Human-computer interaction
Redefining human experiences through innovations in research, design, and technology.
Microsoft Research Blog
Research Focus: Week of August 14, 2023
In this issue: HyWay enables hybrid mingling; Auto-Tables transforms non-relational tables into standard relational forms; training dense retrievers to identify high-quality in-context examples for LLM; improving pronunciation assessment in CAPT.
Project
DragNUWA
DragNUWA is a video generation model that utilizes text, images, and trajectory as three essential control factors to facilitate highly controllable video generation. DragNUWA is a video generation model that utilizes text, images, and trajectory…
Project
HyWay
A platform to enable mingling between in-person (physical) and remote (virtual) users. As normalcy has returned after the COVID-19 pandemic, offices have reopened, and events have returned to a physical format. However, the convenience and…
Podcast
Collaborators: Data-driven decision-making with Jina Suh and Shamsi Iqbal
Researcher Jina Suh and manager Shamsi Iqbal are longtime collaborators. Learn how their history of working together and their unique perspectives are informing their development of tools to support decision-making for organizational leaders.
Podcast
Collaborators: Gaming AI with Haiyan Zhang
For over a decade, Xbox has been leveraging AI to elevate gaming. Haiyan Zhang, GM of Gaming AI, explores the collaborations behind the work and the potential for generative AI to support better experiences for…
Microsoft Research Blog
Thinking beyond audio: Augmenting headphones for everyday digital interactions
Because headphones rank among the most popular wearables in the market, we have an exciting opportunity to expand their capabilities through integrating existing sensors with supplementary ones to enable a wide variety of experiences that…
Project
Project Rumi
Project Rumi incorporates paralinguistic input into prompt-based interactions with LLMs with the objective of improving the quality of communication. Providing this context is critical to enhancing LLMs capabilities in this “AI as a copilot” era.