Haotian Ni

Postgraduate

About Me

I studied Computer Science at Beihang University (BUAA) from 2022 to 2026 and recently graduated with a bachelor’s degree. I will pursue an MRes in AI and Machine Learning at Imperial College London from 2026 to 2027 and am currently seeking PhD opportunities. During my junior year, I joined GeWu-lab as a research assistant under the supervision of Professor Di Hu.

Download CV

Interests

Multimodal Learning
Deep Generative Models

Education

BSc Computer Science
Beihang University

📚 My Research

I have a strong interest in Artificial Intelligence and Machine Learning, with a focus on developing a unified model that can understand and generate content accordingly. My research interests lie in multimodal learning and large multimodal foundation models.

Please reach out to collaborate 😃

Publications

Yu Miao*, Zequn Yang*, Yake Wei, Ziheng Chen, Haotian Ni, Haodong Duan, Kai Chen, Di Hu (2026). MIBench: Evaluating LMMs on Multimodal Interaction. arXiv 2026.

PDF

Zequn Yang, Yake Wei, Haotian Ni, Zhihao Xu, Di Hu (2026). Information-Theoretic Decomposition for Multimodal Interaction Learning. In CVPR 2026.

PDF

Haotian Ni, Yake Wei, Hang Liu, Gong Chen, Chong Peng, Hao Lin, Di Hu (2025). RollingQ: Reviving Cooperation Dynamics in Multimodal Transformer. In ICML 2025.

PDF Code

News

[2026-03-13] Our work MIBench has been released on arXiv.

[2026-03-03] A paper accepted by CVPR 2026! Thanks to all co-authors! 🎉🎉🎉

[2025-05-01] A paper accepted by ICML 2025! Thanks to all co-authors! 🎉🎉🎉

Recent & Upcoming Talks