# David Chuan-En Lin

> David Chuan-En Lin researches human-computer interaction and builds tools that help designers steer generative AI. PhD in Human-Computer Interaction from Carnegie Mellon University.

## Identity

- Name: David Chuan-En Lin (林傳恩)
- Role: Postdoctoral Scholar at the Stanford Institute for Human-Centered Artificial Intelligence (HAI)
- Advisors: Sean Follmer, Hari Subramonyam
- PhD: Human-Computer Interaction, Carnegie Mellon University, Human-Computer Interaction Institute (advisor: Nikolas Martelaro), 2026
- BEng: Computer Science, Hong Kong University of Science and Technology (HKUST)
- [ORCID](https://orcid.org/0000-0003-0116-0463): 0000-0003-0116-0463
- [DBLP](https://dblp.org/pid/293/9726): 293/9726
- [Wikidata](https://www.wikidata.org/wiki/Q131129285): Q131129285

## Research Focus

Steerable Abstractions — designing intuitive, controllable representations that let humans steer AI at the right abstraction level.

Core areas:

- Human-Computer Interaction (HCI)
- Design Tools
- Human-AI Interaction
- Creativity Support Tools
- Generative AI
- Computer Vision

## Publications (First Author)

- [Visual Lyrics: Generating Animated Text for Music Lyric Videos with an Augmented Text Editor](https://dlin.org/visuallyrics): IUI 2026. Visual Lyrics generates animated text for music lyric videos with an augmented text editor. It combines music analysis and LLM-generated animation code, with a public dataset of over 300 creative text animations. [paper](https://dlin.org/papers/visuallyrics.pdf), [dataset](https://visual-lyrics-dataset.vercel.app/), [video](https://www.youtube.com/watch?v=SUqdSGdQewc), [doi](https://doi.org/10.1145/3742413.3789072)
- [Inkspire: Supporting Design Exploration with Generative AI through Analogical Sketching](https://dlin.org/inkspire): CHI 2025. Inkspire helps product designers explore ideas with AI-assisted sketching, analogical inspiration, and a sketch-to-design-to-sketch feedback loop. [paper](https://arxiv.org/pdf/2501.18588), [video](https://www.youtube.com/watch?v=YQuvMm4AXBY), [doi](https://doi.org/10.1145/3706598.3713397)
- [Jigsaw: Supporting Designers to Prototype Multimodal Applications by Chaining AI Foundation Models](https://dlin.org/jigsaw): CHI 2024. Jigsaw lets designers build creative AI workflows by combining models for different tasks and media with compatible puzzle pieces. [paper](https://arxiv.org/pdf/2310.08574), [code](https://github.com/chuanenlin/jigsaw), [video](https://www.youtube.com/watch?v=Q32rmYdNGPQ), [doi](https://doi.org/10.1145/3613904.3641920)
- [VideoMap: Supporting Video Editing Exploration, Brainstorming, and Prototyping in the Latent Space](https://dlin.org/videomap): C&C 2024. VideoMap helps video editors organize footage, find transitions, and prototype rough cuts by exploring video frames on a visual map. [paper](https://arxiv.org/pdf/2211.12492), [video](https://www.youtube.com/watch?v=U8SiyZL4qnk), [doi](https://doi.org/10.1145/3635636.3656192)
- [Videogenic: Identifying Highlight Moments in Videos with Professional Photographs as a Prior](https://dlin.org/videogenic): C&C 2024. Videogenic finds video highlights using photographs as examples of moments to look for. Editors can use a photo collection to create highlight videos for different activities. [paper](https://arxiv.org/pdf/2211.12493), [video](https://www.youtube.com/watch?v=uFBWXn5sqLM), [doi](https://doi.org/10.1145/3635636.3656186)
- [Soundify: Matching Sound Effects to Video](https://dlin.org/soundify): UIST 2023. Soundify matches sound effects to video, synchronizes them with the action, and adjusts panning and volume to create spatial audio. [paper](https://arxiv.org/pdf/2112.09726.pdf), [code](https://github.com/chuanenlin/soundify), [demo](http://soundify.cc), [video](https://www.youtube.com/watch?v=VhsD699oslM), [doi](https://doi.org/10.1145/3586183.3606823)
- [Learning Personal Style from Few Examples](https://dlin.org/pseudoclient): DIS 2021. PseudoClient learns personal graphic design preferences from a handful of examples to help designers understand a client’s visual style. [paper](https://arxiv.org/pdf/2105.14457.pdf), [video](https://www.youtube.com/watch?v=IiuO6IUN9rY), [doi](https://doi.org/10.1145/3461778.3462115)
- [ARchitect: Building Interactive Virtual Experiences from Physical Affordances by Bringing Human-in-the-Loop](https://dlin.org/architect): CHI 2020. ARchitect lets an assistant use augmented reality to map physical objects to virtual objects with matching interactions, so a VR player can use their surroundings. [paper](https://dlin.org/papers/architect-chi2020.pdf), [video](https://www.youtube.com/watch?v=Dh5urSon4lQ), [doi](https://doi.org/10.1145/3313831.3376614)

