# David Chuan-En Lin - Academic Website

> Context for AI assistants and LLM crawlers.

## Identity

- Name: David Chuan-En Lin (林傳恩)
- Role: Postdoctoral Scholar at Stanford University
- Advisors: Sean Follmer, Hari Subramonyam
- PhD: Carnegie Mellon University, Human-Computer Interaction Institute (advisor: Nikolas Martelaro)
- BS: Hong Kong University of Science and Technology (HKUST)

## 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
- Accessibility
- Generative AI
- Computer Vision

## Publications (First Author)

### Visual Lyrics (IUI 2026)
- Title: Visual Lyrics: Generating Animated Text for Music Lyric Videos with an Augmented Text Editor
- URL: https://dlin.org/visuallyrics
- Paper: https://dlin.org/papers/visuallyrics.pdf
- Description: We developed a tool for generating animated lyric videos using an augmented text editor interface with an LLM-driven animation pipeline.

### Inkspire (CHI 2025)
- Title: Inkspire: Supporting Design Exploration with Generative AI through Analogical Sketching
- URL: https://dlin.org/inkspire
- Paper: https://arxiv.org/pdf/2501.18588
- Description: We developed a sketching tool that allows designers to sketch product designs with analogical inspirations and AI-generated shadows beneath the canvas.

### Jigsaw (CHI 2024)
- Title: Jigsaw: Supporting Designers to Prototype Multimodal Applications by Chaining AI Foundation Models
- URL: https://dlin.org/jigsaw
- Paper: https://arxiv.org/pdf/2310.08574
- Code: https://github.com/chuanenlin/jigsaw
- Description: We developed a tool for combining AI models across different capabilities and modalities by combining them like puzzle pieces.

### VideoMap (C&C 2024)
- Title: VideoMap: Supporting Video Editing Exploration, Brainstorming, and Prototyping in the Latent Space
- URL: https://dlin.org/videomap
- Paper: https://arxiv.org/pdf/2211.12492
- Description: We developed a proof-of-concept video editing interface that operates on video frames projected onto a latent space.

### Videogenic (C&C 2024)
- Title: Videogenic: Identifying Highlight Moments in Videos with Professional Photographs as a Prior
- URL: https://dlin.org/videogenic
- Paper: https://arxiv.org/pdf/2211.12493
- Description: We developed a system for detecting highlight moments by leveraging photographs taken by photographers.

### Soundify (UIST 2023)
- Title: Soundify: Matching Sound Effects to Video
- URL: https://dlin.org/soundify
- Paper: https://arxiv.org/pdf/2112.09726.pdf
- Code: https://github.com/chuanenlin/soundify
- Demo: http://soundify.cc
- Description: We developed a system to assist video editors in adding content-aware spatial sound effects to video.

### PseudoClient (DIS 2021)
- Title: Learning Personal Style from Few Examples
- URL: https://dlin.org/pseudoclient
- Paper: https://arxiv.org/pdf/2105.14457.pdf
- Description: We developed a model for learning personal graphic design style from a small handful of examples.

### ARchitect (CHI 2020)
- Title: ARchitect: Building Interactive Virtual Experiences from Physical Affordances by Bringing Human-in-the-Loop
- URL: https://dlin.org/architect
- Paper: https://chuanenlin.github.io/papers/architect-chi2020.pdf
- Description: We explored an asymmetric workflow of an AR builder and a VR player for creating VR experiences that incorporate real-world interaction affordances.

## Publications (Co-Author)

### Tracing Creativity (CHI 2026)
- Title: Tracing Creativity: A Design Space For Creative Activity Traces in HCI
- Lead: Noor Hammad
- Description: 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.

### Biospark (CHI 2025, Best Paper Honorable Mention)
- Title: BioSpark: Beyond Analogical Inspiration to LLM-augmented Transfer
- Lead: Hyeonsu Kang
- Description: We developed an interactive system that helps designers discover analogical biology inspirations and transfer them to target domains.

### NoTeeline (IUI 2025)
- Title: NoTeeline: Supporting Real-Time, Personalized Notetaking with LLM-Enhanced Micronotes
- Lead: Faria Huq
- Description: We built an interactive notetaking tool that lets users write quick keypoints while watching educational videos then automatically expands them into full notes.

### Gen4Gen (BMVC 2025)
- Title: Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition
- Lead: Chun-Hsiao Yeh
- Description: We developed a pipeline and dataset for benchmarking multi-concept personalized text-to-image diffusion models.

### SeqDynamics (EuroVis 2020)
- Title: SeqDynamics: Visual Analytics for Evaluating Online Problem-solving Dynamics
- Lead: Meng Xia
- Description: We developed an interactive visual analytics system for instructors to evaluate problem-solving dynamics of student learners.

### Learning Drone (CVPR 2019)
- Title: Learning to Film from Professional Human Motion Videos
- Lead: Chong Huang
- Description: We developed an automatic drone cinematography system by learning from cinematic drone videos captured by professionals.

## Contact

- Email: dcelin@stanford.edu
- Website: https://dlin.org
- Google Scholar: https://scholar.google.com/citations?user=0XhFbQQAAAAJ
- GitHub: https://github.com/chuanenlin
- Twitter/X: https://twitter.com/chuanenlin
- LinkedIn: https://linkedin.com/in/chuanenlin

## Site Pages

- / — Homepage with bio, research, publications
- /visuallyrics — Visual Lyrics project page
- /inkspire — Inkspire project page
- /jigsaw — Jigsaw project page
- /videomap — VideoMap project page
- /videogenic — Videogenic project page
- /soundify — Soundify project page
- /pseudoclient — PseudoClient project page
- /architect — ARchitect project page
- /experiments — Side projects and experiments