Mina Huh

@minahuh.bsky.social

Ph.D. student @UTCompSci | Google Ph.D. Fellow | Research Scientist Intern @AdobeResearch | GenAI for Creativity & Accessibility

Recent AI models can suggest endless video edits, offering many alternatives to video creators. But how can we easily sift through them all? In our #CHI2025 paper, we propose VideoDiff, an AI video editing tool designed for editing with alternatives.

Screenshot of the paper with the author list and the teaser figure. Author list: Mina Huh, Dingzeyu Li, Kim Pimmel, Hijung Valentina Shin, Amy Pavel, Mira Dontcheva.
Teaser figure shows the workflow with VideoDiff with three steps: (1). VideoDiff supports easy comparison by aligning videos and highlighting differences using timeline and transcript views (2). Users can narrow down options by sorting and further customize them by refining and regenerating AI suggestions (3). Timelines and transcripts of videos are color highlighted to show which parts are command and unique.