Hey there! 👋 I am a 6th year Computer Science Ph.D. student at Carnegie Mellon University, working with Professor Nik Martelaro and Toyota. I graduated with a Bachelors in Computer Science from HKUST (full scholarship) and was fortunate to work with Professor Xiaojuan Ma and Professor Kwang-Ting Cheng. Previously, I did three research internships with Adobe and Runway. Here is a demo reel of my research. I also enjoy documenting my travels as a hobby.

My Research

I build AI-augmented tools for designers to co-create with AI capabilities using intuitive high-level abstractions. For example, ✏️ sketching with AI-generated scaffolding, 🧩 assembling AI model puzzle pieces, and 🗺️ exploring latent space maps. I work on both designing interfaces and building ML pipelines to support these abstractions, coming from my mixed background in HCI and Computer Vision.

I work on projects spanning various modalities, including video, image, 3D, text, audio, and sketching. A large thread of my research has been on AI-augmented video creation tools, including tools for adding sound effects to visuals, detecting highlight moments, and organizing video footage.

My research impacts design practice by blending AI capabilities into designers' natural workflows, improving designers' creative exploration and productivity.

Papers

Inkspire: Supporting Design Exploration with Generative AI through Analogical Sketching

CHI '25

David Chuan-En Lin, Hyeonsu Kang, Nikolas Martelaro, Aniket Kittur, Yan-Ying Chen, Matthew Hong

We developed a sketching tool that allows designers to sketch product designs with analogical inspirations and AI-generated shadows beneath the canvas.
PaperVideoTalkCite

Visual Lyrics: Automatic Generation of Animated Lyric Videos

Preprint

David Chuan-En Lin, Cuong Nguyen, Hijung Valentina Shin, Nikolas Martelaro

We developed a code-driven animated lyrics generation pipeline with a text-based interface for creative control.
PreprintWebpageVideo

Jigsaw: Supporting Designers to Prototype Multimodal Applications by Chaining AI Foundation Models

CHI '24

David Chuan-En Lin, Nikolas Martelaro

We developed a tool for combining AI models across different capabilities and modalities by combining them like puzzle pieces.
WebpagePaperVideoCodeCite

VideoMap: Supporting Video Editing Exploration, Brainstorming, and Prototyping in the Latent Space

C&C '24

David Chuan-En Lin, Fabian Caba Heilbron, Joon-Young Lee, Oliver Wang, Nikolas Martelaro

We developed a proof-of-concept video editing interface that operates on video frames projected onto a latent space.
WebpageC&C PaperNeurIPS PaperVideoCite

Videogenic: Identifying Highlight Moments in Videos with Professional Photographs as a Prior

C&C '24

David Chuan-En Lin, Fabian Caba Heilbron, Joon-Young Lee, Oliver Wang, Nikolas Martelaro

We developed a system for detecting highlight moments by leveraging photographs taken by photographers.
WebpageC&C PaperNeurIPS PaperVideoCite

Soundify: Matching Sound Effects to Video

UIST '23

David Chuan-En Lin, Anastasis Germanidis, Cristóbal Valenzuela, Yining Shi, Nikolas Martelaro

We developed a system to assist video editors in adding content-aware spatial sound effects to video.
WebpageUIST PaperNeurIPS PaperTalkDemoCodeCite

Learning Personal Style from Few Examples

DIS '21

David Chuan-En Lin, Nikolas Martelaro

We developed a model for learning personal graphic design style from a small handful of examples.
WebpagePaperTalkCite

ARchitect: Building Interactive Virtual Experiences from Physical Affordances by Bringing Human-in-the-Loop

CHI '20

Chuan-En Lin*, Ta Ying Cheng*, Xiaojuan Ma(* = equal contribution)

We explored an asymmetric workflow of an AR builder and a VR player for creating VR experiences that incorporate real-world interaction affordances.
WebpagePaperVideoCite
Co-authored Papers

BioSpark: Beyond Analogical Inspiration to LLM-augmented Transfer

CHI '25

Hyeonsu Kang, David Chuan-En Lin, Yan-Ying Chen, Matthew Hong, Nikolas Martelaro, Aniket Kittur

We developed an interactive system that helps designers discover analogical biology inspirations and transfer them to target domains.
PaperTalkCite

NoTeeline: Supporting Real-Time, Personalized Notetaking with LLM-Enhanced Micronotes

IUI '25

Faria Huq, Abdus Samee, David Chuan-En Lin, Xiaodi Alice Tang, Jeffrey Bigham

We built an interactive notetaking tool that lets users write quick keypoints while watching educational videos then automatically expands them into full notes.
PaperVideoCodeCite

Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition

BMVC '25

Chun-Hsiao Yeh, Ta-Ying Cheng, He-Yen Hsieh, Chuan-En Lin, Yi Ma, Andrew Markham, Niki Trigoni, H.T. Kung, Yubei Chen

We developed a pipeline and dataset for benchmarking multi-concept personalized text-to-image diffusion models.
WebpagePaperVideoCodeCite

SeqDynamics: Visual Analytics for Evaluating Online Problem-solving Dynamics

EuroVis '20

Meng Xia, Min Xu, Chuan-En Lin, Ta Ying Cheng, Huamin Qu, Xiaojuan Ma

We developed an interactive visual analytics system for instructors to evaluate problem-solving dynamics of student learners.
PaperVideoCite

Learning to Film from Professional Human Motion Videos

CVPR '19

Chong Huang, Chuan-En Lin, Zhenyu Yang, Yan Kong, Peng Chen, Xin Yang, Kwang-Ting Cheng

We developed an automatic drone cinematography system by learning from cinematic drone videos captured by professionals.
PaperVideoCite