Zhihao Xie

I am an undergraduate student at the Huazhong University of Science and Technology (HUST). I will join the Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen) as an incoming PhD student, advised by Prof. Li Jiang. My research interests include visual tokenizers, video generation, unified multimodal understanding and generation, and embodied intelligence.

I have been fortunate to work with Prof. Xiang Bai and Prof. Yuliang Liu at the VLR Lab, and Prof. Wei Wei at the CCIIP Lab at HUST.

	VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders Zhihao Xie, Junfeng Wu, Xinting Hu, Junchao Huang, Li Jiang arXiv, 2026 arXiv / code / project page
	TokBench: Evaluating Your Visual Tokenizer before Visual Generation Junfeng Wu, Dongliang Luo, Weizhi Zhao, Zhihao Xie, Yuanhao Wang, Junyi Li, Xudong Xie, Yuliang Liu, Xiang Bai ACM MM, 2026 (Dataset Track Oral) arXiv / project page
	Mitigating Hallucinations in Large Multimodal Reasoning Models by Regulating Parametric Prior Drift Xiaoye Qu, Yanzhe Wu, Zhihao Xie, Daizong Liu, Wei Wei ACM MM, 2026
	TopCom: Fast Token Compression with Top-K Selection for Efficient Video Understanding Yanzhe Wu, Zhihao Xie*, Wei Wei ICME*, 2026

Design and source code from Jon Barron's website.