Yunnan Wang (王允楠)

Currently, I am a thrid-year Ph.D. student of the joint program between Artificial Intelligence Institute, Shanghai Jiao Tong University (supervised by Prof. Xiaokang Yang (杨小康) and Eastern Institute for Advanced Study (co-supervised by Prof. Kevin Zeng (曾文军) and Prof. Xin Jin (金鑫)). Meanwhile, I am also a research intern at Ant Research (supervised by Dr. Kecheng Zheng (郑可成)). Before that, I received my M.S. degree from Shanghai Jiao Tong University in 2023 (supervised by Prof. Jianxun Li (李建勋)) and my B.S. degree from Northwestern Polytechnical University in 2020 (supervised by Prof. Jianhua He (何建华)). Besides, I also had a great time interning at 2012 Lab of Huawei and Applied Machine Learning of ByteDance .

My research interests include Computer Vision, Semantic Segmentation, Un-/Semi-supervised Learning from 2019, and AI Generated Content (AIGC) and Multimodal Representation Learning from 2023.

🔥 News

2026.01: 🎉🎉 We are excited to introduce LingBot-VLA, a pragmatic Vision-Language-Action foundation model.
2025.10: 🎉🎉 I was invited to participate in the 3rd Westlake University Half-Marathon (1h29m) and broke the record of EIT.
2025.10: 🎉🎉 I was awarded the National Scholarship for Doctoral Students (Top 3% in SJTU)~
2025.07: 🎉🎉 One paper was accepted by TCSVT (JCR Q1) and ACM MM Industry Demonstration (CCF-A)~
2025.06: 🎉🎉 One paper was accepted by ICCV (CCF-A)~
2025.03: 🎉🎉 One paper was accepted by KBS (JCR Q1)~
2024.12: 🎉🎉 One paper was accepted by TMI (Top Journal in Medical Imaging, CCF-B)~
2024.10: 🎉🎉 I was invited to participate in the 2nd Westlake University Half-Marathon (1h35m), competing with Yigong Shi (施一公).
2024.09: 🎉🎉 Two papers (with one Spotlight) were accepted by NeurlPS 2024 (CCF-A)~
2024.08: 🎉🎉 One paper was accepted by BIBM 2024 (Top Conference in Bioinformatics, CCF-B)~
2024.07: 🎉🎉 I joined Interaction Intelligence Lab, Ant Research as a research intern.
2024.04: 🎉🎉 Congratulations to Prof. Kevin Zeng on his election as the International Fellow of the Canadian Academy of Engineering.
2024.04: 🎉🎉 One paper was accepted by IJCAI 2024 (CCF-A)~
2023.09: 🎉🎉 I joined Eastern Institute for Advanced Study as a research intern.
2023.05: 🎉🎉 Shanghai Jiao Tong University officially released a news about me.
2023.03: 🎉🎉 I will continue to pursue my Ph.D. degree at Shanghai Jiao Tong University.
2023.03: 🎉🎉 I graduated with the highest honors from Shanghai Jiao Tong University.
2022.05: 🎉🎉 One paper was accepted by IROS 2022 (Top Conference in Robotics, CCF-C)~

📝 Publications

$^\star$Equal contribution; $^\dagger$Corresponding author; $^\ddagger$Project lead

Technical Report

sym

A Pragmatic VLA Foundation Model

Wei Wu$^\star$, Fan Lu$^\star$, Yunnan Wang$^\star$, Shuai Yang$^\star$, Shi Liu$^\star$, Fangjing Wang$^\star$, Qian Zhu, He Sun, Yong Wang, Shuailei Ma, Yiyu Ren, Kejia Zhang, Hui Yu, Jingmei Zhao, Shuai Zhou, Zhenqi Qiu, Houlong Xiong, Ziyu Wang, Zechen Wang, Ran Cheng, Yong-Lu Li, Yongtao Huang, Xing Zhu, Yujun Shen, Kecheng Zheng$^\ddagger$

Technical Report.

Project/Arxiv/Code

NeurlPS 2024

sym

Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation

Yunnan Wang, Ziqiang Li, Zequn Zhang, Wenyao Zhang, Baao Xie, Xihui Liu, Wenjun Zeng, Xin Jin$^\dagger$

Annual Conference on Neural Information Processing Systems (NeurIPS 2024). Spotlight.

Project/Arxiv/Code

TCSVT 2025

sym

Canvas: Compositional Generation for Art Painting with Seamless Subject-Driven Infusion

Yunnan Wang, Ziqiang Li, Wenyao Zhang, Lexiang Lv, Zequn Zhang, Xiaoyu Shen, Xin Jin, Wenjun Zeng$^\dagger$

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT 2025).

ACM International Conference on Multimedia (ACM MM 2024 Industry Demonstration).

