Author: Andy Beatman

MatterGen is a diffusion-based generative model for inorganic materials design. It can propose stable, novel crystal structures and be guided by target properties like bulk modulus, band gap, or magnetic density, accelerating materials discovery.

CalcLM is a prototype from Azure AI Foundry Labs that experiments with bringing agentic AI into the grid interface of Excel. It enables users to express agent steps as formulas, chain tasks across cells, and quickly explore how simple agent workflows might flow in a familiar surface.

Debug-gym is an open-source research environment for teaching AI coding agents to debug more like humans—interactively and iteratively. With tools like Python’s pdb, agents can set breakpoints, inspect code, and run tests, enabling smarter, more reliable coding workflows.

Trellis is a research system for generating editable 3D assets from simple text or image prompts. Using a novel latent representation, it produces meshes, radiance fields, and 3D Gaussians with rich texture and structure—accelerating workflows in gaming, AR/VR, digital twins, and industrial design.

NextCoder is a research model series designed to improve code editing. Using a novel synthetic data pipeline and the SeleKT adaptation algorithm, it teaches language models to handle diverse edit requirements while retaining strong code generation skills, outperforming peers across multiple benchmarks.

TypeAgent is research sample code exploring how to build a single personal agent with natural language interfaces. By distilling language models into logical structures for actions, memory, and plans, it enables safer, faster, and lower-cost ways to map user requests into meaningful applications.

Magentic-UI is a research platform for advancing human-in-the-loop AI experiences. It explores co-planning, co-tasking, and task learning. Features like action guards and safe sandboxes enable more trustworthy human-AI collaboration.

Project Amelie is the first Foundry autonomous agent designed to perform machine learning engineering tasks. With natural language prompts, it generates validated ML pipelines, evaluation metrics, trained models, and reproducible code—advancing automation in research and development.

The MCP Server for Azure AI Foundry Labs equips GitHub Copilot with custom tools for model discovery, integration guidance, and rapid prototyping. By streamlining workflows and reducing the idea-to-prototype cycle to under 10 minutes, it accelerates research adoption and boosts developer productivity.

EvoDiff is a diffusion framework for controllable protein generation in sequence space. Trained on evolutionary-scale data, it produces high-fidelity, diverse, and structurally plausible proteins, enabling novel designs beyond structure-based models and advancing sequence-first protein engineering.

PEACE enhances multimodal large language models with geologic expertise, enabling accurate interpretation of complex maps. By combining structured extraction, domain knowledge, and reasoning, it supports disaster risk assessment, resource exploration, and infrastructure planning—transforming general AI into a specialized geoscience tool.

ReMe is a web-based framework that helps researchers build AI chatbots for personalized memory and cognitive training. By combining puzzle tasks, life-logging, and multimodal interaction, it enables more engaging, adaptable interventions to advance digital health and non-pharmacological approaches to cognitive care.

BitNet is the first open-source, native 1-bit large language model, with every parameter represented as −1, 0, or 1. Scaled to 2 billion parameters, it demonstrates how ternary LLMs can achieve strong performance while dramatically reducing memory, compute, and energy requirements for AI training and inference.