Hello! I’m Yikun Liu. I am currently a 3rd-year PhD candidate of MediaBrain at Shanghai Jiao Tong University (SJTU), advised by Prof.Weidi Xie, Prof.Jiangchao Yao and Prof.Yanfeng Wang. Previously, I received my B.S. degree from Beijing University of Posts and Telecommunications (BUPT) in june 2023.
My current research interest lies in multi-modal representation learning. Feel free to reach me if you are seeking any form of cooperation.
🔥 News
- 2026.06: 🎉🎉 One paper (VersaViT) has been accepted by ECCV.
- 2026.03: 🎉🎉 One paper (SanityCIR) has been accepted by CVPRW.
- 2026.02: 🎉🎉 One paper (POINTS-Long) has been accepted by CVPR.
- 2025.05: Start internship at Tencent, Shanghai.
- 2025.02: 🎉🎉 One paper (LamRA) has been accepted by CVPR.
- 2024.07: Start internship at Xiaohongshu, Shanghai.
- 2024.02: 🎉🎉 One paper (UFE-AVS) has been accepted by CVPR.
- 2023.08: 🎉🎉 One paper (ZS-CIR) has been accepted by BMVC.
📝 Publications
ECCV 2026 VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization
Yikun Liu, Yuan Liu, Shangzhe Di, Haicheng Wang, Zhongyin Zhao, Le Tian, Xiao Zhou, Jie Zhou, Jiangchao Yao, Yanfeng Wang, Weidi Xie.
CVPR 2026 POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs
Haicheng Wang*, Yuan Liu*, Yikun Liu*, Zhemeng Yu, Zhongyin Zhao, Yangxiu You, Zilin Yu, Le Tian, Xiao Zhou, Jie Zhou, Weidi Xie, Yanfeng Wang.
CVPRW 2026 A Sanity Check on Composed Image Retrieval
Yikun Liu, Jiangchao Yao, Weidi Xie, Yanfeng Wang.
Arxiv 2026 POINTS-GUI-G: GUI-Grounding Journey
Zhongyin Zhao, Yuan Liu, Yikun Liu, Haicheng Wang, Le Tian, Xiao Zhou, Yangxiu You, Zilin Yu, Yang Yu, Jie Zhou.
ICCV 2025 Learning Streaming Video Representation via Multitask Training
Yibin Yan, Jilan Xu, Shangzhe Di, Yikun Liu, Yudi Shi, Qirui Chen, Zeqian Li, Yifei Huang, Weidi Xie.
CVPR 2025 LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant
Yikun Liu, Pingan Chen, Jiayin Cai, Xiaolong Jiang, Yao Hu, Jiangchao Yao, Yanfeng Wang, Weidi Xie.
CVPR 2024 Audio-Visual Segmentation via Unlabeled Frame Exploitation
Jinxiang Liu, Yikun Liu, Fei Zhang, Chen Ju, Ya Zhang, Yanfeng Wang.
BMVC 2023 Zero-shot Composed Text-Image Retrieval
Yikun Liu, Jiangchao Yao, Yanfeng Wang, Ya Zhang, Weidi Xie.
💻 Internships
- 2025.05 - now, Tencent, China.
- 2024.07 - 2025.04, Xiaohongshu, China.
🎖 Honors and Awards
- 2021.12 China National Scholarship
- 2021.04 Finalist Prize in MCM Competition (Top 1%)