Hongyu Li

MS student, Beijing University of Aeronautics and Astronautics

Intern, ByteDance Inc.

Intern, stepfun

Joined

November 2023

Names

Hongyu Li (Preferred)

Emails

****@buaa.edu.cn (Confirmed)

****@163.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

MS student

Beijing University of Aeronautics and Astronautics (buaa.edu.cn)

2024 – 2027

Intern

ByteDance Inc. (bytedance.com)

2024 – 2026

Intern

stepfun (stepfun.com)

2024 – 2026

Intern

Meituan (meituan.com)

2024 – 2025

Intern

Zhejiang University (zju.edu.cn)

2023 – 2025

Intern

Fudan University (fudan.edu.cn)

2023 – 2025

Undergrad student

Beijing University of Aeronautics and Astronautics (buaa.edu.cn)

2019 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Si Liu

2024 – Present

Expertise

Embodied AI

2024 – 2024

Vision-Language

2023 – 2024

Publications

OneThinker: All-in-one Reasoning Model for Image and Video
Kaituo Feng, Manyuan Zhang, Hongyu Li, Kaixuan Fan, Shuang Chen, Yilei Jiang, Dian Zheng, Peiwen Sun, Yiyuan Zhang, Haoze Sun, Yan Feng, Peng Pei, Xunliang Cai, Xiangyu Yue
- OpenReview Archive Direct Upload
- Readers: Everyone
EditThinker: Unlocking Iterative Reasoning for Any Image Editor
Hongyu Li, Manyuan Zhang, Dian Zheng, Ziyu Guo, Yimeng Jia, Kaituo Feng, Hao Yu, Yexin Liu, Yan Feng, Peng Pei, Xunliang Cai, Linjiang Huang, Hongsheng Li, Si Liu
- OpenReview Archive Direct Upload
- Readers: Everyone
Architecture Decoupling Is Not All You Need For Unified Multimodal Model
Dian Zheng, Manyuan Zhang, Hongyu Li, Kai Zou, Hongbo Liu, Ziyu Guo, Kaituo Feng, Yexin Liu, Ying Luo, Yan Feng, Peng Pei, Hongsheng Li
- OpenReview Archive Direct Upload
- Readers: Everyone
EditThinker: Unlocking Iterative Reasoning for Any Image Editor
Hongyu Li, Manyuan Zhang, Dian Zheng, Ziyu Guo, Yimeng Jia, Kaituo Feng, Hao Yu, Yexin Liu, Yan Feng, Peng Pei, Xunliang Cai, Linjiang Huang, Hongsheng Li, Si Liu
- CoRR 2025
- Readers: Everyone
OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation
Yexin Liu, Manyuan Zhang, Yueze Wang, Hongyu Li, Dian Zheng, Weiming Zhang, Changsheng Lu, Xunliang Cai, Yan Feng, Peng Pei, Harry Yang
- CoRR 2025
- Readers: Everyone
OneThinker: All-in-one Reasoning Model for Image and Video
Kaituo Feng, Manyuan Zhang, Hongyu Li, Kaixuan Fan, Shuang Chen, Yilei Jiang, Dian Zheng, Peiwen Sun, Yiyuan Zhang, Haoze Sun, Yan Feng, Peng Pei, Xunliang Cai, Xiangyu Yue
- CoRR 2025
- Readers: Everyone
Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
Ziyu Guo, Renrui Zhang, Hongyu Li, Manyuan Zhang, Xinyan Chen, Sifan Wang, Yan Feng, Peng Pei, Pheng-Ann Heng
- CoRR 2025
- Readers: Everyone
Architecture Decoupling Is Not All You Need For Unified Multimodal Model
Dian Zheng, Manyuan Zhang, Hongyu Li, Kai Zou, Hongbo Liu, Ziyu Guo, Kaituo Feng, Yexin Liu, Ying Luo, Yan Feng, Peng Pei, Xunliang Cai, Hongsheng Li
- CoRR 2025
- Readers: Everyone
OmniAlpha: A Sequence-to-Sequence Framework for Unified Multi-Task RGBA Generation
Hao Yu, Jiabo Zhan, Zile Wang, Jinglin Wang, Huaisong Zhang, Hongyu Li, Xinrui Chen, Yongxian Wei, Chun Yuan
- CoRR 2025
- Readers: Everyone
Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
Hongyu Li, Songhao Han, Yue Liao, Junfeng Luo, Jialin Gao, Shuicheng Yan, Si Liu
- CoRR 2025
- Readers: Everyone

View all 15 publications

Co-Authors

View all 58 co-authors