financial risk control, identifying patterns in this data is essential to many important operations. At the same time, the creation of time-series data, or data synthesis, is gaining momentum The post TimeCraft: A universal framework for time-series generation appeared first on Microsoft Research.

As large language models (LLMs) continue to improve at writing code, a key challenge has emerged: enabling them to generate complex, high-quality training data that actually reflects real-world programming. Currently, most data synthesis methods rely on simple code snippets as starting points. While these fragments are useful for illustrating specific functions, they often fail to The post Feature tree-driven synthesis improves training data for code LLMs  appeared first on Microsoft Research.

One of the driving forces behind AI’s rapid progress is access to large-scale, high-quality data, essential to enable training models to continuously improve and perform reliably. But that well is running dry. As the supply of usable internet data shrinks, it’s becoming harder and more expensive to gather the kind of training data AI needs. The post SynthLLM: Breaking the AI “data wall” with scalable synthetic data appeared first on Microsoft Research.

World models are a key concept in AI, used to simulate how agents behave in virtual environments and enable immersive, interactive experiences. They’re not only transforming game and media generation, they’re also opening new frontiers for using AI in complex, dynamic settings. One emerging trend is generative games, where game environments are created frame by The post MaaG: A new framework for consistent AI-generated games appeared first on Microsoft Research.

Time-series data—measurements collected over time like stock prices or heart rates—plays a vital role in AI forecasting systems across industries. As these systems advance, the need for time-series data is increasing, especially synthetic data, which offers numerous advantages over real-world data. In healthcare, synthetic data protects patient privacy; in finance, it enables risk-free testing of The post TimeDP: Creating cross-domain synthetic time-series data appeared first on Microsoft Research.

Math is more than a school subject—it’s the engine behind scientific discovery, driving advances in everything from climate modeling to AI. At Microsoft Research Asia, senior researcher Xian Zhang is leading efforts to help AI move beyond surface-level pattern recognition toward deeper, rules-based reasoning. In a recent interview, he explained how this shift could significantly expand The post Teaching LLMs to think: Xian Zhang on advancing mathematical reasoning in AI appeared first on Microsoft Research.

AI is reshaping our world at an unprecedented pace, yet the path from research breakthroughs to industry-ready solutions doesn’t happen overnight. Turning technical innovations into practical tools takes more than cutting-edge algorithms. It also requires a clear understanding of industry needs—and close collaboration across disciplines. At Microsoft Research Asia, a team of researchers is working The post Xiaofan Gui: Bridging abstract thinking with practical solutions appeared first on Microsoft Research.

When earthquakes hit, they often come with little warning. Each year, about 500,000 earthquakes ripple through the Earth—some are felt, many aren’t, but all are part of a complex and dynamic system that geologists are trying to understand. Earthquakes are notoriously difficult to predict, but a new interdisciplinary effort is using AI to bring us The post PEACE project unlocks AI applications in geology using GeoMap appeared first on Microsoft Research.

A key challenge, and opportunity, of large language models (LLMs) is bridging the gap between their training data and the vast amount of unfamiliar information they encounter in real-world applications. Successfully navigating this divide could unlock a new era of data analysis, helping these models to uncover nuanced themes and semantic concepts across a wide The post PIKE-RAG: Enabling industrial LLM applications with domain-specific data appeared first on Microsoft Research.