I'm looking for research interns and collaborators in AI-assisted filmmaking, generative video authoring, multimodal understanding, and accessible creative tools. If your work overlaps, I'd love to hear from you.
How to reach me and send your CV →About
I build AI systems for filmmaking and video creation, combining generative video, multimodal understanding, human-computer interaction, graphics, and audio. My goal is to advance how people author, edit, animate, and tell stories, and to make creative tools more collaborative, accessible, and production-ready.
I am a Senior Staff Research Manager and Scientist at Adobe Research. I earned my Ph.D. in Computer Science from Columbia University and my B.Eng. in Computer Engineering from the Hong Kong University of Science and Technology, and I studied at ETH Zurich as an exchange student.
My work has been recognized with an Emmy Award for Technology and Engineering (2020) and two ACM UIST Best Paper Awards (2022 and 2017), along with an ACM IUI Best Paper Award nomination (2026) and two appearances in Adobe MAX Sneaks. I was named an Adobe Distinguished Inventor in 2025.
Selected Publications
Google Scholar · DBLP- A Text-Native Interface for Generative Video Authoring Xingyu Bruce Liu, Mira Dontcheva, and Dingzeyu Li UIST 2026 · Conditionally Accepted
- Sidekick: Designing Communication for Effective Multitasking with Computer Use Agents Ruei-Che Chang, Wenqian Xu, Dingzeyu Li, Bryan Wang, and Anhong Guo UIST 2026 · Conditionally Accepted
- VidTune: Creating Video Soundtracks with Generative Music and Video-Based Thumbnails Mina Huh, C. Ailie Fraser, Dingzeyu Li, Mira Dontcheva, and Bryan Wang CHI 2026
- Rewriting Video: Text-Driven Reauthoring of Video Footage Sitong Wang, Anh Truong, Lydia B. Chilton, and Dingzeyu Li IUI 2026 · Best Paper Award Candidate
- Morae: Proactively Pausing UI Agents for User Choices Yi-Hao Peng, Dingzeyu Li, Jeffrey P. Bigham, and Amy Pavel UIST 2025
- VideoMix: Aggregating How-To Videos for Task-Oriented Learning Saelyne Yang, Anh Truong, Juho Kim, and Dingzeyu Li IUI 2025
- VideoDiff: Human-AI Video Co-Creation with Alternatives Mina Huh, Dingzeyu Li, Kim Pimmel, Hijung Valentina Shin, Amy Pavel, and Mira Dontcheva CHI 2025
- PodReels: Human-AI Co-Creation of Video Podcast Teasers Sitong Wang, Zheng Ning, Anh Truong, Mira Dontcheva, Dingzeyu Li, and Lydia B. Chilton DIS 2024
- ReelFramer: Human-AI Co-Creation for News-to-Video Translation Sitong Wang, Samia Menon, Tao Long, Keren Henderson, Dingzeyu Li, and collaborators CHI 2024
- CrossA11y: Identifying Video Accessibility Issues via Cross-modal Grounding Xingyu Bruce Liu, Ruolin Wang, Dingzeyu Li, Xiang Anthony Chen, and Amy Pavel UIST 2022 · Best Paper Award
- MakeItTalk: Speaker-Aware Talking-Head Animation Yang Zhou, Xintong Han, Eli Shechtman, Jose Echevarria, Evangelos Kalogerakis, and Dingzeyu Li ACM TOG / SIGGRAPH Asia 2020
Selected Public Product Releases
- Precision Flow Generates a range of image variations from a single prompt in Adobe Firefly, with a slider to dial in the best result.
- GenAI Alt Text Automatically writes alt text for AI-generated images in Adobe Firefly, making them usable by blind and low-vision creators.
- Adobe Express Clip Maker Automatically turns long-form videos and podcasts into social-media-ready short clips in Adobe Express.
- Project Blink Edits video as easily as a transcript, with visual search to jump to any moment.
- Animate from Audio Turns a voice recording into a lip-synced animated character in Adobe Express.
- Speech-Aware Animation Generates expressive character animation directly from a speech recording, faster than real time.
- Project On the Beat Automatically edits and syncs video motion to the beat of a music track.
- Project Sweet Talk Animates a single still portrait into a talking face from an audio clip.
- Automatic Lipsync Automatically lip-syncs animated characters to recorded dialogue in Adobe Character Animator.
Research Mentoring and Students
I mentor research interns and student collaborators working on AI-assisted filmmaking, generative video authoring, accessibility, multimodal understanding, animation, and audio.
Patents and Invention
I am a named inventor on 27 issued U.S. patents spanning AI-assisted video editing, multimodal search, animation, audio, and creative interfaces. See the current patent search for the latest record.
- Generative video assembly 12,640,168 (2026)
- Text-native video editing and multimodal search 12,367,238, 12,206,930 (2025)
- Speech-driven performance and gesture animation 12,347,135 (2025), 11,776,188 (2023), 11,417,041 (2022)
- Creative video interface designs D1,056,944, D1,056,943, D1,056,942, D1,056,928 (2025)
- Hierarchical video segmentation, navigation, and interaction 12,014,548, 11,922,695, 11,893,794 (2024), 11,450,112 (2022)
- Video timeline, metadata, tile, and cluster interaction 11,995,894, 11,899,917, 11,887,629, 11,880,408 (2024), 11,631,434, 11,630,562 (2023)
- Snap-point and thumbnail video segmentation 12,033,669, 11,887,371 (2024)
- Scene-aware audio and audiovisual timing 11,812,254, 11,682,238 (2023), 11,190,898 (2021)
- Audio-visual cue recognition 12,125,317 (2024)
- Image acquisition and domain adaptation 11,908,036 (2024)
Service and Community
I served as co-chair of the Adobe Research Fellowship program from 2019–2022. I have served on international program committees for CHI, Eurographics, Graphics Interface, and ACM Multimedia, and as a reviewer for UIST, CHI, SIGGRAPH, CVPR, ICCV, and related venues.
Outside work, I host Not Just Research in English and 李丁聊天室 (YouTube) in Chinese, with conversations about research, careers, and life.