Project/Arxiv/Code

NeurlPS 2024

sym

Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models

Baao Xie, Qiuyu Chen,Yunnan Wang, Zequn Zhang, Xin Jin$^\dagger$, Wenjun Zeng

Annual Conference on Neural Information Processing Systems (NeurIPS 2024).

Project/Arxiv/Code

ICCV 2025

sym

Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation

Wenyao Zhang, Hongsi Liu, Bohan Li, Jiawei He, Zekun Qi, Yunnan Wang, Shengyang Zhao, XinQiang Yu, Wenjun Zeng, Xin Jin$^\dagger$

IEEE/CVF International Conference on Computer Vision (ICCV 2025).

Project/Arxiv/Code

TMI 2024

sym

Exploring Contrastive Pre-training for Domain Connections in Medical Image Segmentation

Zequn Zhang$^\star$, Yun Jiang$^\star$, Yunnan Wang, Baao Xie, Wenyao Zhang, Yuhang Li, Zhen Chen, Xin Jin, Wenjun Zeng$^\dagger$

IEEE Transactions on Medical Imaging (TMI 2024).

Project/Arxiv/Code

BIBM 2024

sym

Consistency Prior Matters: Biomedical-Prompting Dual Augmentation for Domain Adaptive Medical Image Segmentation

Yunnan Wang, Zequn Zhang, Xin Jin, Wenjun Zeng$^\dagger$

IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2024). Oral Presentation.

Project/Arxiv/Code

KBS 2025

sym

Single-Instance Feature Bias Calibrating Learning Base EM for Text-to-Image Person Re-identification

Yifeng Gou, Ziqiang Li, Junyin Zhang, Yunnan Wang, Yongxin Ge$^\dagger$

Knowledge-based Systems (KBS 2025).

Project/Arxiv/Code

IJCAI 2024

sym

Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion

Bohan Li, Yasheng Sun, Zhujin Liang, Dalong Du, Zhuanghui Zhang, Xiaofeng Wang, Yunnan Wang, Xin Jin, Wenjun Zeng$^\dagger$

International Joint Conference on Artificial Intelligence (IJCAI 2024).

Project/Arxiv/Code

IROS 2022

sym

Bilateral Knowledge Distillation for Unsupervised Domain Adaptation of Semantic Segmentation

Yunnan Wang, Jianxun Li$^\dagger$

IEEE/RSJ International Conference on Intelligent Robots and System (IROS 2022). Oral Presentation.

Project/Arxiv/Code

Preprint

sym

Vision-Centric Activation and Coordination for Multimodal Large Language Models

Yunnan Wang$^\star$, Fan Lu$^\star$, Kecheng Zheng$^\ddagger$, Ziyuan Huang, Ziqiang Li, Wenjun Zeng, Xin Jin$^\dagger$

Under Review.

Project/Arxiv/Code

📖 Educations

2023.03 - present, Ph.D. in Computer Science,Shanghai Jiao Tong University (SJTU), Shanghai
2020.09 - 2023.03, M.S. in Automation, Shanghai Jiao Tong University (SJTU), Shanghai
2016.09 - 2020.09, B.S. in Automation, Northwestern Polytechnical University (NWPU), Xi’an, Shaanxi

💻 Internships

2024.07 - present: Interaction Intelligence Lab, Ant Research , Hangzhou, Zhejiang
- Position: Multi-Modal Algorithm Intern
- Duty: Multi-Modal Algorithm Research
- Supervisor: Dr. Kecheng Zheng
2023.09 - present: College of Information Science and Technology, Eastern Institute for Advanced Study , Ningbo, Zhejiang
- Position: Computer Vision Algorithm Intern
- Dutiy: AI Generated Content (AIGC) Research
- Supervisor: Prof. Wenjun Zeng and Prof. Xin Jin
2022.06 - 2022.10: Central Media Technology Institute, 2012 Lab, Huawei , Shanghai
- Position: Computer Vision Algorithm Intern
- Duty: Optical Flow Estimation, Motion Detection, and Lane Detection
- Supervisor: Dr. Jia Cai
2022.03 - 2022.06: Applied Machine Learning (AML), ByteDance , Shanghai
- Position: Machine Learning Algorithm Intern
- Duty: Recommendation/Advertising/Search Algorithm Research
- Supervisor: Dr. Xiang Li

🎖 Honors and Awards

💬 Activities

Reviewer: NeurlPS, CVPR, ICCV, ACM MM, TCSVT and TNNLS etc.
2023.03 - present, Alumni Trustee of Shanghai Jiao Tong University.
2020.09 - 2023.03, Monitor of Master Class B2003292, Shanghai Jiao Tong University.
2016.09 - 2020.06, Mental-Health Counselor, Northwestern Polytechnical University.
Avocation : Competitive road cycling (more than 10 years); Marathon (Half Marathon PB: 1h22m, Marathon PB: 3h08m).