I’m a second-year PhD student from the School of Computer Science, Shanghai Jiaotong University. I am very fortunate to be advised by Prof. Wei Shen. Currently, I am also interning with the LongCat model team at Meituan.

My research interests lie in computer vision and deep learning, with a particular focus on visual reasoning in multimodal large models and segmentation. I am driven by the challenge of creating models that can understand and interact with complex, multi-modal scenes. Please feel free to contact me through email: changsong@sjtu.edu.cn.

📖 Educations

  • 2024.09 - 2028.06 (now), PhD student of Shanghai Jiaotong University.
  • 2021.09 - 2024.06, Master student of Nankai University.
  • 2017.09 - 2021.07, Undergraduate student of Xidian University.

    🔥 News

  • 2026.06:  🎉🎉 one papers is accepted by ECCV 2026.
  • 2026.02:  🎉🎉 one papers is accepted by CVPR 2026.
  • 2025.10:  🎉🎉 one paper is accepted by AAAI 2026.
  • 2025.05:  🎉🎉 one paper is accepted by ICML 2025.
  • 2025.02:  🎉🎉 three papers are accepted by CVPR 2025.
  • 2023.07:  🎉🎉 One paper is accepted by ICCV 2023.
  • 2023.03:  🎉🎉 One paper is accepted by CVPR 2023.

    🎖 Honors and Awards

  • 2025.12 Young Elite Scientists Sponsorship Program by CAST (PhD Student Special Plan)
  • 2023.10 National Scholarship.
  • 2022.11 Gongneng Scholarship of Nankai University.
  • 2021.11 Recommended Scholarship of Nankai University.
  • 2021.07 Outstanding Graduates Awards.
  • 2020.10 Special Scholarship of Xidian University.

📝 Publications

ECCV 2026
sym

Exploring Efficient Reasoning Segmentation with Small Language Models

Changsong Wen, Zelin Peng, Yu Huang, Xiaokang Yang, Wei Shen

CVPR 2026
sym

Unlocking 3D Affordance Segmentation with 2D Semantic Knowledge

Yu Huang, Zelin Peng, Changsong Wen, Xiaokang Yang, Wei Shen

AAAI 2026
sym
ICML 2025
sym

Tackling View-Dependent Semantics in 3D Language Gaussian Splatting

Jiazhong Cen, Xudong Zhou, Jiemin Fang, Changsong Wen, Lingxi Xie, Xiaopeng Zhang, Wei Shen, Qi Tian

CVPR 2025
sym

Domain Generalization in CLIP via Learning with Diverse Text Prompts

Changsong Wen, Zelin Peng, Yu Huang, Xiaokang Yang, Wei Shen

CVPR 2025
sym
CVPR 2025
sym

Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space

Zelin Peng, Zhengqin Xu, Zhilin Zeng, Changsong Wen, Yu Huang, Menglin Yang, Feilong Tang, Wei Shen

ICCV 2023
sym

Ordinal Label Distribution Learning

Changsong Wen, Xin Zhang, Xingxu Yao, Jufeng Yang

CVPR 2023
sym

DIP: Dual Incongruity Perceiving Network for Sarcasm Detection

Changsong Wen*, Guoli Jia*, Jufeng Yang