A Text-Native Interface for Generative Video Authoring
Honorable Mention for Best Paper Award
Senior Principal Scientist
Seattle, WA
Mira Dontcheva is a Senior Principal Scientist at Adobe Research focusing on Human-AI interaction and creative tools. She leads the STORIE Lab (Storytelling and Interactive Experiences), which explores how people and AI agents can create videos together. Mira and her team design tools that make creation easier, more fun, and accessible to a broader range of people, from text-based and agentic video editing to generative soundtracks and AI-assisted story development. She is passionate about multimodal interaction, AI that brings people together, and experiences at the intersection of the physical and digital worlds.
Her lab’s research regularly ships in Adobe products. Recent examples include Quick Cut, which turns raw clips into a structured first cut and is available in the Firefly video editor, the Firefly AI Assistant, and Adobe’s connectors for AI assistants such as Claude, ChatGPT, and Gemini. Earlier, she helped lead Project Blink, an AI-powered video editor for the web unveiled at Adobe MAX, and her research has shipped in Photoshop, Premiere, and Behance.
Mira has published more than 60 peer-reviewed papers, including award-winning work at CHI and UIST, and holds more than 55 US patents. She received her M.S. and Ph.D. in computer science from the University of Washington, advised by David Salesin, Michael Cohen, and Steven Drucker, and her B.S.E. in computer engineering from the University of Michigan.
Honorable Mention for Best Paper Award
Honorable Mention
Newly published work from Adobe researchers has been honored with a Best Paper Honorable Mention Award at this year’s ACM Symposium on User Interface Software and Technology (UIST). The paper, A Text-Native Interface for Generative Video Authoring, describes an experimental tool, and a new paradigm, that allows users to create and refine generative videos using text, all within a single document.
November 5, 2026The experimental technology VidTune generates multiple music tracks from a text prompt and produces visual "contextual thumbnails" for each one, letting creators compare options at a glance.
April 9, 2026Vidmento is an experimental AI-assisted video authoring tool from Adobe Research, accepted at CHI 2026, that helps creators build complete video stories by blending their own captured footage with contextually generated clips — preserving narrative continuity and creative intent throughout.
April 3, 2026Clip Maker, a collaboration between Adobe Research and Adobe Express, combines cutting-edge AI with intuitive design to help creators craft social-ready clips in seconds. Check out the behind-the-scenes story!
November 6, 2025Principal Scientist and Research Manager Mira Dontcheva shares how her work in human computer interaction at Adobe Research has evolved. Her current focus: Livestreaming.
April 21, 2020