Yingchen Yu

Research Scientist  ·  Ph.D., Nanyang Technological University

prof_pic.webp

I was a Research Scientist @ TikTok/ByteDance, Singapore. I received my Ph.D. in Computer Science from Nanyang Technological University (NTU), supervised by Prof. Shijian Lu, under the Alibaba–NTU Industrial Postgraduate Programme (IPP).

Before that, I obtained my B.E. degree in Electrical & Electronic Engineering at NTU, and my M.S. degree in Computer Science at National University of Singapore (NUS).

Research Interests

  • Visual Generation
  • Multimodal LLMs
  • GUI Agents

news

  1. Our paper Let ViT Speak was accepted by ECCV 2026!
  2. Our paper TextSeg++ was accepted by TPAMI.
  3. Two papers CodeDance and ThinkGen were accecpted by CVPR 2026.
  4. Our paper RoSE was accecpted by ICLR 2026 as oral presentation.
  5. Our paper GUI-Rise was accecpted by NeurIPS 2025.
  6. Two paper Timeexpert and VTG were accecpted by ICCV 2025.
  7. One paper was accecpted by TMM.

selected publications

  1. SteerVTE.webp
    SteerVTE: Seamless Video Text Editing with Style and Glyph Control
    Kai Zeng, Moran Li, Zhengwei Wang, Yingchen Yu†, Yiheng Lin, and 4 more authors
    arXiv
    arXiv preprint arXiv:2606.23254, 2026
    arXiv Model Data Code Website
  2. rose.webp
    Monocular Normal Estimation via Shading Sequence Estimation
    Zongrui Li, Xinhua Ma, Minghui Hu, Yunqing Zhao, Yingchen Yu, and 4 more authors
    ICLROral
    In International Conference on Learning Representations (ICLR), 2026
  3. Timeexpert.webp
    Timeexpert: An expert-guided video llm for video temporal grounding
    Zuhao Yang, Yingchen Yu, Yunqing Zhao, Shijian Lu, and Song Bai
    ICCV
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025
    Website
  4. GUI-Rise.webp
    GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation
    Tao Liu, Chongyu Wang, Rongjie Li, Yingchen Yu, Xuming He, and 1 more author
    NeurIPS
    Advances in Neural Information Processing Systems (NeurIPS), 2025
    Code
  5. MorphNeRF.webp
    MorphNeRF: Text-Guided 3D-Aware Editing via Morphing Generative Neural Radiance Fields
    Yingchen Yu, Rongliang Wu, Yifang Men, Shijian Lu, Miaomiao Cui, and 2 more authors
    TMM
    IEEE Transactions on Multimedia, 2024
  6. MISE.webp
    Multimodal image synthesis and editing: A survey
    Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang, Shijian Lu, and 4 more authors
    TPAMI
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
    arXiv Code Website
  7. RABIT.webp
    Bi-level feature alignment for versatile image translation and manipulation
    Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang, Kaiwen Cui, and 3 more authors
    ECCV
    In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XVI (ECCV), 2022
    arXiv Code
  8. CF-CLIP.webp
    Towards counterfactual image manipulation via clip
    Yingchen Yu, Fangneng Zhan, Rongliang Wu, Jiahui Zhang, Shijian Lu, and 4 more authors
    ACM MM
    In Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), 2022
    arXiv Code
  9. WaveFill.webp
    Wavefill: A wavelet-based generation network for image inpainting
    Yingchen Yu, Fangneng Zhan, Shijian Lu, Jianxiong Pan, Feiying Ma, and 2 more authors
    ICCVOral
    In Proceedings of the IEEE/CVF international conference on computer vision (ICCV), 2021
    arXiv Code
  10. BATFill.webp
    Diverse image inpainting with bidirectional and autoregressive transformers
    Yingchen Yu, Fangneng Zhan, Rongliang Wu, Jianxiong Pan, Kaiwen Cui, and 4 more authors
    ACM MMOral
    In Proceedings of the 29th ACM International Conference on Multimedia (ACM MM), 2021
    arXiv Code