Ming-Yu Liu

I am a PhD candidate at the State Key Laboratory of CAD&CG, Zhejiang University, advised by Hao Chen and Chunhua Shen. 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 any exciting topics about Robots and Foundation Model. Feel free to contact me!

Formal Bio Github G. Scholar LinkedIn

mingyuliu [at] zju [dot] edu [dot] cn

Some recent news:

[09/2026]: Three Papers accepted by NeurIPS2026.

[09/2026]: Two Papers accepted by CoRL2026.

[08/2026]: One Paper accepted by EMNLP2026.

[06/2026]: One Paper accepted by ECCV2026.

[05/2026]: Three Papers accepted by ICML2026.

[04/2026]: StaMo is chosen as CVPR2026 Highlight(top 3.8%)!

[02/2026]: Two Papers accepted by CVPR2026.

[01/2026]: One Paper accepted by ICLR2026.

[11/2025]: Odyssey and Affordance-R1 are chosen as AAAI2025 Oral(top 3.5%)!

[11/2025]: Three Papers accepted by AAAI2025.

[09/2025]: Diception is chosen as NeurIPS2025 Spotlight(top 3.1%)!

[09/2025]: Two Papers accepted by NeurIPS2025.

[06/2025]: One Paper accepted by ICCV2025.

[04/2025]: One Paper accepted by IJCAI2025.

[03/2025]: One Paper accepted by SIGGRAPH2025.

[02/2025]: One Paper accepted by CVPR2025.

[02/2025]: PerturboLLaVa is chosen as ICLR2025 Spotlight(top 5.1%)!

[01/2025]: Three Papers accepted by ICLR2025.

[07/2024]: One Paper accepted by ECCV2024.

Embodied AI

Robot learning, manipulation, VLA policies, and affordance grounding.

PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training

Mingyu Liu*, Chonghao Sima*, Tianjian Feng, Hanqing Wang, Cong Chen, Hao Chen, Chunhua Shen
Manuscript, 2026
Webpage • Code • PDF

Perfect Demo Makes Poor Teacher: Learning Robust Alignment from Critical Motion Segments

Mingyu Liu*, Zeju Li*, Jiuhe Shu, Hanqing Wang, Yuhao Chao, Hao Chen, Chunhua Shen
Conference on Robot Learning (CoRL) 2026
Webpage • Code • PDF

VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model

Hanqing Wang*, Mingyu Liu*, Xiaoyu Chen, Chengwei MA, Yiming Zhong, Wenti Yin, Yuhao Liu, Zhiqing Cui, Jiahao Yuan, Lu Dai, Zhiyuan Ma, Hui Xiong
Conference on Neural Information Processing Systems (NeurIPS) 2026
Webpage • Code • PDF

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

Mingyu Liu*, Jiuhe Shu, Hui Chen, Zeju Li, Canyu Zhao, Jiange yang, Shenyuan Gao, Hao Chen, Chunhua Shen
Conference on Computer Vision and Pattern Recognition (CVPR) 2026
★ Highlight Presentation(3.1% in all submission) ★
Webpage • Code • PDF

GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert

Mingyu Liu, Zheng Huang, Xiaoyi Lin, Muzhi Zhu, Canyu Zhao, Yating Wang, Haoyi Zhu, Hao Chen, Chunhua Shen
International Conference on Machine Learning (ICML) 2026
Webpage • Code • PDF

NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces

Zheng Huang*, Mingyu Liu*, Xiaoyi Lin, Muzhi Zhu, Canyu Zhao, Zongze Du, Ye Lin, Xiaoman Li, Yiduo Jia, Hao Zhong, Hao Chen, Chunhua Shen
Conference on Neural Information Processing Systems (NeurIPS) 2026
Webpage • Code • PDF

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks

Kaijun Wang, Liqin Lu, Mingyu Liu, Jianuo Jiang, Zeju Li, Bolin Zhang, Wancai Zheng, Xinyi Yu, Hao Chen, Chunhua Shen
AAAI Conference on Artificial Intelligence (AAAI) 2026
★ Oral Presentation ★
Webpage • Code • PDF

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers

Yating Wang, Haoyi Zhu, Mingyu Liu, Jiange Yang, Hao-Shu Fang, Tong He
International Conference on Computer Vision (ICCV) 2025
Webpage • Code • PDF

AdvDex: Learning Dexterous Manipulation from Human Demonstrations via Joint-Aligned Actions and Adversarial Learning

Zhiyue Zhao, Jingyi Wu, Hairuo Liu, Mingyu Liu, Liyang Li, Hengdi Zhang, Tong He, Zhengxue Cheng
Conference on Robot Learning (CoRL) 2026
Webpage • Code • PDF

Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learning

Hanqing Wang, Zhenhao Zhang, Kaiyang Ji, Mingyu Liu, …, Zhiyuan Ma, Hui Xiong
European Conference on Computer Vision (ECCV) 2026
Webpage • Code • PDF

CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning

Jiange Yang, Yansong Shi, Haoyi Zhu, Mingyu Liu, Kaijing Ma, Yating Wang, Gangshan Wu, Tong He, Limin Wang
Conference on Computer Vision and Pattern Recognition (CVPR) 2026
Webpage • Code • PDF

Foundation Model

Vision-language reasoning and multimodal evaluation, including earlier work on recognition and document understanding.

