Research Tools: code, datasets, & models

SigmaCollab is a dataset that enables research on human-AI physically situated collaboration. The dataset consists of a set of 85 sessions in which untrained participants were guided by a mixed-reality assistive AI agent in performing…

Generative modeling, representation learning, and classification are three core problems in machine learning (ML), yet their state-of-the-art (SoTA) solutions remain largely disjoint. In this paper, we ask: Can a unified principle address all three? Such…

We propose Large Market Model (LMM), an order-level generative foundation model, for financial market simulation, akin to language modeling in the digital world. Our financial Market Simulation engine (MarS), powered by LMM, addresses the domain-specific…

MIRA is a foundation model for medical time-series, designed to learn a unified representation space across heterogeneous clinical datasets and support zero-shot forecasting in real-world healthcare settings. Unlike conventional time-series models that operate on fixed…

MetaEase is a framework for automatically finding worst-case inputs of heuristics by maximizing the gap between heuristic and optimal solutions. It combines symbolic execution (KLEE) with gradient-based optimization to efficiently explore the input space. This…

RadEdit is a latent diffusion model trained to generate and edit chest X-rays from medical reports. It is described in detail in RadEdit: Stress-Testing Biomedical Vision Models via Diffusion Image Editing (F. Pérez-García, S. Bond-Taylor, et…

RosettaFold3 (RF3) is a unified biomolecular modeling system that predicts 3D structures of proteins, nucleic acids, and small molecules within a single framework. Combining multimodal transformers and generative diffusion models, RF3 enables precise modeling of…

Microsoft’s first agentic small language model specifically designed for computer use. With only 7 billion parameters, Fara-7B achieves state-of-the-art performance within its size class and is competitive with larger, more resource-intensive agentic systems that depend…

Promptions is a simple, flexible dynamic prompt middleware technique for AI that uses ephemeral UI. From a single, simple prompt, the system helps users steer the AI by suggesting parameterized choices as dynamically generated, ephemeral UI components. As…

SPARROW, developed by Microsoft’s AI for Good Lab, is an AI-powered edge computing solution designed to monitor and protect wildlife in the most remote regions of the world. Solar-powered and equipped with advanced sensors, it collects biodiversity…