Cuong Nguyen

Hello! I'm Cuong đź‘‹

HCI, Agents, Applied AI.

I’m a Senior Research Scientist at Google. My work brings together human-computer interaction, creative tools, and applied AI. I build agentic AI systems that turn frontier model capabilities into structured, editable, and reliable creative workflows.

Previously, I founded Scrambo (June–November 2026), a multi-agent SDK for reliable agentic video products. I designed generate–validate–repair workflows, evaluation systems, and tools that let people inspect, compare, and refine AI-generated work. I also turned verifier feedback and successful repairs into training data for smaller models.

Previously, I was a Senior Research Scientist at Adobe Research (October 2017–June 2026). My research contributed to creative features in Adobe Express and VR video-editing tools in Premiere Pro and After Effects that received a Technology & Engineering Emmy Award in 2025. I’ve published more than 25 papers at top HCI conferences and filed 39 patents, with 19 issued.

I received my Ph.D. in Computer Science from Portland State University in 2017, advised by Professor Feng Liu. My research received Best Paper Honorable Mention awards at ACM CHI in 2013, 2015, and 2017.

I was born and raised in Ho Chi Minh City, Vietnam 🇻🇳. Outside work, I enjoy sports and fitness. My deadlift personal best is 415 lbs.

Some of my research has contributed to the following product features. I enjoy working closely with product teams to address unique customer problems, explore untapped data opportunities, and drive AI/HCI technology transfer. I find it deeply rewarding to see research translated into real-world products that impact millions of users.

2024. Animate All: Auto animate design documents. (Adobe Express, article, feature). Increased animation usage by approximately 30% after launch, reaching approximately 1.8 million monthly uses as of October 2025.
2023. Face-aware video captioning. (Adobe Express, article, feature).
360 video editing in VR. (Adobe Premiere and After Effects, feature). Received a Technology & Engineering Emmy Award in 2025.

2026

DepthScape: Authoring 2.5D Designs with Depth Estimation, Semantic Understanding, and Geometry Extraction
DepthScape: Authoring 2.5D Designs with Depth Estimation, Semantic Understanding, and Geometry Extraction

Xia Su, Cuong Nguyen, Matheus Gadelha, Jon E. Froehlich

In Proceedings of ACM DIS 2026

Visual Lyrics: Automatic Generation of Animated Lyric Videos
Visual Lyrics: Automatic Generation of Animated Lyric Videos

David Chuan-En Lin, Cuong Nguyen, Valentina Shin, Nikola Martelaro

In Proceedings of ACM IUI 2026

2025

SweeperBot: Making 3D Browsing Accessible through View Analysis and Visual Question Answering
SweeperBot: Making 3D Browsing Accessible through View Analysis and Visual Question Answering

Chen Chen, Cuong Nguyen, Alexa Siu, Ding Li, Nadir Weibel

International Journal of Human-Computer Interaction 2025

2024

MemoVis: A GenAI-Powered Tool for Creating Companion Reference Images for 3D Design Feedback
MemoVis: A GenAI-Powered Tool for Creating Companion Reference Images for 3D Design Feedback

Chen Chen, Cuong Nguyen, Thibault Groueix, Vladimir G. Kim, Nadir Weibel

ACM TOCHI. Presented at UIST 2024.

2023

PaperToPlace: Transforming Instruction Documents into Spatialized and Context-Aware Mixed Reality Experiences
PaperToPlace: Transforming Instruction Documents into Spatialized and Context-Aware Mixed Reality Experiences

Chen Chen, Cuong Nguyen, Jane Hoffswell, Jennifer Healey, Trung Bui, Nadir Weibel

In Proceedings of UIST 2023

GestureCanvas: Prototyping Compound Freehand Interaction in VR through Programming by Demonstration
GestureCanvas: Prototyping Compound Freehand Interaction in VR through Programming by Demonstration

Anika Sayara, Emily Lynn Chen, Cuong Nguyen, Robert Xiao, Dongwook Yoon

In Proceedings of UIST 2023

PoseVEC: Authoring Adaptive Pose-aware Effects Using Visual Programming and Demonstrations
PoseVEC: Authoring Adaptive Pose-aware Effects Using Visual Programming and Demonstrations

Yongqi Zhang, Cuong Nguyen, Rubaiat Habib Kazi, Lap-Fai Yu

In Proceedings of UIST 2023

VideoDoodles: Hand-Drawn Animations on Videos with Scene-Aware Canvases
VideoDoodles: Hand-Drawn Animations on Videos with Scene-Aware Canvases

Emilie Yu, Kevin Blackburn-Matzen, Cuong Nguyen, Oliver Wang, Rubaiat Habib Kazi, Adrien Bousseau

In Proceedings of ACM Transactions on Graphics (SIGGRAPH) 2023

PointShopAR: Supporting Environmental Design Prototyping Using Point Cloud in Augmented Reality
PointShopAR: Supporting Environmental Design Prototyping Using Point Cloud in Augmented Reality

Zeyu Wang, Cuong Nguyen, Paul Asente, Julie Dorsey

In Proceedings of CHI 2023

Using Online Videos as the Basis for Developing Design Guidelines: A Case Study of AR-based Assembly Instructions
Using Online Videos as the Basis for Developing Design Guidelines: A Case Study of AR-based Assembly Instructions

