Bryan Wang

Research Interests

Human-AI Interaction · Creativity Support Tools · Video & Audio Production · LLM Agents & UI Automation

Education

• Ph.D. in Computer Science · University of Toronto · Advisor: Tovi Grossman2024

  Thesis: Human-AI Systems for Creating, Consuming, and Interacting with Digital Content

• M.Sc. in Computer Science · University of Toronto · Advisor: Tovi Grossman2020
• B.Sc. in Computer Science · National Taiwan University2018

Experience

• Adobe Research

  Research Scientist II (Senior)

  Jun 2026 to Present

  Research Scientist

  Sep 2024 to Jun 2026

  Pioneering generative-AI creative tools end-to-end, from original research and 0→1 prototypes to production features in Adobe products. Currently leading R&D on generative video creation agents.

• Research Intern · Meta Reality Labs - Research

  Summer 2023

  Created LAVE, an LLM-powered video editing agent that plans, searches, and edits footage through natural conversation.

• Student Researcher · Google Research

  Summer 2022

  Among the first to show LLMs could enable conversational interaction with GUI through prompting alone, no task-specific training required.

• Research Intern · Adobe Research

  Summer 2021, Winter 2022

  Built ROPE, an NLP-driven tool that automatically condenses voice recordings into social-media-ready audio stories while preserving narrative flow.

• Research Intern · Google Research

  Summer 2020, Winter 2021

  Created a 110K-summary, 22K-screen multimodal dataset and trained vision-language models to automatically summarize mobile UIs.

Shipped Products

• Precision Flow · Adobe Firefly · Research Lead (0→1)

  2026

  A Firefly image editing feature that renders every edit as a continuous spectrum. Glide a slider from A to B and land anywhere in between.

• Generate Soundtrack · Adobe Firefly · Contributor

  2025

  A Firefly audio tool that generates commercially-safe instrumental soundtracks from a text prompt or video. Music that fits your footage, automatically.

Publications

28 publications · 1,500+ citations · h-index 16 · See Google Scholar

• Dramarrator: Object-Based Audio Editing for Audio Drama Production from Books

  UIST 2026

  Karim Benharrak, Oriol Nieto, Bryan Wang, Zeyu Jin, Amy Pavel

• Sidekick: Designing Ambient Communication for Effective Multitasking with Computer Use Agents

  UIST 2026

  Ruei-Che Chang, Wenqian Xu, Ding Li, Bryan Wang, Anhong Guo

• Vidmento: Creating Video Stories Through Context-Aware Expansion With Generative Video

  CHI 2026

  Catherine Yeh, Anh Truong, Mira Dontcheva, Bryan Wang

• VidTune: Creating Video Soundtracks with Generative Music and Contextual Thumbnails

  CHI 2026

  Mina Huh, Ailie C. Fraser, Dingzeyu Li, Mira Dontcheva, Bryan Wang

• Script2Screen: Supporting Dialogue Scriptwriting with Interactive Audiovisual Generation

  IUI 2026

  Zhecheng Wang, Jiaju Ma, Eitan Grinspun, Tovi Grossman, Bryan Wang

• MapStory: Prototyping Editable Map Animations with LLM Agents

  UIST 2025

  Aditya Gunturu, Ben Pearman, Keiichi Ihara, Morteza Faraji, Bryan Wang, Rubaiat Habib Kazi, Ryo Suzuki

• SimTube: Generating Simulated Video Comments through Multimodal AI and User Personas

  IUI 2025

  Yu-Kai Hung, Yun-Chien Huang, Ting-Yu Su, Yen-Ting Lin, Lung-Pan Cheng, Bryan Wang*, Shao-Hua Sun* (∗Equal advisory contribution.)

