Scholar
Anyi Rao
Google Scholar ID: 8lKr7j4AAAAJ
Assistant Professor, HKUST
Human AI
AI for Creativity
Generative AI
Content Creation
Film
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
10,406
H-index
20
i10-index
24
Publications
20
Co-authors
27
list available
Contact
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
17 items
InstanceAnimator: Multi-Instance Sketch Video Colorization
2026
Cited
0
Controllable Text-to-Motion Generation via Modular Body-Part Phase Control
2026
Cited
0
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models
2026
Cited
0
ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation
2026
Cited
0
SesaHand: Enhancing 3D Hand Reconstruction via Controllable Generation with Semantic and Structural Alignment
2026
Cited
0
Collaposer: Transforming Photo Collections into Visual Assets for Storytelling with Collages
2026
Cited
0
Composing Concepts from Images and Videos via Concept-prompt Binding
2025
Cited
0
Hollywood Town: Long-Video Generation via Cross-Modal Multi-Agent Orchestration
2025
Cited
0
Load more
Resume (English only)
Academic Achievements
Key works include ControlNet, AnimateDiff, MovieNet, Virtual Studio, and IC-Light
ControlNet received the Marr Prize (Best Paper Award) at ICCV 2023
Published extensively at top venues including CVPR, ICCV, ECCV, UIST, ICML, ACM MM, ICLR, and SIGGRAPH
IC-Light accepted as Oral at ICLR 2025
CineVision accepted to UIST 2025; Light-A-Video accepted to ICCV 2025
Won the Rising Star Award at the World Artificial Intelligence Conference 2024
Named to Forbes 30 Under 30 Asia 2025
Recipient of the Brown Media Innovation Research Fund and Amazon Video Research Fund
Research Experience
Research experience at Meta Reality Lab, Vector Institute, University of Toronto, and University of Hong Kong
Organized the SIGGRAPH/CVPR/ICCV/ECCV Workshop on AI for Creative Visual Content
Organized the SIGGRAPH Course on Generative Models for Visual Content
Served as co-chair for MMSys26, UIST25, VINCI25, CVM25, UIST24
Served as area chair/TPC member for CVPR26, ICLR26, SIGGRAPH Asia26/25
Background
Assistant Professor at the Hong Kong University of Science and Technology (HKUST)
Leads the Multimedia Creativity Lab (MMLab@HKUST)
Associate Director of HKUST Media Intelligence Research Center
Researches human-AI collaboration for creativity, focusing on understanding, editing, and creation of art, media, and film
Aims to build human-AI collaborative intelligence to enhance human creativity and productivity
Co-authors
27 total
lvmin zhang
Stanford University
Maneesh Agrawala
Stanford University
Dahua Lin
The Chinese University of Hong Kong
Bo Dai
The University of Hong Kong
Yuwei Guo
MMLab, The Chinese University of Hong Kong
Ceyuan Yang
The Chinese University of Hong Kong
Co-author 7
Daniel Lowd
Professor of Computer Science, University of Oregon
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up