Zixian Gao | The University of Tokyo

🍀 About Me

I am an incoming master’s student at the University of Tokyo, supervised by Prof. Hideki Nakayama. Previously, I worked as a research assistant at the Center of Future Media, University of Electronic Science and Technology of China, under the mentorship of Prof. Xing Xu.

I am always open to academic collaborations. Feel free to drop me an email or connect with me on WeChat!

WeChat QR

🔬 Research Interests

Generative Models: Video Generation/Editing, World Simulation
Multimodal Learning: Vision Language Models, 3D Foundation Models

🔥 What's New

[May. 2025] 🌻 Our paper about MLLMs Hallucination is released now!

[Dec. 2024] 🌻 I started an internship at Shanghai AI Lab. See you in Shanghai!

[Jul. 2024] 🌻 Our paper about Mixture of Expert is accepted to ACM MM 2024!

[Mar. 2024] 🌻 Our paper about Multimodal Fusion is accepted to ICME 2024!

[Feb. 2024] 🌻 Our paper about Uncertainty Learning is accepted to CVPR 2024!

📝 Selected Publications

Google Scholar

Preprint

Mitigating Object Hallucination via Robust Local Perception Search

Zixian Gao, Chao Yang, Zhanhui Zhou, Xing Xu, Chaochao Lu

Arxiv

PDF Code

CVPR

Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion

Zixian Gao*, Xun Jiang*, Xing Xu, Fumin Shen, Yujie Li, Heng Tao Shen

IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024.

PDF Code