• GazeNoter: Co-Piloted AR Note-Taking via Gaze Selection of LLM Suggestions to Match Users' Intentions

  CHI 2025

  Hsin-Ruey Tsai, Shih-Kang Chiu, Bryan Wang

• KnowledgeTrail: Generative Timeline for Exploration and Sensemaking of Historical Events and Knowledge Formation

  arXiv 2025

  Sangho Suh, Rahul Hingorani, Bryan Wang, Tovi Grossman

• LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing

  IUI 2024

  Bryan Wang, Yuliang Li, Zhaoyang Lv, Haijun Xia, Yan Xu, Raj Sodhi

• SynthScribe: Deep Multimodal Tools for Synthesizer Sound Retrieval and Exploration

  IUI 2024

  Stephen Brade, Bryan Wang, Mauricio Sousa, Gregory Lee Newsome, Sageev Oore, Tovi Grossman

  Jazzki Human-Machine Creativity Award, First Place

• Flowy: Supporting UX Design Decisions Through AI-Driven Pattern Annotation in Multi-Screen User Flows

  arXiv 2024

  Yuwen Lu, Ziang Tong, Qinyi Zhao, Yewon Oh, Bryan Wang, Toby Jia-Jun Li

• A Zero-Shot Language Agent for Computer Control with Structured Reflection

  EMNLP (Findings) 2023

  Tao Li, Gang Li, Zhiwei Deng, Bryan Wang, Yang Li

• Democratizing Content Creation and Consumption through Human-AI Copilot Systems

  UIST Doctoral Consortium 2023

  Bryan Wang

• Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models

  UIST 2023

  Stephen Brade, Bryan Wang, Mauricio Sousa, Sageev Oore, Tovi Grossman

• Enabling Conversational Interaction with Mobile UI using Large Language Models

  CHI 2023

  Bryan Wang, Gang Li, Yang Li

• Stargazer: An Interactive Camera Robot for Capturing How-To Videos Based on Subtle Instructor Cues

  CHI 2023

  Jiannan Li, Mauricio Sousa, Bryan Wang, Paula Akemi Aoyagui, Nicole Yu, Angela Yang, Ravin Balakrishnan, Anthony Tang, Tovi Grossman

• Creepy Assistant: Development and Validation of a Scale to Measure the Perceived Creepiness of Voice Assistants

  CHI 2023

  Rachel Phinnemore, Mohi Reza, Blaine Lewis, Karthik Mahadevan, Bryan Wang, Michelle Annett, Daniel Wigdor

• Record Once, Post Everywhere: Automatic Shortening of Audio Stories for Social Media

  UIST 2022

  Bryan Wang, Zeyu Jin, Gautham Mysore

• Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning

  UIST 2021

  Bryan Wang, Gang Li, Xin Zhou, Zhourong Chen, Tovi Grossman, Yang Li

• Soloist: Generating Mixed-Initiative Tutorials from Existing Guitar Instructional Videos Through Audio Processing

  CHI 2021

  Bryan Wang, Meng Yu Yang, Tovi Grossman

• AIive: Interactive Visualization and Sonification of Neural Networks in Virtual Reality

  AIVR (Demo) 2021

  Zhuoyue Lyu, Jiannan Li, Bryan Wang

  Best Presentation Award

• BlyncSync: Enabling Multimodal Smartwatch Gestures with Synchronous Touch and Blink

  CHI 2020

  Bryan Wang, Tovi Grossman

• PerformanceNet: Score-to-Audio Music Generation with Multi-Band Convolutional Residual Network

  AAAI 2019

  Bryan Wang, Yi-Hsuan Yang

• Demonstration of PerformanceNet: A Convolutional Neural Network Model for Score-to-Audio Music Generation

  IJCAI (Demo) 2019

  Yu-Hua Chen, Bryan Wang, Yi-Hsuan Yang

• ActiveErgo: Automatic and Personalized Ergonomics Using Self-Actuating Furniture

  CHI 2018

  Yu-Chian Wu, Te-Yen Wu, Paul Taele, Bryan Wang, Jun-You Liu, Pin-Sung Ku, Po-En Lai, Mike Y. Chen

• CircuitSense: Automatic Sensing of Physical Circuits and Generation of Virtual Circuits to Support Software Tools

