Scholar
Long Mai
Google Scholar ID: QHCY1cgAAAAJ
Research Scientist
Computer Vision
Computational Photography
Machine Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
5,089
H-index
24
i10-index
30
Publications
20
Co-authors
0
Contact
Email
long.mai@bytedance.com
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
4 items
TokenDial: Continuous Attribute Control in Text-to-Video via Spatiotemporal Token Offsets
2026
Cited
0
TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance
2026
Cited
0
V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation
2026
Cited
0
DreamLoop: Controllable Cinemagraph Generation from a Single Photograph
arXiv.org · 2026
Cited
0
Resume (English only)
Academic Achievements
MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation, SIGGRAPH 2025
REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder, ICCV 2025
Progressive Growing of Video Tokenizers for Highly Compressed Latent Spaces, ICCV 2025
MVDream: Multi-view Diffusion for 3D Generation, ICLR 2024
Motion-Adjustable Neural Implicit Video Representation, CVPR 2022 (Oral Presentation)
Research Experience
Has also worked as a senior research scientist at ByteDance Research and SEA AI Lab (SAIL).
Education
Worked with Professor Feng Liu in the Computer Graphics & Vision Lab at Portland State University before joining Adobe.
Background
A Senior Research Scientist at Adobe Research. Works focus on data-driven approaches to visual content understanding and generation.
Co-authors
0 total
Co-authors: 0 (list not available)
×
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