At Microsoft Research, we accelerate scientific discovery and technology innovation to empower every person and organization on the planet to achieve more. We do this by bringing together the best minds across diverse disciplines and backgrounds to take on the most pressing research challenges for Microsoft and for society.
Our Research Lens
We consider research directions through the lens of the positive impact we aspire to create with and for customers, communities, and all of society.
Paige and Microsoft Research unveil PRISM2: a whole-slide foundation model that analyzes tissue and understands it in context.
From zero-shot predictions to clinician-ready reports, PRISM2 brings unparalleled versatility to diagnostics, biomarker discovery and multimodal patient outcome modeling.
Trained on 2.3 million slides and paired with clinical reports, PRISM2 seamlessly integrates with Microsoft Phi-3, setting a new benchmark in performance, interpretability, and flexibility.
https://lnkd.in/erXw8yYX
Recipient of an ICML 2025 Outstanding Paper Award, CollabLLM improves how LLMs collaborate with users, including knowing when to ask questions and how to adapt tone and communication style to different situations. This approach helps move AI toward more user-centric and trustworthy systems. https://msft.it/6043Shf29
AI is becoming one of science’s go-to tools. From medical advancements to atomic modeling, researchers are using it to solve problems too complex for conventional tools: https://msft.it/6006ShRqe
In “AI Testing and Evaluation,” former UK cybersecurity chief Ciaran Martin explores differentiated standards and public-private partnerships in cybersecurity, and Microsoft’s Tori Westerhoff examines the insights through an AI red-teaming lens.
https://msft.it/6041Shbd5
In this issue: We’re spotlighting Microsoft’s presence at ICML 2025, where our researchers are showcasing their accepted papers and delivering oral presentations exploring reasoning, optimization, multimodality, and more.
Daphne Koller, Noubar Afeyan, & Dr. Eric Topol, MD, leaders in AI-driven medicine, explore how AI is reshaping how we diagnose and treat disease—from early-stage drug discovery to clinical care—in Episode 8 of “The AI Revolution in Medicine, Revisited.” https://msft.it/6043S7pdR
Today in the journal Science: BioEmu from Microsoft Research AI for Science. This generative deep learning method emulates protein equilibrium ensembles – key for understanding protein function at scale. https://msft.it/6043S7rAH
BioEmu aims to emulate the ensemble of structures that a protein will adopt in an experiment or the cell. The ability of a protein to dynamically switch between distinct structures is a basis for its function.
BioEmu 1.1 is trained longer and more carefully in 3 distinct stages on vast data of protein structures, >200 milliseconds of molecular dynamics simulations, and 500,000 protein stability measurements.
BioEmu 1.1 predicts functionally relevant conformational changes, including large-scale domain motions and local unfolding events + an increased success rate in predicting the formation of “cryptic” binding pockets.
BioEmu 1.1 can emulate equilibrium distributions of millisecond-timescale MD at many orders of magnitude speedup, bringing GPU-years down to GPU-hours.
BioEmu 1.1 improves ability to match experimental protein stability measurements with sampled protein structure ensembles with prediction errors below 1 kcal/mol, correlations >0.6 for a large protein stability test set, and train-test sequence similarities ~ 50%.
This also holds up for predicting stability changes of single and double mutants. These results indicate that the encoding of protein mutants still resolves enough differences to be predictive when fine-tuned with the right data.
Also available: MD simulations generated to train BioEmu – more than 100 milliseconds worth of data of 1000s of protein systems and 10,000s of mutants. This dataset stands out for its combined protein sequence diversity and simulation length.
Learn more: https://msft.it/6044S7rAy
Congratulations to Hayley LeBlanc, Jay Lorch, Chris Hawblitzel, Cheng Huang and co-authors of “Power Never Corrupts: Tool-Agnostic Verification of Crash Consistency and Corruption Detection” for winning the Distinguished Artifact Award at #OSDI2025!
This recognition highlights the impact of their work in advancing reliable systems research. Dive into this paper and explore all of Microsoft’s accepted research at OSDI 2025 on our conference site: https://msft.it/6043SAYEB
Cement is everywhere. It’s the second most-used material on Earth after water—and one of the biggest contributors to greenhouse gas emissions.
But what if we could use a natural green material to help build a more sustainable future?
A new study from Microsoft Research and the University of Washington explores just that—introducing unprocessed seaweed in cement as a way to reduce its carbon emissions.
The method leverages the carbon-capturing potential of intact biomass while minimizing the need for energy-intensive processing. And thanks to machine learning, the researchers completed the optimization process in just 28 days—five times faster than conventional approaches. https://msft.it/6049SAKeJ
Photo Credit: Mark Stone /University of Washington
In “AI Testing & Evaluation,” professor Daniel Carpenter & Prof. Timo Minssen explore pharma & medical device regulation, including the role of clinical trials, while Microsoft’s Chad Atalla shares where AI governance stakeholders might find inspiration. https://msft.it/6044Sfpt0