  UIST 2017

  Te-Yen Wu, Bryan Wang, Jiun-Yu Lee, Hao-Ping Shen, Yu-Chian Wu, Yu-An Chen, Pin-Sung Ku, Ming-Wei Hsu, Yu-Chih Lin, Mike Y. Chen

• CircuitStack: Supporting Rapid Prototyping and Evolution of Electronic Circuits

  UIST 2016

  Chiuan Wang, Hsuan-Ming Yeh, Bryan Wang, Te-Yen Wu, Hsin-Ruey Tsai, Rong-Hao Liang, Yi-Ping Hung, Mike Y. Chen

  Best Talk Award

Honours & Awards

• Jazzki Human-Machine Creativity Award, First Place · SynthScribe2024
• Special Recognition for Outstanding Reviews · CHI '22–'24, UIST '22–'24, '26 · 12 recognitions2022 to 2026
• Wolfond Scholarship · University of Toronto · $5,000 CAD2023 to 2024
• DiDi Graduate Student Award in Computer Science · University of Toronto · $10,000 CAD, two years2021 to 2023
• Snap Creative Challenge Award · Snap Inc.2022
• Apple AI/ML Fellowship Nominee · University of Toronto · one of three at the school2022
• Best Presentation Award · IEEE AIVR 2021 · AIive2021
• Best Talk Award · ACM UIST 2016 · CircuitStack2016
• James Dyson Award, World Finalist · James Dyson Foundation2016
• AI and CS Research Excellence Scholarship · Appier Inc.2017, 2018

Mentoring & Advising

Academic Service

• Program Committee · ACM UIST'23, '24, '25
• Program Committee · ACM CHI'25, '26
• Program Committee · ACM IUI'25, '26
• Program Committee · ACM DIS'25
• Organizer · ICML Workshop on AI & HCI'23

Selected Press

• Adobe Brings Chat to Firefly AI Assistant Across Creative Cloud Apps · ForbesApril 2026
• Adobe's new Firefly AI Assistant could forever change the way you use its apps · Fast CompanyApril 2026
• New image editing features in Adobe Firefly get you from 'almost there' to 'exactly right' · Adobe BlogApril 2026
• Vidmento: Filling the gaps in your video story with generative AI · Adobe ResearchApril 2026
• When the Music Fits: VidTune Helps Video Creators Find the Right Soundtrack · Adobe ResearchApril 2026
• Adobe's new AI audio tools can add soundtracks and voice-overs to videos · The VergeOct. 2025
• Adobe's Firefly can now use AI to generate soundtracks, speech and video · EngadgetOct. 2025
• Tuning into Tomorrow: AI can help musicians compose and create new sounds. Is it just another music-making tool – or something else? · University of Toronto MagazineApril 2024
• Revolutionizing Digital Creativity: LAVE's AI Merges with Video Editing for Novice-Friendly Innovation · BNN BreakingFeb. 2024
• Revolutionizing Video Editing: How LAVE and AI are Democratizing Creative Expression · MarkTechPostFeb. 2024
• When Sora's explosive video generation emerged, Meta began using an agent to automatically edit videos. (In Chinese) · Heart of MachineFeb. 2024
• Enabling conversational interaction on mobile with LLMs · Google AI BlogMay. 2023
• This Artificial Intelligence (AI) Research Shows The Feasibility Of Enabling Conversational Interactions With Mobile UIs Using Large Language Models LLMs · MarkTechPostMar. 2023
• Developed by the University of Toronto, Soloist turns YouTube musical instrument lesson videos into personalized instruction. (In Japanese) · ITmediaFeb. 2021

Skills

Research Areas

Human-AI Interaction · Creativity Support Tools · Video & Audio Production · LLM Agents & UI Automation

Methods

Interactive system prototyping · Dataset curation & annotation · Model fine-tuning & evaluation · Technical writing & paper authorship

Engineering

Python · TypeScript / React / Next.js / CSS · PyTorch · LLM tooling

Languages

English (fluent) · Mandarin Chinese (native)