Skip to content
View ShaoDingBao's full-sized avatar
0 followers · 1 following

Highlights

  • Pro

Block or report ShaoDingBao

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ShaoDingBao/README.md

Dingbao Shao

Video generation and editing · Diffusion Transformers and Wan · Datasets to distributed training

Building controllable video systems, from data construction to large-scale training.

🎓 M.S. Candidate @ Nanjing University 🔎 Open to 2027 New-Grad Opportunities

💼 Internship Experience

Alibaba
Moku Lab · Video Generation & Editing
2026.06 — Present

China Mobile
JIUTIAN Research · General Video Editing
2025.11 — 2026.06

🔬 Selected Research

InstructVVT — arXiv 2026
Co-first author

Instruction-driven video virtual try-on without inference-time masks, poses, or parsing maps.

Paper · Project


TripVVT — ECCV 2026
First author

A large-scale triplet dataset and a coarse-mask DiT baseline for in-the-wild video virtual try-on.

Paper · Project · Dataset

Video Generation Video Editing Diffusion / DiT Wan Distributed Training

Email · InstructVVT · TripVVT

Popular repositories Loading

  1. TripVVT TripVVT Public

    ECCV 2026 | A large-scale triplet dataset and coarse-mask DiT baseline for in-the-wild video virtual try-on.

    HTML 1

  2. ShaoDingBao ShaoDingBao Public

    Video generation and editing researcher at Nanjing University.

  3. InstructVVT InstructVVT Public

    Instruction-driven video virtual try-on without auxiliary spatial priors

    CSS