Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Tool
DPSDA
DSPDA: Differentially Private Synthetic Data via Foundation Model APIs—This repo is a Python library to generate differentially private (DP) synthetic data without the need of any ML model training. It is based on the following papers…
Tool
DEEGO: PPGNN
We study various aspects of our proposed model including, dependency on the number of eigencomponents utilized, latent polynomial filters learned, and performance of the individual polynomials on the node classification task. We further show that…
Tool
ReinMax
Bridging Discrete and Backpropagation: Straight-Through and Beyond—Guided by our findings, we propose a novel method called ReinMax, which integrates Heun’s Method, a second-order numerical method for solving ODEs, to approximate the gradient. Our method, ReinMax,…
Microsoft Research Blog
Incorporating chemists’ insight with AI models for single-step retrosynthesis prediction
Retrosynthesis analysis is a critical task in organic chemistry and central to many important industries. It primarily involves decomposing a target molecule into commercially available molecules step by step. Since synthesis strategies can be quite…
Publication
Large-Scale Automatic Audiobook Creation
Tool
CO-BED
CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design. We formalize the problem of contextual optimization through the lens of Bayesian experimental design and propose CO-BED—a general, model-agnostic framework for designing contextual experiments using information-theoretic principles.
Tool
Deep Language Networks
We view Large Language Models as stochastic language layers in a network, where the learnable parameters are the natural language prompts at each layer. We stack two such layers, feeding the output of one layer…
Microsoft Research Blog
Frontiers of multimodal learning: A responsible AI approach
New evaluation methods and a commitment to continual improvement are musts if we’re to build multimodal AI systems that advance human goals. Learn about cutting-edge research into the responsible development and use of multimodal AI…
