Discover an index of datasets, SDKs, APIs and open-source tools developed by Microsoft researchers and shared with the global academic community below. These experimental technologies—available through Azure AI Foundry Labs (opens in new tab)—offer a glimpse into the future of AI innovation.
Phi-4-multimodal and Phi-4-mini, the newest models in Microsoft’s Phi family of small language models (SLMs) are now available. These models are designed to empower developers with advanced AI capabilities. Phi-4-multimodal, with its ability to process…
ReMe is a web-based framework that helps researchers create AI chatbots for personalized training and interventions aimed at strengthening memory and cognitive functions. Early evaluations show its potential to contribute to digital health innovation and…
EvoDiff is a general-purpose diffusion framework that combines evolutionary-scale data with the distinct conditioning capabilities of diffusion models for controllable protein generation in sequence space. EvoDiff generates high-fidelity, diverse, and structurally-plausible proteins that cover natural…
PEACE enhances multimodal large language models (MLLMs) with geologic expertise, enabling accurate interpretation of complex, high-resolution maps. By integrating structured extraction, domain knowledge, and reasoning, it supports critical tasks in disaster risk, resource discovery, and…
The MCP Server for Azure AI Foundry Labs is designed to supercharge team velocity in adopting and evaluating breakthrough AI research. By equipping GitHub Copilot with custom tools for intelligent model discovery, tailored implementation guidance,…
With Project Amelie, we are unveiling our first Foundry autonomous agent that can perform machine learning engineering tasks. ML teams can use the agent to initiate complex machine learning tasks using prompts —such as, “Help…
Precio is a Rust library that implements the Precio protocol for computing private layered histograms and sums.
Protein language models (PLMs) pretrained via a masked language modeling objective have proven effective across a range of structure-related tasks, including high-resolution structure prediction. However, it remains unclear to what extent these models factorize protein…
Lost in Conversation is a code repository to facilitate benchmarking LLMs on multi-turn task completion and the reproduction of experiments included in the accompanying paper: “LLMs Get Lost in Multi-Turn Conversation”.