## Publications (Co-Author)

- [Tracing Creativity: A Design Space For Creative Activity Traces in HCI](https://dl.acm.org/doi/pdf/10.1145/3772318.3791263): CHI 2026, led by Noor Hammad. We reviewed 133 creativity systems to map how creator activity traces are captured and used, providing a design space for leveraging trace data in future creativity tools. [doi](https://doi.org/10.1145/3772318.3791263)
- [BioSpark: Beyond Analogical Inspiration to LLM-augmented Transfer](https://arxiv.org/pdf/2503.09838): CHI 2025, Best Paper Honorable Mention, led by Hyeonsu Kang. We developed an interactive system that helps designers discover analogical biology inspirations and transfer them to target domains. [video](https://www.youtube.com/watch?v=9GhcQt1wgB8), [doi](https://doi.org/10.1145/3706598.3714053)
- [NoTeeline: Supporting Real-Time, Personalized Notetaking with LLM-Enhanced Micronotes](https://arxiv.org/pdf/2409.16493): IUI 2025, led by Faria Huq. We built an interactive notetaking tool that lets users write quick keypoints while watching educational videos then automatically expands them into full notes. [code](https://github.com/oaishi/NoTeeline), [video](https://www.youtube.com/watch?v=UUWTUbET86I), [doi](https://doi.org/10.1145/3708359.3712086)
- [Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition](https://danielchyeh.github.io/Gen4Gen/): BMVC 2025, led by Chun-Hsiao Yeh. We developed a pipeline and dataset for benchmarking multi-concept personalized text-to-image diffusion models. [paper](https://arxiv.org/pdf/2402.15504), [code](https://github.com/louisYen/Gen4Gen), [video](https://danielchyeh.github.io/Gen4Gen/static/images/gen4gen_video.mp4), [doi](https://doi.org/10.48550/arXiv.2402.15504)
- [SeqDynamics: Visual Analytics for Evaluating Online Problem-solving Dynamics](https://www.xiameng.org/EuroVIS2020_SeqDynamics.pdf): EuroVis 2020, led by Meng Xia. We developed an interactive visual analytics system for instructors to evaluate problem-solving dynamics of student learners. [video](https://www.youtube.com/watch?v=KCTSZpvp2W8), [doi](https://doi.org/10.1111/cgf.13998)
- [Learning to Film from Professional Human Motion Videos](https://openaccess.thecvf.com/content_CVPR_2019/papers/Huang_Learning_to_Film_From_Professional_Human_Motion_Videos_CVPR_2019_paper.pdf): CVPR 2019, led by Chong Huang. We developed an automatic drone cinematography system by learning from cinematic drone videos captured by professionals. [video](https://www.youtube.com/watch?v=20ny7zsRED4), [doi](https://doi.org/10.1109/CVPR.2019.00437)

## Contact

- [Website](https://dlin.org): dlin.org
- [Google Scholar](https://scholar.google.com/citations?user=0XhFbQQAAAAJ): publication and citation record
- [GitHub](https://github.com/chuanenlin): code and open-source projects
- [X](https://twitter.com/chuanenlin): @chuanenlin
- [LinkedIn](https://linkedin.com/in/chuanenlin): professional profile
- Email: dcelin@stanford.edu

## Site Pages

- [Homepage](https://dlin.org): bio, research interests, full publication list
- [Visual Lyrics](https://dlin.org/visuallyrics): project page
- [Inkspire](https://dlin.org/inkspire): project page
- [Jigsaw](https://dlin.org/jigsaw): project page
- [VideoMap](https://dlin.org/videomap): project page
- [Videogenic](https://dlin.org/videogenic): project page
- [Soundify](https://dlin.org/soundify): project page
- [PseudoClient](https://dlin.org/pseudoclient): project page
- [ARchitect](https://dlin.org/architect): project page
- [Experiments](https://dlin.org/experiments): side projects and experiments