Microsoft Research

Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. msft.it/63325aaFPD

For decades, a key question about the challenges of high-dimensional computation resisted proof. New research resolves the KLS conjecture, removing a major barrier to understanding the efficiency of randomized algorithms used throughout science and computing. msft.it/63326aakQa

When the problems you're working to solve feel overwhelming, what keeps you hopeful? For Microsoft Research's Chris White, it's knowing there's something he can do. Find the podcast: msft.it/63322av2PO

Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security: msft.it/63322atJ5m

Some AI failures are obvious. Others look right...until they compound. Microsoft Partner Research Manager Jennifer Neville shares “surprising failures” that challenge our assumptions about what should be easy or hard for AI with host Chad Atalla. www.microsoft.com/en-us/resear...

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them.: www.microsoft.com/en-us/resear...

Progress involves stops, starts, and pivots. It’s rarely linear—for people or AI systems. Jennifer Neville explores the turns that led her to AI and the ways she’s identifying AI failures so the tech can do more—and better—than what it’s doing today. www.microsoft.com/en-us/resear...

Extreme space-weather events can damage power systems on Earth and degrade GPS accuracy and satellite operations. A new machine learning system can predict where damage is likely to occur 30-60 minutes before a storm arrives: www.microsoft.com/en-us/resear...

Since launching a year ago, the Microsoft Research Asia — Singapore lab has established a strong foundation, deepened collaboration across government, academia, and industry, and explored how frontier AI research can create real-world value: www.microsoft.com/en-us/resear...

Securing data when trusted hardware is compromised; monitoring underwater recordings to protect endangered whales; Living Library enables conversations with historical figures; AI builders should listen to the young people who will ultimately use it. www.linkedin.com/pulse/monito...

Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads. www.microsoft.com/en-us/resear...

Custom-made molecules are advancing medicine, materials, and agriculture, but producing them is slow and expensive. A new Nature paper highlights RetroChimera, a predictive model that helps accelerate chemical synthesis.: www.microsoft.com/en-us/resear...

A look at how coding agents behave at scale; evaluating AI models that find lymphoma lesions in PET/CT scans; understanding AI chatbot dependence; and advancing large-scale decision-making systems. Dive into the latest issue of Research Focus.: www.linkedin.com/pulse/evalua...

How is AI reshaping the way we work? Join researchers, builders, and practitioners at The New Future of Work Summit on Sept. 14 for practical workshops, live demos, and research-backed insights on AI and agents. Free and open to all. Register: globalai.community/e/9j3q97d1

Curious about a future in research? The Microsoft Research Undergrad Internship Program offers hands-on research experience, mentorship, & a chance to explore advanced study. Rising juniors & seniors can apply for 12-week internships in Redmond, NYC, or New England. Apply by Oct. 5: aka.ms/msr-ugrad

💭 What’s it like to spend a summer doing research at Microsoft? Matheus Kunzler Maldaner is an undergraduate research intern exploring agentic systems. Meet him in the first episode of our new series, Research | Start Here: Inside the Internship. ▶️

What if pathology foundation models could do more with less? GigaPath-Flash and GigaTIME-Flash cut computational demands while maintaining strong performance, opening the door to larger studies and broader exploration. www.microsoft.com/en-us/resear...

We treat the way the world works now as normal. It isn't. Doug Burger, Amy Luers & Ishai Menache sit with a hard idea: modern civilization is a historical anomaly built on fossil fuels & exponential growth & AI may be the first tool capable of rewiring it. www.microsoft.com/en-us/resear...

Skala 1.1, the updated deep-learning exchange-correlation functional from Microsoft Research, provides greater accuracy, expanded accessibility across the computational chemistry ecosystem, and a living benchmark to track computational performance. www.microsoft.com/en-us/resear...

Every powerful new technology comes with trade-offs. The internet had them. Social media had them. Doug Burger, Amy Luers, and Ishai Menache explore AI’s climate impact and steering the tech to support a sustainable future. msft.it/6040az1Bi

Microsoft is proud to be a part of SIGCOMM 2026. Check out our sessions, covering network traffic engineering, new load balancing strategy, adaptive photonic switching schedules, AI network simulation, and more. www.linkedin.com/pulse/micros...

A path, a fence, a knot. MindTopo sets a new benchmark for testing how AI understands topological relationships and highlights new opportunities to strengthen spatial reasoning and planning. www.microsoft.com/en-us/resear...

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. www.microsoft.com/en-us/resear...

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. www.microsoft.com/en-us/resear...

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. www.microsoft.com/en-us/resear...

Researchers Jenna Butler, Jake Hofman, and Rebecca Janssen spend a lot of time studying AI’s influence on how people do their jobs. On the Microsoft Research Podcast, they share their thoughts on what the future of work looks like in the age of AI. www.microsoft.com/en-us/resear...

Aurora 1.5 scales open forecasting; Flint redefines visualization; FlowDAgger accelerates adaptation. Plus: AI agents crack Rowhammer defenses and memory reshapes conversational AI. www.linkedin.com/pulse/22-new...

Recalling a new password after hours of distractions can be hard. Not for a transformer. Microsoft CVP Doug Burger & AI researchers Subutai A. & Nicolo Fusi discuss the fundamental differences between human memory and machine intelligence. www.microsoft.com/en-us/resear...

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. www.microsoft.com/en-us/resear...

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. www.microsoft.com/en-us/resear...

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. www.microsoft.com/en-us/resear...

Among Microsoft’s 100+ accepted papers, 3 oral presentations, and 1 expo demo at ICML in Seoul, highlights include Fara 1.5 computer-use agents, critique-resilient benchmarking, expanded protein ML benchmarks with FLIP2, and improved LLM reasoning stability. msft.it/6019vaCHU

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: msft.it/6012vsvEs

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: msft.it/6018vs3gC

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. msft.it/6011vUtRd

Talos was built to help resolve a major bottleneck in genomic medicine: human review time. The open-source system recovered 90% of in-scope diagnoses while surfacing just 1.3 candidate variants per patient for expert review. msft.it/6014vUBwK

On the Microsoft Research Podcast, Microsoft’s Jaime Teevan, Jenna Butler, Jake Hofman, and Rebecca Janssen explore how looking at AI as more than a tool for automating tasks people are already capable of might open the door to new possibilities. msft.it/6011vo8cX

Can you remember a new password after listening to five hours of stories? A transformer can. AI researchers Subutai Ahmad and Nicolò Fusi explore the fundamental differences between human memory and machine intelligence with Microsoft CVP Doug Burger. msft.it/6016vllRa

ResNet has received the Longuet-Higgins Prize at CVPR 2026, recognizing research with proven, lasting impact. A decade after its publication, residual connections remain foundational to how modern AI systems are built, with over 320,000 citations and growing. msft.it/6017vl6bl

30x faster analytics, GPU kernels generated automatically from SQL, AI matched to lab-grown tumor models for cancer treatment, and LLMs that learn across tasks without retraining. Dive into the latest issue of Research Focus: msft.it/6010vcYZ4

Project Ire examined a timely malware sample and determined its intent through reverse engineering—identifying LOTUSLITE characteristics even as most major EDR tools did not detect it. msft.it/6011viy4N