Mingyu Liu

I am a PhD student at the State Key Laboratory of CAD&CG, Zhejiang University, advised by Chunhua Shen. Currently, I am a research intern at Shanghai AI Laboratory. I got my bachelor degree from the School of Artificial Intelligence and Automation(Elite Class), Huazhong University of Science and Technology. I'm open for discussion on exciting topics about AI and happy to make friends with people from various backgrounds. Feel free to contact me!
I was a research intern at MVIG, SJTU, advised by Yonglu Li and Cewu Lu. Before, I was delighted to work as a research intern at VLR Group, HUST, advised by Yuliang Liu and Xiang Bai. I have also worked at HAIV Lab, HUST, with Xiang Xiang. I visited Nanyang Technology University in 2024.
Formal Bio Github G. Scholar CV
mingyuliu [at] zju [dot] edu [dot] cn

DICEPTION: a generalist diffusion model for visual perceptual tasks
Canyu Zhao*, Mingyu Liu*, Huanyi Zheng, Muzhi Zhu, Zhiyue Zhao, Hao Chen, Tong He, Chunhua Shen
arxiv
Webpage •
PDF •
Code

MovieBench:A Hierarchical Movie Level Dataset for Long Video Generation
Weijia Wu, Mingyu Liu, Zeyu Zhu, Xi Xia, Haoen Feng, Wen Wang, Kevin Qinghong Lin, Chunhua Shen, Mike Zheng Shou
Conference on Computer Vision and Pattern Recognition (CVPR) 2025
Webpage •
PDF •
Code

PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
Cong Chen*, Mingyu Liu*, Chenchen Jing, Yizhou Zhou, Fengyun Rao, Hao Chen, Bo Zhang, Chunhua Shen
International Conference on Learning Representations (ICLR) 2025
★ Spotlight Presentation(5.1% in all submission) ★
Webpage •
PDF •
Code

Moviedreamer: Hierarchical generation for coherent long visual sequence
Canyu Zhao*, Mingyu Liu*, Wen Wang, Weihua Chen, Fan Wang, Hao Chen, Bo Zhang, Chunhua Shen
International Conference on Learning Representations (ICLR) 2025
Webpage •
PDF •
Code

What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
Guangkai Xu, Yongtao Ge, Mingyu Liu, Chengxiang Fan, Kangyang Xie, Zhiyue Zhao, Hao Chen, Chunhua Shen
International Conference on Learning Representations (ICLR) 2025
Webpage •
PDF •
Code

Take A Step Back: Rethinking the Two Stages in Visual Reasoning
Mingyu Zhang, Jiting Cai, Mingyu Liu, Yue Xu, Cewu Lu, Yong-Lu Li
European Conference on Computer Vision (ECCV), 2024
Webpage •
PDF •
Code
2024
Excellent Undergradute Graduation thesis2023
Academic Excellence Scholarship (rk1/30 Honor Class),HUST2022
Outstanding Undergraduate of Academic Performance (Top 1% in HUST)2019
National High School Mathematics League, First Prize