Tong Wang

Biography个人简介

About关于我

I am currently a Ph.D. student at the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications of Ministry of Education, Southeast University.

I am also a visiting Ph.D. student at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI).

我目前是东南大学教育部新一代人工智能技术及其交叉应用重点实验室的博士研究生。

同时，我也是阿联酋人工智能大学（MBZUAI）的访问博士生。

Research Interests:研究兴趣：

  • Multimodal Models:多模态模型： Vision-Language Models, Agentic AI, LLM Reasoning视觉语言模型，智能体 AI，大语言模型推理
  • Generative AI:生成式 AI： Autoregressive Models, Diffusion Models, Efficient Generative Models, World Models, Video Generation自回归模型，扩散模型，高效生成模型，世界模型，视频生成
  • Medical Image Analysis:医学图像分析： Image Segmentation, Medical Video Analysis, Medical Image Representation Learning图像分割，医学视频分析，医学图像表征学习

I welcome research discussions and collaborations around multimodal models, generative AI, and medical image analysis.
If our interests overlap, feel free to contact me at tong.wang AT mbzuai.ac.ae. 欢迎围绕多模态模型、生成式 AI 和医学图像分析开展交流与合作。
如果我们的研究兴趣契合，欢迎通过 tong.wang AT mbzuai.ac.ae 联系我。

News最新动态

Recent近期
  • [Jun, 2026] ARTEMIS is available on arXiv.ARTEMIS 已发布在 arXiv。
  • [Jun, 2026] Two papers have been accepted by MICCAI 2026. 🎉🎉🎉两篇论文被 MICCAI 2026 接收。🎉🎉🎉
  • [May, 2026] CMSA-Net has been accepted by MICCAI 2026. 🎉🎉🎉CMSA-Net 被 MICCAI 2026 接收。🎉🎉🎉
  • [Feb, 2026] CMSA-Net is available on arXiv.CMSA-Net 已发布在 arXiv。
  • [Nov, 2025] TGS-Agent has been accepted by AAAI 2026. 🎉🎉🎉TGS-Agent 被 AAAI 2026 接收。🎉🎉🎉
  • [Nov, 2025] DiverseVAR is available on arXiv.DiverseVAR 已发布在 arXiv。
  • [Aug, 2025] Composed Object Retrieval is available on arXiv.Composed Object Retrieval 已发布在 arXiv。

Experiences经历

Timeline时间线
MBZUAI logo

Mohamed bin Zayed University of Artificial Intelligence

Visiting Student | 2024 - Present访问学生 | 2024年至今

Mentors:合作导师： Prof. Fahad Shahbaz Khan, Prof. Salman Khan, Dr. Nian Liu and和 Dr. Yutong Xie

Research focus: Multimodal Models, Generative Model, Medical Image Analysis研究重点：多模态模型、生成模型、医学图像分析

Southeast University logo

Southeast University

Ph.D. Student | 2022 - Present博士研究生 | 2022年至今

Ph.D. Advisor:博士生导师： Prof. Guanyu Yang

Research focus: Computer Vision, Medical Image Analysis研究重点：计算机视觉、医学图像分析

Publications论文发表

Selected Works代表工作

Preprint Papers预印本论文

ARTEMIS: Agent-guided Reliability-aware Temporal Mask Evolution for Imperfectly Supervised Video Polyp SegmentationARTEMIS：面向不完美监督视频息肉分割的智能体引导可靠性感知时序掩码演化

Tong Wang, Siwen Wang, Yaolei Qi, Jinxing Zhou, Yuting He, Guanyu Yang, Yutong Xie.

arXiv preprint arXiv:2606.20161

Preprint 2026 Paper论文 Code代码

Diversity Has Always Been There in Your Visual Autoregressive Models视觉自回归模型中的多样性一直存在

Tong Wang, Guanyu Yang, Nian Liu, Kai Wang, Yaxing Wang, Abdelrahman M Shaker, Salman Khan, Fahad Shahbaz Khan, Senmao Li.