Niu Chen, Frances Sin, Laura Herman, Ivan Song, Dongwook Yoon

In Proceedings of ISS 2023

Warpy: Contextual and Multi-view Indirect 3D Curve Sketching in Augmented Reality
Warpy: Contextual and Multi-view Indirect 3D Curve Sketching in Augmented Reality

Rawan Alghofaili, Cuong Nguyen, Vojtch Krs, Nathan Carr, Radomir Mech, Lap-Fai Yu

In Proceedings of IEEE VR 2023

2021

Rapido: Prototyping Interactive AR Experiences through Programming by Demonstration
Rapido: Prototyping Interactive AR Experiences through Programming by Demonstration

German Leiva, Jens Emil Sloth Grnbk, Clemens Nylandsted Klokmose, Cuong Nguyen, Paul Asente, Rubaiat Habib Kazi

In Proceedings of UIST 2021

DistanciAR: Authoring Site-Specific Augmented Reality Experiences for Remote Environments
DistanciAR: Authoring Site-Specific Augmented Reality Experiences for Remote Environments

Zeyu Wang, Cuong Nguyen, Paul Asente, Julie Dorsey

In ACM CHI, 2021

2020

TransceiVR: Bridging Asymmetrical Communication Between External and VR Users
TransceiVR: Bridging Asymmetrical Communication Between External and VR Users

Balasaravanan Thoravi Kumaravel, Cuong Nguyen, Stephen DiVerdi, Bjoern Hartmann

In ACM UIST, 2020

View-Dependent Effects For 360 Virtual Reality Video
View-Dependent Effects For 360 Virtual Reality Video

Jeremy Hartmann, Stephen DiVerdi, Cuong Nguyen, Daniel Vogel

In ACM UIST, 2020

Pronto: Rapid Augmented Reality Video Prototyping Using Sketches and Enaction
Pronto: Rapid Augmented Reality Video Prototyping Using Sketches and Enaction

German Leiva, Cuong Nguyen, Rubaiat Habib Kazi, Paul Asente

In ACM CHI, 2020

Slicing Volume: Hybrid 3D/2D Multi target Selection Technique for Dense Virtual Environments
Slicing Volume: Hybrid 3D/2D Multi target Selection Technique for Dense Virtual Environments

Roberto A. Montano-Murillo, Cuong Nguyen, Rubaiat Habib Kazi, Sriram Subramanian, Stephen DiVerdi, Diego Martinez-Plasencia

In IEEE VR, 2020 (Conference Paper)

2019

Challenges and Design Considerations for Multimodal Asynchronous Collaboration in VR
Challenges and Design Considerations for Multimodal Asynchronous Collaboration in VR

Kevin Chow, Caitlin Coyiuto, Cuong Nguyen, Dongwook Yoon

In ACM CSCW, 2019

TutoriVR: A Video-Based Tutorial System for Design Applications in Virtual Reality
TutoriVR: A Video-Based Tutorial System for Design Applications in Virtual Reality

Balasaravanan Thoravi Kumaravel, Cuong Nguyen, Stephen DiVerdi, Bjoern Hartmann

In ACM CHI, 2019

2012 - 2018

Depth Conflict Reduction for Stereo VR Video Interfaces
Depth Conflict Reduction for Stereo VR Video Interfaces

Cuong Nguyen, Stephen DiVerdi, Aaron Hertzmann, Feng Liu

In ACM CHI, 2018

CollaVR: Collaborative In-Headset Review for VR Video
CollaVR: Collaborative In-Headset Review for VR Video

Cuong Nguyen, Stephen DiVerdi, Aaron Hertzmann, Feng Liu

In ACM UIST, 2017

Vremiere: In-headset Virtual Reality Video Editing
Vremiere: In-headset Virtual Reality Video Editing

Cuong Nguyen, Stephen DiVerdi, Aaron Hertzmann, Feng Liu

In ACM CHI, 2017 🏆 (best paper honorable mention award)

Gaze-based Notetaking for Learning from Lecture Videos
Gaze-based Notetaking for Learning from Lecture Videos

Cuong Nguyen, Feng Liu

In ACM CHI, 2016

Making Software Tutorial Video Responsive
Making Software Tutorial Video Responsive

Cuong Nguyen, Feng Liu

In ACM CHI, 2015 🏆 (best paper honorable mention award)

Hotspot: Making Computer Vision More Effective for Human Video Surveillance
Hotspot: Making Computer Vision More Effective for Human Video Surveillance

Cuong Nguyen, Wu-chi Feng, Feng Liu

Information Visualization

Direct Manipulation Video Navigation on Touch Screens
Direct Manipulation Video Navigation on Touch Screens

Cuong Nguyen, Yuzhen Niu, Feng Liu

In ACM MobileHCI, 2014

Direct Manipulation Video Navigation in 3D
Direct Manipulation Video Navigation in 3D

Cuong Nguyen, Yuzhen Niu, Feng Liu

In ACM CHI, 2013 🏆 (best paper honorable mention award)

Video Summagator: An Interface for Video Summarization and Navigation
Video Summagator: An Interface for Video Summarization and Navigation

Cuong Nguyen, Yuzhen Niu, Feng Liu

In ACM CHI, 2012