Xiaofeng Yang

prof_pic.jpg

I am currently a Research Fellow in NTU Singapore. I received my Ph.D. in Computer Science from Nanyang Technological University, where I was advised by Prof. Guosheng Lin. Prior to this, I obtained my Bachelor degree from NTU as well. My research interests include generative model theories (diffusion, flow matching), 3D generative models, post-training of diffusion models and multimodal learning.

News

Feb 02, 2025 Our work “Text-to-Image Rectified Flow as Plug-and-Play Priors” is accepted to ICLR 2025.

Selected Publications

  1. ICLR
    Text-to-Image Rectified Flow as Plug-and-Play Priors
    Xiaofeng Yang, Cheng Chen, Xulei Yang, and 2 more authors
    In International Conference on Learning Representations (ICLR), 2025
    HTML Code
  2. ECCV
    Learn to Optimize Denoising Scores: A Unified and Improved Diffusion Prior for 3D Generation
    Xiaofeng Yang*, Yiwen Chen*, Cheng Chen, and 5 more authors
    In European Conference on Computer Vision (ECCV), 2024
    HTML Code
  3. AAAI
    Diverse and Stable 2D Diffusion Guided Text to 3D Generation with Noise Recalibration
    Xiaofeng Yang, Fayao Liu, Yi Xu, and 3 more authors
    In AAAI Conference on Artificial Intelligence (AAAI), 2024
    HTML
  4. ECCV
    TRRNet: Tiered Relation Reasoning for Compositional Visual Question Answering
    Xiaofeng Yang, Guosheng Lin, Fengmao Lv, and 1 more author
    In European Conference on Computer Vision (ECCV), 2020
    HTML