About
I am a PhD candidate in the VisLab at The Hong Kong University of Science and Technology, supervised by Prof. Huamin Qu with co-supervisors Prof. Pan Hui and Prof. Anyi Rao.
My research advances visual analytics and human-centered AI for visual content creation, drawing on immersive HCI, cinematic data storytelling, and multi-agent co-creation. I am currently a visiting researcher at the University of Chicago’s Knowledge Lab, collaborating with Prof. James Evans on science-of-science projects.
My work has appeared in venues such as IEEE TVCG/VR/VIS/ISMAR, ACM UIST/WWW/MM/SIGGRAPH/CHI/CSCW, IJHCI and IJCAI. I have also served as Program Committee for The Web Conference 2026、Program Chair for the CVPR 2025 CVEU Workshop and Proceedings Chair for ACM MMSys 2026.
Approach & Goals
My research focuses on advancing human-centered AI systems for visual content creation, with the aim of improving human perception, decision-making, and interaction. Guided by the principle of the human–AI loop, I study how feedback, intent capture, and collaboration can be designed to empower creators and communities. I approach this agenda through three directions:
- Immersive HCI for Skill Training (VR/XR): Developing adaptive and data-driven training systems that accelerate learning and enhance real-world transfer.
- Cinematic Data Storytelling: Building narrative frameworks and computational models that make data-driven media more interpretable, engaging, and impactful.
- Human–AI Collaboration Systems: Designing co-creative pipelines—from script to storyboard to visual production—and expanding them into multi-agent systems for scalable and reliable media creation.
Ultimately, my goal is to center humans while shaping intelligence—making complex information more intuitive and actionable, fostering inclusive and responsible generative media, and creating innovative pathways for artistic and analytical expression.
My Journey
I completed a solo expedition across China in a pure electric vehicle, following the iconic G219 Highway. Starting from Guangzhou, I traversed Guangxi, Yunnan, Tibet, and the remote Ali region, reaching Xinjiang and the Khorgos border before returning through Urumqi, Gansu, Ningxia, Shaanxi, Hubei, and Hunan. Along the way, I stood at Everest Base Camp at 5,000 meters to witness the sunrise over Mount Everest, circled the sacred Mount Kailash, and crossed hundreds of kilometers of the Ali no-man’s land. This journey was both an exploration of China’s vast landscapes and a testament to sustainable travel powered by clean energy.
News
I presented at IEEE ISMAR 2025 on “Exploring Gaze Dynamics in VR Film Education: Gender, Avatar, and the Shift Between Male and Female Perspectives.”
📍 Session: 3DUI: Gaze 2
Oct 2025
I serve on the Program Committee for The Web Conference (WWW 2026) — Social Networks and Social Media Track.
Oct 2025
Our art paper “Algorithmic Miner: Humanity in Service – An AI-Driven VR Journey into Machine Logic” was featured in the ACM SIGGRAPH Blog interview “AI Is Not Just About Machines — It’s About People.” The piece highlights how our VR work explores hidden human labor behind AI systems and emphasizes keeping people at the center of technological narratives.
Sep 2025
I presented at ACM UIST 2025 (Busan) on “CineVision: An Interactive Pre-visualization Storyboard System for Director–Cinematographer Collaboration.”
📍 Session: Interacting with Audio and Video
Sep 2025
Our course “Generative Models for Visual Content Editing and Creation” has been accepted into the SIGGRAPH Asia 2025 Course！
Aug 2025
I served as a Proceedings Chair for ACM Multimedia Systems (MMSys) 2026！
Aug 2025
Our AI film “Mirror” has been featured in i-CABLE News television program interview.
Aug 2025
Our Siggraph 2025 art paper has been highlighted by SIGGRAPH 2025 press release！
June 2025
I served as a Program Chair for the CVPR 2025 CVEU Workshop！
June 2025
Our AI film “Mirror” has been featured in over 200+ media outlets worldwide (e.g., AP News)
April 2025
Our AI Film Wins Best Film - Honorable Mentions at the First HKUST AI Film Festival
April 2025
Participate in
IEEE VR 2025 (Oral)
Best Papers - Honorable Mentions
March 2025
Participate in
IEEE VIS 2024 (Oral)
October 2024
Participate in
ACM MM 2024
October 2024
Participate in
ACM SIGGRAPH 2024
July 2024
Participate in TheWebConf 2024 (Oral)
May 2024
Participate in
ACM MM 2023 (Oral)
November 2023
Participate in
IEEE VR 2023
March 2023
Talk
I gave an in-person talk at Northwestern University (Kellogg School of Management) titled “Center Humans, Shape Intelligence: Human–AI Co-Creation for Visual Content.” Many thanks to Prof. Matt Groh and his group for the kind invitation.
Oct 2025
I gave an in-person talk at the School of Information Sciences, University of Illinois Urbana-Champaign (UIUC), titled “Center Humans, Shape Intelligence: Human–AI Co-Creation for Visual Content.” Many thanks to Prof. Yun Huang and her group for the kind invitation.
Oct 2025
I gave an in-person talk at Seoul National University titled “Center Humans, Shape Intelligence: Human–AI Co-Creation for Visual Content.” Many thanks to Prof. inwook Seo’s group for the invitation.
Sep 2025
I gave an in-person talk at Texas A&M University titled “Center Humans, Shape Intelligence: Human–AI Co-Creation for Visual Content.” Many thanks to Prof. Meng Xia’s group and Prof. Wai Tong’s group for the invitation.
Sep 2025
I gave a virtual talk at KAIST’s KIXLAB titled “Center Humans, Shape Intelligence: Human–AI Co-Creation for Visual Content.” I shared a Perception → Decision → Interaction loop for visual creation, with results from VR film education, cinematic data storytelling, and multi-agent co-creation. Many thanks to Prof. Juho Kim’s group for the invitation.
Sep 2025
I gave a virtual talk at Northeastern University’s Human-Centered AI Lab titled “Center Humans, Shape Intelligence: Human–AI Co-Creation for Visual Content.”
I shared a Perception → Decision → Interaction loop for visual creation, with results from VR film education, cinematic data storytelling, and multi-agent co-creation. Many thanks to Prof. Dakuo Wang’s group for the invitation.
Sep 2025
