Weijia Li 李唯嘉

Associate Professor

Shenzhen International Graduate School

Tsinghua University

Email: liweijia@sz.tsinghua.edu.cn

Google Scholar

I am a Tenure-Track Associate Professor at Institute of Data and Information, SIGS, Tsinghua University, starting from 2026 Spring. Previously, I was an Associate Professor (2021.11-2026.1) at Sun Yat-sen University. I was a Post-doc Researcher (2019.11-2021.11) at MMLab, Department of Information Engineering, CUHK, working with Prof. Dahua Lin. I received my Ph.D. (2014-2019) from Department of Earth System Science, Tsinghua University, advised by Prof. Haohuan Fu, and the Bachelor degree (2010-2014) from Department of Computer Science, Sun Yat-sen University.

My research interests include computer vision, deep learning, and their applications in urban remote sensing, with a recent focus on large multimodal models, generative models and AI agents. I serve as a reviewer for many SCI journals and TOP conferences, including RSE, ISPRS P&RS, IEEE TIP/TGRS/GRSM, CVPR, ICCV, ECCV, NeurIPS, ICLR, AAAI, etc.

I am looking for self-motivated PostDoc, graduate/undergraduate students and research interns. We have close research collaboration with Shanghai AI Lab. Please feel free to contact me if you are interested!

清华深研院课题组招收博士后、2027年入学的保研/考研/港澳台/国际学生，并常年招收优秀的科研实习生加入。有兴趣的同学请尽早与我邮件联系！

2027届计算机技术专业硕士仍有少量推免名额，有意向且已申请该项目的同学请尽早与我邮件联系！

news

Jul 20, 2026 Mind-Brush is accepted by SIGGRAPH Asia 2026!
Jun 20, 2026 RealGen is accepted by ECCV 2026 as ORAL!
May 1, 2026 OmniAID is accepted by ICML 2026!
Feb 21, 2026 Four papers (OmniDocLayout, etc.) are accepted by CVPR 2026!
Jan 26, 2026 Earth-Agent and UrbanFeel are accepted by ICLR 2026!
Sep 19, 2025 Four papers (FakeVLM, Blink-Twice, etc.) are accepted by NeurIPS 2025!
Jun 26, 2025 Three papers (LEGION, SkyDiffusion, WhereamI) are accepted by ICCV 2025!
Jan 23, 2025 LOKI is accepted by ICLR 2025 as spotlight (scores:8/8/8/8)!
Dec 10, 2024 UrBench and VHM are accepted by AAAI 2025!
Jul 1, 2024 Two papers are accepted by ECCV 2024!
Apr 5, 2024 SG-BEV is selected as Highlight (2.8%) by CVPR 2024!
Feb 27, 2024 Three papers are accepted by CVPR 2024!
Feb 28, 2023 OmniCity is accepted by CVPR 2023!
Nov 19, 2022 One paper is accepted by AAAI 2023!

selected publications

  1. ICLR
    Earth-agent: Unlocking the full landscape of earth observation with agents
    Peilin Feng#, Zhutao Lv#, Junyan Ye, Xiaolei Wang, Xinjie Huo, Jinhua Yu, Wanghan Xu, Wenlong Zhang, Lei Bai, Conghui He, and Weijia Li*
    ICLR 2026
    Paper project Code
  2. CVPR
    OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning
    Hengrui Kang#, Zhuangcheng Gu#, Zhiyuan Zhao, Zichen Wen, Bin Wang, Weijia Li*, and Conghui He*
    CVPR (Highlight) 2026
    Paper
  3. ICML
    OmniAID: Decoupling Semantic and Artifacts for Universal AI-Generated Image Detection in the Wild
    Yuncheng Guo, Junyan Ye, Chenjue Zhang, Hengrui Kang, Haohuan Fu, Conghui He, and Weijia Li*
    ICML 2026
    Paper Code
  4. ECCV
    Realgen: Photorealistic text-to-image generation via detector-guided rewards
    Junyan Ye#, Leiqi Zhu#, Yuncheng Guo, Dongzhi Jiang, Zilong Huang, Yifan Zhang, Zhiyuan Yan, Haohuan Fu, Conghui He, and Weijia Li*
    ECCV (ORAL) 2026
    Paper project Code
  5. NeurIPS
  6. NeurIPS
    Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation
    Siwei Wen#, Junyan Ye#, Peilin Feng, Hengrui Kang, Zichen Wen, Yize Chen, Jiang Wu, Wenjun Wu, Conghui He, and Weijia Li*
    NeurIPS 2025
    Paper Code
  7. ICCV
    LEGION: Learning to Ground and Explain for Synthetic Image Detection
    Hengrui Kang#, Siwei Wen#, Zichen Wen#, Junyan Ye, Weijia Li*, Peilin Feng, Baichuan Zhou, Bin Wang, Dahua Lin, Linfeng Zhang, and Conghui He*
    ICCV (Highlight) 2025
    Paper project Code
  8. ICCV
    Where am I? Cross-View Geo-localization with Natural Language Descriptions
    Junyan Ye#, Honglin Lin#, Leyan Ou, Dairong Chen, Zihao Wang, Conghui He, and Weijia Li*
    ICCV 2025
    Paper project Code
  9. ICCV
    Leveraging BEV Paradigm for Ground-to-Aerial Image Synthesis
    Junyan Ye#, Jun He#, Weijia Li*, Zhutao Lv, Jinhua Yu, Haote Yang, and Conghui He
    ICCV 2025
    Paper project Code
  10. ICLR
    LOKI: A comprehensive synthetic data detection benchmark using large multimodal models
    Junyan Ye#, Baichuan Zhou#, Zilong Huang#, Junan Zhang#, Tianyi Bai, Hengrui Kang, Jun He, Honglin Lin, Zihao Wang, Tong Wu, Zhizhen Wu, Yiping Chen, Dahua Lin, Conghui He*, and Weijia Li*
    ICLR (Spotlight) 2025
    Paper project Code
  11. AAAI
    UrBench: A comprehensive benchmark for evaluating large multimodal models in multi-view urban scenarios
    Baichuan Zhou#, Haote Yang#, Dairong Chen#, Junyan Ye#, Tianyi Bai, Jinhua Yu, Songyang Zhang, Dahua Lin, Conghui He*, and Weijia Li*
    AAAI 2025
    Paper project Code
  12. CVPR
    SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation
    Junyan Ye, Qiyan Luo, Jinhua Yu, Huaping Zhong, Zhimeng Zheng, Conghui He, and Weijia Li*
    CVPR (Highlight) 2024
    Paper Code
  13. CVPR
    3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions
    Weijia Li#, Haote Yang#, Zhenghao Hu, Juepeng Zheng, Gui-Song Xia, and Conghui He*
    CVPR 2024
    Paper Code
  14. CVPR
    OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images
    Weijia Li, Yawen Lai, Linning Xu, Yuanbo Xiangli, Jinhua Yu, Conghui He*, Gui-Song Xia*, and Dahua Lin
    CVPR 2023
    Paper project Video Code