lg.png

Leigang Qu

Ph.D. candidate at NUS

NExT++ Research Center
Institute of Data Science, School of Computing
National University of Singapore


I am currently a Ph.D. candidate at NExT++, National University of Singapore (NUS), supversied by Prof. Tat-Seng Chua and mentored by Wenjie Wang. Before that, I obtained my Master’s degree from Shandong University in 2022, supervised by Prof. Liqiang Nie and mentored by Prof. Meng Liu. I have also interned at ByteDance Seed, collaborating with Dr. Lu Jiang and Dr. Feng Cheng.

My research interests lie in Visual Content Generation, Multimodal Information Retrieval, and Multimodal Large Language Models.

News

Oct 2025 Announce our new work, TTOM (TTOM: Test-Time Optimization and Memorization for Compositional Video Generation)!
Jun 2025 Announce our new work, VINCIE (VINCIE: Unlocking In-context Image Editing from Video)!
Feb 2025 Our work, SILMM (SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation), accepted by CVPR’25!
Jan 2025 Our work, TIGeR (TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models), accepted by ICLR’25!
Dec 2024 Announce our new work, SILMM (Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation)!
Jun 2024 Announce our new work, TIGeR (Unifed Text-to-Image Generation and Retrieval)!
Feb 2024 Our work, DPT (Discriminative Probing and Tuning for Text-to-Image Generation), accepted by CVPR’24!
Aug 2023 Our work, LayoutLLM-T2I (Eliciting Layout Guidance from LLM for Text-to-Image Generation), accepted by ACM MM’23!
Apr 2023 Our work, LeaPRR (Learnable Pillar-based Re-ranking for Image-Text Retrieval), accepted by SIGIR’23!
Aug 2022 Start my Ph.D. study at National University of Singapore (NUS)!

Selected Publications/Preprints [Full List]

  1. arXiv’25
    TTOM: Test-Time Optimization and Memorization for Compositional Video Generation
    Leigang Qu* ,  Ziyang Wang* ,  Na Zheng ,  Wenjie Wang ,  Liqiang Nie ,  and  Tat-Seng Chua
    In arXiv preprint , 2025
    PDF Code Website
  2. arXiv’25
    VINCIE: Unlocking In-context Image Editing from Video
    Leigang Qu ,  Feng Cheng ,  Ziyan Yang ,  Qi Zhao ,  Shanchuan Lin ,  Yichun Shi ,  Yicong Li ,  Wenjie Wang ,  Tat-Seng Chua ,  and  Lu Jiang
    In arXiv preprint , 2025
    PDF Code Website
  3. CVPR’25
    SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation
    Leigang Qu ,  Haochuan Li ,  Wenjie Wang ,  Xiang Liu ,  Juncheng Li ,  Liqiang Nie ,  and  Tat-Seng Chua
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2025
    PDF Code Website
  4. ICLR’25
    TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models
    Leigang Qu ,  Haochuan Li ,  Tan Wang ,  Wenjie Wang ,  Yongqi Li ,  Liqiang Nie ,  and  Tat-Seng Chua
    In The Thirteenth International Conference on Learning Representations , 2025
    PDF Code Website
  5. CVPR’24
    Discriminative Probing and Tuning for Text-to-Image Generation
    Leigang Qu ,  Wenjie Wang ,  Yongqi Li ,  Hanwang Zhang ,  Liqiang Nie ,  and  Tat-Seng Chua
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2024
    PDF Code Website
  6. ACM MM’23
    LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation
    Leigang Qu* ,  Shengqiong Wu* ,  Hao Fei ,  Liqiang Nie ,  and  Tat-Seng Chua
    In Proceedings of the 31st ACM International Conference on Multimedia , 2023
    (Oral)
    PDF Code Website
  7. SIGIR’23
    Learnable Pillar-based Re-ranking for Image-Text Retrieval
    Leigang Qu ,  Meng Liu ,  Wenjie Wang ,  Zhedong Zheng ,  Liqiang Nie ,  and  Tat-Seng Chua
    In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval , 2023
    PDF Code
  8. ACM MM’22
    Search-oriented Micro-video Captioning
    Liqiang Nie ,  Leigang Qu ,  Dai Meng ,  Min Zhang ,  Qi Tian ,  and  Alberto Del Bimbo
    In Proceedings of the 30th ACM international conference on multimedia , 2022

    (Best Paper Award)

    PDF Code
  9. SIGIR’21
    Dynamic Modality Interaction Modeling for Image-Text Retrieval
    Leigang Qu ,  Meng Liu ,  Jianlong Wu ,  Zan Gao ,  and  Liqiang Nie
    In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval , 2021

    (Best Student Paper Award)

    PDF Code
  10. ACM MM’20
    Context-Aware Multi-View Summarization Network for Image-Text Matching
    Leigang Qu ,  Meng Liu ,  Da Cao ,  Liqiang Nie ,  and  Qi Tian
    In Proceedings of the 28th ACM International Conference on Multimedia , 2020
    (Oral)
    PDF Code

Academic Services

Invited Reviewer for TIP, TMM, TKDE, TOIS, TCSVT, ToMM, IPM, Information Sciences, Multimedia Systems, Neurocomputing
Invited Reviewer of ICML in 2024
Program Committee Member/Reviewer of NeurIPS, ACL, SIGIR, ACMMM, KDD, AAAI in 2024
Program Committee Member/Reviewer of SIGIR, ACMMM, AAAI, KDD, SIGIR-AP in 2023

Honors

• Research Achievement Award, NUS SoC, 2023
• Student Travel Grant, SIGIR, 2023
• Best Paper Award, ACMMM, 2022
• President's Graduate Fellowship, NUS, 2022
• Best Student Paper Award, SIGIR, 2021