arXiv preprint arXiv:2511.17074

Preprint 2025 Paper论文 Code代码 Page主页

Composed Object Retrieval: Object-level Retrieval via Composed Expressions组合对象检索：通过组合表达实现对象级检索

Tong Wang, Guanyu Yang, Nian Liu, Zongyan Han, Jinxing Zhou, Salman Khan, Fahad Shahbaz Khan.

arXiv preprint arXiv:2508.04424

Preprint 2025 Paper论文 Code代码

OpenSeg-R: Improving Open-Vocabulary Segmentation via Step-by-Step Visual ReasoningOpenSeg-R：通过逐步视觉推理改进开放词汇分割

Zongyan Han, Jiale Cao, Shuo Chen, Tong Wang, Jorma Laaksonen, Rao Muhammad Anwer.

arXiv preprint arXiv:2505.16974

Preprint 2025 Paper论文 Code代码

Conference Papers会议论文

CMSA-Net: Causal Multi-scale Aggregation with Adaptive Multi-source Reference for Video Polyp SegmentationCMSA-Net：用于视频息肉分割的因果多尺度聚合与自适应多源参考

Tong Wang, Yaolei Qi, Siwen Wang, Imran Razzak, Guanyu Yang, Yutong Xie.

arXiv preprint arXiv:2602.22821

MICCAI 2026 (Early Accept) Paper论文 Code代码 Page主页 Slides幻灯片 Poster海报

Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation先思考再分割：用于指代音视频分割的对象感知推理智能体

Jinxing Zhou, Yanghao Zhou, Mingfei Han, Tong Wang, Xiaojun Chang, Hisham Cholakkal, Rao Muhammad Anwer.

arXiv preprint arXiv:2508.04418

AAAI 2026 Paper论文 Code代码

Energy-induced Explicit Quantification for Multi-modality MRI Fusion面向多模态 MRI 融合的能量诱导显式量化

Xiaoming Qi, Yuan Zhang, Tong Wang, Guanyu Yang, Yueming Jin, Shuo Li.

European Conference on Computer Vision

ECCV 2024 Paper论文 Code代码

Journal Papers期刊论文

Polyp Segmentation via Semantic Enhanced Perceptual Network基于语义增强感知网络的息肉分割

Tong Wang, Xiaoming Qi, Guanyu Yang.

IEEE Transactions on Circuits and Systems for Video Technology

IEEE TCSVT 2024 Paper论文 Code代码

Neighborhood Contrastive Representation Learning for Attributed Graph Clustering面向属性图聚类的邻域对比表示学习

Tong Wang, Junhua Wu, Yaolei Qi, Xiaoming Qi, Juwei Guan, Yuan Zhang, Guanyu Yang.

Neurocomputing

NeuroCom 2023 Paper论文 Code代码

Multi-scale Graph Attention Subspace Clustering Network多尺度图注意力子空间聚类网络

Tong Wang, Junhua Wu, Zhenquan Zhang, Wen Zhou, Guang Chen, Shasha Liu.

Neurocomputing

NeuroCom 2021 Paper论文 Code代码

Awards and Honors奖励与荣誉

Honors荣誉
  • 2025, Outstanding Postgraduate, Southeast University.2025年，东南大学优秀研究生。
  • 2024, Outstanding Postgraduate, Southeast University.2024年，东南大学优秀研究生。
  • 2022, Outstanding Graduates, Nanjing Tech University.2022年，南京工业大学优秀毕业生。
  • 2022, Outstanding Master's Thesis, Nanjing Tech University.2022年，南京工业大学优秀硕士学位论文。
  • 2021, National Scholarship, Ministry of Education.2021年，教育部国家奖学金。
  • 2018, National Scholarship, Ministry of Education.2018年，教育部国家奖学金。

Services学术服务

Community学术共同体

Journal Reviewer期刊审稿人

  • IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT)
  • Neurocomputing
  • Knowledge-Based Systems

Conference Reviewer会议审稿人

  • ECCV 2026
  • MICCAI 2026
  • ICML 2026
  • CVPR 2026
  • AAAI 2026