Bowen Xue
Avatar

Bowen Xue (薛博文)

I’m a third-year undergraduate student at USTC. Currently a research intern at MIT HanLab (mentored by Muyang Li), I was formerly an algorithm intern at Tencent (mentored by Qixin Yan). I’m exploring generative models and seeking PhD opportunities for Fall 2027.

🎯 Research Interests

Generative models, IP injection, T2I, T2V, image editing, diffusion models, large model acceleration, VLLM

🔍 Goal

My ultimate ambition is to revolutionize generative AI models, making them significantly faster, better, and more versatile. My dream is to develop generative AI models that can flawlessly accomplish a vast array of generative tasks at unprecedented quality.

📰 News

  • 🚀 Released my new academic homepage! Feel free to reach out!

  • 🎓 Started a new research journey as an intern at MIT Han Lab!

  • 💼 Worked as an Algorithm Intern at Tencent.

📝 Publications

Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

Bowen Xue, Qixin Yan, Wenjing Wang, Hao Liu, Chen Li

Stand-In trains just 1% of the original model’s parameters with 2,000 video–prompt pairs, yet achieves high-quality identity-preserving video generation.

Project Page Paper Code Models

✨ Behind the Work

This was my first complete research project. Ten days after releasing it on GitHub, Stand-In gained over 500 stars, and my work was accepted by the community. During that period, I almost refreshed the star count every day whenever I had free time, actively responded to issues, and improved the project as planned. Later, when the tide receded, everything almost returned to normal—except that I kept working hard: maintaining the project and preparing for the next, more solid one.