Zesen Cheng <br>(成泽森)

Zesen Cheng
(成泽森)

🤡🐀人

我是北京大学计算机科学与技术专业直博四年级学生 （预计 2026 年毕业），本科毕业于华南理工大学电子与信息学院（2021 届）。

人生格言: 知行合一，格物致知；志存高远，脚踏实地。

📌 主要研究方向

我的研究方向主要集中在 “多模态大模型与图像/视频理解” 领域，具体包括：

  • 多模态大模型 (视频理解), 包括:
    • 泛视频理解: Qwen2.5-VL core contributor
    • 音视频理解: VideoLLaMA2; CMM
    • 流视频理解: VideoLLaMA3
    • 长视频理解: Inf-CL (CVPR 2025 Highlight)
    • 细粒度视频理解: VideoRefer (CVPR 2025)
  • 图像/视频分割，包括:
    • 弱监督分割:  OCR (CVPR 2023)
    • 视频实例分割: TAR (ICCV 2025)
    • 多模态分割:  WiCo (IJCAI 2023, Neurocomputing 2024); PVD (AAAI 2024); BriVIS (AAAI 2025)
    • 医学图像分割: Fused U-Net (Medical Physics 2021)

📈 学术成果

目前已发表论文 20+ 篇，总 Google Scholar 引用量为 Citations。

所参与开源项目获得广泛关注，代表性项目的 GitHub Star 数如下：

VideoLLaMA2 Stars VideoLLaMA3 Stars Inf-CL Stars CMM Stars VideoRefer Stars

💬 联系方式

如果您对我的研究感兴趣，欢迎联系交流合作或提供实习 / 全职机会 🙏🙏。这是我的联系邮箱: cyanlaser@stu.pku.edu.cn

🔥 News

  • 2021.03: I join Sensetime as a research intern in shenzhen for developing MMSegmentation toolkit.

📝 Publications

🎞️ Multi-modal LLM (Video Understanding)

Qwen2.5-VL
sym

Qwen2.5-VL Technical Report
Core Contributors: Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, …, Zesen Cheng, Hang Zhang, Zhibo Yang, Haiyang Xu, Junyang Lin

Project | Code |

VideoLLaMA3
sym

VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
Boqiang Zhang* Kehan Li*, Zesen Cheng*, Zhiqiang Hu*, Yuqian Yuan*, Guanzheng Chen*, Sicong Leng*, Yuming Jiang*, Hang Zhang*, Xin Li*, Peng Jin, Wenqi Zhang, Fan Wang, Lidong Bing, Deli Zhao

Code | hf_space | hf_space | hf_paper

VideoLLaMA2

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Zesen Cheng*, Sicong Leng*, Hang Zhang*, Yifei Xin*, Xin Li*, Guanzheng Chen, Yongxin Zhu, Wenqi Zhang, Ziyang Luo, Deli Zhao, Lidong Bing

Code | hf_space | hf_space | hf_paper

CMM
sym

The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
Sicong Leng*, Yun Xing*, Zesen Cheng*, Yang Zhou, Hang Zhang, Xin Li, Deli Zhao, Shijian Lu, Chunyan Miao, Lidong Bing

Project | Code | hf_data

CVPR 2025 Highlight
sym

Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy (Hightlight)
Zesen Cheng*, Hang Zhang*, Kehan Li*, Sicong Leng, Zhiqiang Hu, Fei Wu, Deli Zhao, Xin Li, Lidong Bing

Code | hf_paper | PyPI

CVPR 2025
sym

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
Yuqian Yuan, Hang Zhang, Wentong Li, Zesen Cheng, et al.

Project | Code | | |

🧩 Image/Video Segmentation

ICCV 2025
tar

Temporal-aware Query Routing for Real-time Video Instance Segmentation
Zesen Cheng, Kehan Li, Yian Zhao, et al.

AAAI 2025
tar

Aligning Instance Brownian Bridge with Texts for Open-vocabulary Video Instance Segmentation
Zesen Cheng, Kehan Li, Li Hao, Peng Jin, et al.

Code

AAAI 2024
tar

Parallel Vertex Diffusion for Unified Visual Grounding
Zesen Cheng, Kehan Li, Peng Jin, et al.

IJCAI 2023
tar

WiCo: Win-win Cooperation of Bottom-up and Top-down Referring Image Segmentation
Zesen Cheng, Peng Jin, Hao Li, Kehan Li, et al.

CVPR 2023
tar

Out-of-Candidate Rectification for Weakly-supervised Semantic Segmentation
Zesen Cheng, Pengchong Qiao, Kehan Li, Siheng Li, et al.

Others

🥇 Honors and Awards

  • 2023.10 Pingan Scholarship
  • 2020.10 National Scholarship (Undergraduate) (Top 1%)
  • 2019.10 The Second Prize Scholarship
  • 2018.10 National Scholarship (Undergraduate) (Top 1%)

📖 Educations

💻 Internships

Flag Counter