Recherche
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.
This repository is the official implementation of the paper “FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation.” It can be used for baseline evaluation using the prompts mentioned in the paper. The…
CFPO (Content-Format Integrated Prompt Optimization) is a novel methodology that concurrently optimizes both prompt content and format for Large Language Models (LLMs) through an iterative refinement process. It addresses the limitations of existing prompt optimization…
TimeCraft offers a unified, practical solution for real-world time series generation—combining cross-domain generalization, text-based control, and task-aware adaptation. It’s designed to produce high-quality, controllable synthetic data that’s both realistic and useful for downstream applications.
The RAS library is an open-source implementation of Regional-Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional variability in sampling steps. Unlike conventional methods that uniformly process all image regions, RAS dynamically…
This is the official repository of paper “Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching.” We propose Distilled Decoding (DD) to distill a pre-trained image auto-regressive model to few steps for…
This is the official code repository for the paper “Unearthing Skill-level Insights for Understanding Tradeoffs of Foundation Models”. All rationales, localized skills, and skill-slices for the 12 datasets studied in the paper can also be accessed…
This is the official codebase for the paper “The Belief State Transformer”, based on the nanoGPT repository by Andrej Karpathy.
debug-gym is a text-based interactive debugging framework, designed for debugging Python programs.
In this work, we developed a low-cost, smartphone-based automated Non-Invasive Break-Up Time (NIBUT) measurement prototype. It can be used to estimate dryness of the eye. We utilized the 3D-printed Placido ring attachment on a smartphone’s…