Hi, I’m Xuhan (盛 栩涵), a Ph.D. student in Artificial Intelligence in the Department of Computer Science at the Institute of Science Tokyo (formerly Tokyo Institute of Technology), advised by Prof. Rio Yokota. I received my Master’s degree from Peking University, advised by Prof. Jian ZHANG, and my Bachelor’s degree in Artificial Intelligence from Dalian University of Technology, advised by Prof. Xu JIA.
My research background includes diffusion models, memory-efficient training and inference, vision-language models, and video data pipelines. My previous research includes OmniSSR (ECCV 2024 Oral, co-first author) and panoramic image-to-video generation. I am currently a World Model Research Intern at Xiaomi Auto (Shanghai team).
I am exploring future research directions in video generation, AI agents, and large language models, and am seeking long-term research internships in these areas. I am available for on-site internships in China and Tokyo, Japan, and will also consider opportunities in the United States. Start date is flexible; working hours depend on local requirements and company policy. View my CV.
I am always open to academic and industry collaborations. Feel free to reach out.
🔥 News
- 2026.10: 🎓 Started my Ph.D. in AI at Institute of Science Tokyo, advised by Prof. Rio Yokota.
- 2026.08: 💼 Joined Xiaomi Auto as a research intern, developing video super-resolution for World Model 2.0.
- 2026.03: 💼 Started my internship at Tencent IEG (Game AI Engine Department).
- 2025.09: 🎉 Collaboration: 1 paper accepted in PRCV 2025.
- 2025.08: 🎉 Collaboration: 1 paper accepted in IJCV 2025.
- 2025.06: 🎉 Collaboration: 1 paper accepted in ICME 2025 for oral presentation.
- 2025.05: 💼 Started my internship at OPPO Research Institute (AI Talent Program).
- 2024.09: 🎉 First-author: 1 paper (“OmniSSR”) accepted in ECCV 2024 for oral presentation.
- 2023.06: 🏆 Collaboration: 1 work won the “NTIRE 2023 Challenge on 360deg Omnidirectional Image Super-Resolution track” championship.
💼 Industry Experience
Xiaomi Auto, Shanghai Team
- Contributing to Xiaomi Auto World Model 2.0 (forthcoming), with primary responsibility for video super-resolution.
Tencent, IEG, Game AI Engine Department
- Qwen-Image-based image enhancement for game content and production-level visual assets.
- Built data-pipeline operators for video generative models; developed a streaming shot-segmentation operator that splits long videos into single-shot clips.
OPPO Research Institute
Worked on vision-language models for assisting AI-based image enhancement. Advisor: Prof. Lei Zhang.
🔬 Research Interests
- Interactive Long-Video Generation: Post-training and distillation for controllable video world models with long-horizon consistency.
- 3D Spatial Memory for World Models: Explicit, updatable scene memory to preserve object identity, scene geometry, and occlusion consistency across camera motion and interactions.
- World Models for Visual Reasoning: Modeling physical and causal dynamics to predict future states and evaluate action outcomes.
📑 Publications
(*: indicates equal contribution; #: indicates corresponding author)
Diffusion Models for Image & Video Generation and Restoration
Video Understanding
🎓 Educations
Institute of Science Tokyo, Department of Computer Science
Advisor: Prof. Rio Yokota
Advisor: Prof. Jian ZHANG; GPA: 3.87/4.00
Dalian University of Technology
Advisor: Prof. Xu JIA; GPA: 4.17/5.00
🏅 Honors and Awards
- 2024, Peking University Academic Excellence Award.
- 2023, Dalian University of Technology University-level Outstanding Graduate.
- 2022, Dalian University of Technology First-class Academic Excellence Scholarship.
- 2021, Dalian University of Technology Second-class Academic Excellence Scholarship.
- 2020, Dalian University of Technology First-class Academic Excellence Scholarship.
😊 Hobbies
Click image to zoom.
I love playing flutes (Irish flute, Boehm flute, Shakuhachi). I love Hatsune Miku. I am learning Cantonese.