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 • Code • PDF

Seeing the Unseen: Composing Outliers for Compositional Zero-Shot Learning

Chenchen Jing, Mingyu Liu, Hao Chen, Yuling Xi, Xingyuan Bu, Dong Gong, Chunhua Shen
International Joint Conference on Artificial Intelligence (IJCAI) 2025
Webpage • Code • PDF

Looking and Listening: Audio Guided Text Recognition

Wenwen Yu, Mingyu Liu, Biao Yang, Enming Zhang, Deqiang Jiang, Xing Sun, Yuliang Liu, Xiang Bai
Preprint, 2023
Webpage • Code • PDF

ICDAR 2023 Competition on Reading the Seal Title

Wenwen Yu, Mingyu Liu, Mingrui Chen, Ning Lu, Yinlong Wen, Yuliang Liu, Dimosthenis Karatzas, Xiang Bai
International Conference on Document Analysis and Recognition (ICDAR) 2023
Webpage • Code • PDF

SDEval: Safety Dynamic Evaluation for Multimodal Large Language Models

Hanqing Wang, Yuan Tian, Mingyu Liu, Zhenhao Zhang, Xiangyang Zhu
AAAI Conference on Artificial Intelligence (AAAI) 2026
Webpage • Code • PDF

Learning by Imagining: Debiased Feature Augmentation for Compositional Zero-Shot Learning

Haozhe Zhang, Chenchen Jing, Mingyu Liu, Qingsheng Wang, Hao Chen
Preprint, 2025
Webpage • Code • PDF

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 • Code • PDF

ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images

Wenwen Yu, Chengquan Zhang, Haoyu Cao, Wei Hua, …, Mingyu Liu, …, Jingdong Wang, Xiang Bai
International Conference on Document Analysis and Recognition (ICDAR) 2023
Webpage • Code • PDF

Generative Models & World Models

Image and video generation, diffusion-based perception, and embodied world modeling.

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
Conference on Neural Information Processing Systems (NeurIPS) 2025
★ Spotlight Presentation(3.1% in all submission) ★
Webpage • Code • PDF

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 • Code • PDF

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 • Code • PDF

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 • Code • PDF

World Guidance: World Modeling in Condition Space for Action Generation

Yue Su, Sijin Chen, Haixin Shi, Mingyu Liu, Zhengshen Zhang, Ningyuan Huang, Weiheng Zhong, Zhengbang Zhu, Yuxiao Liu, Xihui Liu
International Conference on Machine Learning (ICML) 2026
Webpage • Code • PDF

Generative Video Matting

Yongtao Ge, Kangyang Xie, Guangkai Xu, Mingyu Liu, Li Ke, Longtao Huang, Hui Xue, Hao Chen, Chunhua Shen
ACM SIGGRAPH (SIGGRAPH) 2025
Webpage • Code • PDF

Learning Primitive Embodied World Models: Towards Scalable Robotic Learning

Qiao Sun, Liujia Yang, Wei Tang, Wei Huang, …, Mingyu Liu, …, Nanyang Ye, Qinying Gu
Preprint, 2025
Webpage • Code • PDF

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Yang Zhou, Yifan Wang, Jianjun Zhou, Wenzheng Chang, …, Mingyu Liu, …, Kaipeng Zhang, Tong He
International Conference on Learning Representations (ICLR) 2026
Webpage • Code • PDF

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Weiliang Chen, Haowen Sun, Jun Gao, Jiawei Chi, …, Mingyu Liu, …, Jiangran Lyu, Fangfu Liu
Technical Report, 2026
Webpage • Code • PDF

Reinforcement Learning

Reinforcement-learning post-training for perception, multimodal reasoning, and VLA policies.

OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering — paper illustration

Internship

ByteDance Seed
Nov. 2025 – Present

Research Scientist Intern

Multimodal Interaction and World Model team
Shanghai AI Laboratory
Dec. 2024 – Oct. 2025

Research Intern

Working with Tong He and Jiangmiao Pang
Shanghai Jiao Tong University
Dec. 2022 – Nov. 2023

Research Intern · MVIG

Advisors: Yonglu Li and Cewu Lu

Education

Zhejiang University
Sep. 2024 – Present

PhD Candidate · State Key Laboratory of CAD&CG

Advisors: Hao Chen and Chunhua Shen
Huazhong University of Science and Technology
Sep. 2020 – Jun. 2024

Bachelor's Degree · Artificial Intelligence and Automation (Elite Class)

Advisors: Yuliang Liu and Xiang Bai

Honors

2026

Silver Reviewer Award, ICML

Outstanding Reviewer, ECCV

2024

Excellent Undergradute Graduation thesis

Outstanding Graduates

FiberHome Scholarship (Only one in the Department)

2023

Academic Excellence Scholarship (rk1/30 Honor Class)，HUST

China Aerospace Science and Technology Corporation(CASC) Scholarship (Only one in the Department)

2022

Outstanding Undergraduate of Academic Performance (Top 1% in HUST)

China University Robot Competition (RoboCon), 3rd place Nationalwide, First Prize

Academic Service

Conference Reviewer

International Conference on Learning Representations (ICLR)
International Conference on Machine Learning (ICML)
Conference on Neural Information Processing Systems (NeurIPS)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
European Conference on Computer Vision (ECCV)
ACM International Conference on Multimedia (ACM MM)