News & features
Research Focus: Week of July 17, 2023
RetroRanker mitigates frequency bias in predictions of retrosynthesis models; new algorithm beats PPO on language tasks; DER dataset aids grid planning; improved PPML balances privacy & accuracy across shared data; ASL Citizen boosts sign language modeling.
Breaking cross-modal boundaries in multimodal AI: Introducing CoDi, composable diffusion for any-to-any generation
| Zineng Tang, Ziyi Yang, Chenguang Zhu, Michael Zeng, and Mohit Bansal
Imagine an AI model that can seamlessly generate high-quality content across text, images, video, and audio, all at once. Such a model would more accurately capture the multimodal nature of the world and human comprehension, seamlessly consolidate information from a…
Research Focus: Week of June 5, 2023
In this issue: Peter Lee discusses AI in medicine. Plus, new research on data inference privacy in machine learning; PII leakage in language models; and automatic prompt organization with gradient descent and beam search.
Azure AI milestone: Microsoft KEAR surpasses human performance on CommonsenseQA benchmark
| Yichong Xu, Chenguang Zhu, Shuohang Wang, Michael Zeng, and Xuedong Huang
KEAR (Knowledgeable External Attention for commonsense Reasoning)—along with recent milestones in computer vision and neural text-to-speech—is part of a larger Azure AI mission to provide relevant, meaningful AI solutions and services that work better for people because they better capture how people learn and…