Xinlei Yu - Homepage

About Me

Hi! I am Xinlei Yu, an incoming PhD student of CUHK@MMLab, supervised by Prof. Xiangyu Yue. Previously, I work as research assistant in NUS@LV-Lab, supervised by Prof. Shuicheng Yan and Dr. Xiaobin Hu. I have published several top conferences and journals, such as CVPR, ICLR, ICML, etc.

My research has a broad focus, covering multimodal AI, agentic AI, and embodied AI. Please feel free to contact me for any discussion or collaboration.

News

04/2026 Two papers accepted at ICML26, with one as first author: L2-VMAS.

04/2026 The survey: The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook released as first author and project organizer, featured as Hugging Face Daily Paper #2.

02/2026 Three papers accepted at CVPR26, with two as first author: MACT (Spotlight) and VisMem.

01/2026 Two papers accepted at ICLR26, with one as first author: ViF.

Education

Multimedia Laboratory , The Chinese University of Hong Kong (CUHK@MMLab)

Ph.D.

Advisor: Prof. Xiangyu Yue

09/2027 - Future

National University of Singapore (NUS)

Master

08/2025 - 06/2026

Experience

Natural Language Laboratory, Explore Academy, JD

TGT (Tech Genius Team) Program Intern

Advisor: Dr. Jiaqi Wang

06/2026 - Present

Learning and Vision Laboratory, National University of Singapore (NUS@LV-Lab)

Research Assistant

Advisor: Prof. Shuicheng Yan and Dr. Xiaobin Hu

05/2025 - 06/2026

Main Publications

DOPD: Dual On-policy Distillation

Xinlei Yu, Gen Li , Qingyi Si, Guibin Zhang1, Yuqi Xu , Congcong Wang, Shuai Dong, Kaiwen Tuo, Xiangyu Zeng, Kaituo Feng, Qunzhong Wang, Yang Shi, Xiaobin Hu, Xiangyu Yue, Jiaqi Wang, Shuicheng Yan

Preprint

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

Xinlei Yu, Zhangquan Chen, Yongbo He, Tianyu Fu, Cheng Yang, Chengming Xu, Yue Ma, Xiaobin Hu, Zhe Cao, Jie Xu, Guibin Zhang, Jiale Tao, Jiayi Zhang, Siyuan Ma, Kaituo Feng, Haojie Huang, Youxing Li, Ronghao Chen, Huacan Wang, Chenglin Wu, Zikun Su, Xiaogang Xu, Kelu Yao, Kun Wang, Chen Gao, Yue Liao, Ruqi Huang, Tao Jin, Cheng Tan, Jiangning Zhang, Wenqi Ren, Yanwei Fu, Yong Liu, Yu Wang, Xiangyu Yue, Yu-Gang Jiang, Shuicheng Yan

Preprint

Dual Latent Memory for Visual Multi-agent System

Xinlei Yu, Chengming Xu, Zhangquan Chen, Bo Yin, Cheng Yang, Yongbo He, Yihao Hu, Jiangning Zhang, Cheng Tan, Xiaobin Hu, Shuicheng Yan

ICML 2026

Vismem: Latent Vision Memory Unlocks Potential of Vision-language Models

Xinlei Yu, Chengming Xu, Guibin Zhang, Zhangquan Chen, Yudong Zhang, Yongbo He, Peng-Tao Jiang, Jiangning Zhang, Xiaobin Hu, Shuicheng Yan

CVPR 2026

Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow

Xinlei Yu, Chengming Xu, Guibin Zhang, Yongbo He, Zhangquan Chen, Zhucun Xue, Jiangning Zhang, Yue Liao, Xiaobin Hu, Yu-Gang Jiang, Shuicheng Yan

ICLR 2026

Visual Document Understanding and Reasoning: A Multi-agent Collaboration Framework with Agent-wise Adaptive Test-time Scaling

Xinlei Yu, Chengming Xu, Zhangquan Chen, Yudong Zhang, Shilin Lu, Cheng Yang, Jiangning Zhang, Shuicheng Yan, Xiaobin Hu

CVPR 2026 (Spotlight)

Crisp-Sam2: Sam2 with Cross-modal Interaction and Semantic Prompting for Multi-organ Segmentation

Xinlei Yu, Changmiao Wang, Hui Jin, Ahmed Elazab, Gangyong Jia, Xiang Wan, Changqing Zou, Ruiquan Ge

ACM MM 2025