I’m a 3-rd year M.S. student in Computer Science at Southeast University, advised by Prof. Hanqian Wu and Prof. Li Yao. I also work closely with Jieyu Zhang at the University of Washington and Linxin Song at the University of Southern California.

😄 Research Interests

My research interest is Data-Centric AI with emphasis on Large Multimodal Models, including Image / Video / 3D / 4D / Multimodal World Model.

If you want to discuss relevant research topics or potential collaborations, feel free to send me an email.

📢 News

[02/21/2026] Our work Synthetic Curriculum Reinforces Compositional Text-to-Image Generation is accepted to CVPR 2026!

[10/28/2025] A new preprint is released! Check Video-Thinker: Sparking “Thinking with Videos” via Reinforcement Learning for more details!

[05/31/2025] Our paper Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification got accepted as an Oral Presentation (top 15%) at ICME 2025!

[04/08/2025] A new preprint is released! Check Investigating the Scaling Effect of Instruction Templates for Training Multimodal Language Model for more details!

📝 Selected Research

(* denotes equal contribution)

• Synthetic Curriculum Reinforces Compositional Text-to-Image Generation
  Shijian Wang*, Runhao Fu*, Siyi Zhao, Qingqin Zhan, Xingjian Wang, Jiarui Jin, Yuan Lu, Hanqian Wu, Cunjian Chen
  CVPR 2026
• Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification
  Shijian Wang, Linxin Song, Ryotaro Shimizu, Masayuki Goto, Hanqian Wu
  ICME 2025 | Oral Presentation [top 15%]
• Video-Thinker: Sparking “Thinking with Videos” via Reinforcement Learning
  Shijian Wang*, Jiarui Jin*, Xingjian Wang, Linxin Song, Runhao Fu, Hecheng Wang, Zongyuan Ge, Yuan Lu, Xuelian Cheng
  Submitted to ICML 2026
• Investigating the Scaling Effect of Instruction Templates for Training Multimodal Language Model
  Shijian Wang*, Linxin Song*, Jieyu Zhang, Ryotaro Shimizu, Jiarui Jin, Ao Luo, Yuan Lu, Li Yao, Cunjian Chen, Julian McAuley, Hanqian Wu
  DATA-FM@ICLR 2025
• Decoding Prokaryotic Whole Genomes with a Product-Contextualized Large Language Model
  Shiwen Ni, Shuaimin Li, Shijian Wang, Xinping Bi, Yitai Li, Chengguang Gan, Jiarui Jin, Yuan Lu, Ahmadreza Argha, Hamid Alinejad-Rokny, Tong Si, Min Yang, Teng Wang
  Submitted to Nature Methods

🏅 Awards

• Southeast University First-Class Scholarship 2023-2024

📍 Professional Services

• Reviewer: ICLR 2026, AAAI 2026, COLM 2025, ECAI 2025, AISTATS 2025, ICME 2025, ICASSP 2025, SynData4CV@CVPR 2024/2025, DATA-FM@ICLR 2025

👨‍💻 Industrial Experience

• ExperienceAI-Lab at Xiaohongshu Inc. - Research Intern
  2025.03-Present

📫 Contact

Email: shijian@seu.edu.cn