About Me

Here is Shaodong Wang (Mercado, 王少东).

I am a PhD student in the Department of Computer Science and Engineering (CSE) at the Hong Kong University of Science and Technology (HKUST), supervised by Prof. Long Chen. I completed my undergraduate studies at the University of Electronic Science and Technology of China (UESTC) and my master’s degree at the School of Electronic and Computer Engineering at Peking University, where I was advised by Prof. Li Yuan.

Prior to joining HKUST, I conducted research in artificial intelligence and generative models under the guidance of Prof. Li Yuan at Peking University. My research primarily focuses on AIGC and unified models, including text-to-image generation, text-to-video synthesis, and image editing.

If you are interested in any aspect of me, I am always open to discussions and collaborations. Feel free to reach out to me at — shaodong_jerry [at] 163.com

Research Interests

AIGC
Unified Models
Text-to-Image Generation
Text-to-Video Generation

News and Updates

June 2025：We release UniWorld-V1, a unified framework for understanding, generation, and editing. Checking our report for more details.
May 2025：Happy to receive a PhD offer from the Department of Computer Science and Engineering at HKUST!
Oct 2024：We released Open-Sora-plan version 1.3.0, featuring: WFVAE, prompt refiner, data filtering strategy, sparse attention, and bucket training strategy. We also support 93x480p within 24G VRAM. More details can be found at our latest report.
July 2024：Our work Prompt2Posters has been accepted to ACM MM 2024 as a poster paper. See you in Melbourne!
Mar 2024：Our work Opne-Sora-Plan has been open sourced as SOTA’s video generation model. We welcome everyone’s guidance and suggestions.