Tao Hu

Ommer Lab.

prof_pic.jpg

Computer Vision & Learning Group

Akademiestr. 7,Munich

Ludwig Maximilian University of Munich

I am a PostDoc Researcher with Bjorn Ommer in Ommer-Group ( Stable Diffusion Group ). I finished my PhD at VISLab, University of Amsterdam, supervised by Cees Snoek and Pascal Mettes. Closely coorporated with David W Zhang, Yuki Asano, Basura Fernando.

Open to discussion and collaboration, feel free to send an email or message on WeChat.

Focused on introducing inductive bias into neural network to achieve data-efficiency by few-shot learning, generative model, etc. Have a conviction that generative modelling will be the future of discriminative modelling.

I'm on the job market. Feel free to contact me. [Generative AI Expert]

Publication | GitHub | CV(updated in Nov.2023) |
LinkedIn
| Research Note | Chat with me |Wechat

Tao Hu's wechat

News

Nov 20, 2023 An extension paper on self-guided diffusion models has been submitted, co-authored by Mathilde Caron and Yuki Asano. Stay tuned for updates. :sparkles:
Aug 7, 2023 I am selected for CVPR 2023, ICCV 2023, and BMVC 2023 Doctoral Consortium. Here is the Summary of my PhD Research.
Jun 29, 2023 Two papers about the flow matching are submitted, thanks to my coorporators~ :sparkles: :smile:
May 22, 2023 Happy to present my works at FoMo lectures, KAUST, JiangMen. Thanks for the invitation from Peter Bloem, Bernard.
Jan 29, 2023 Committee members confirmed: Theo Gevers, Marcel Worring, Efstratios Gavves, Bernard Ghanem, Tim Salimans. :smile:

Selected publications

2024

  1. ToddlerDiffusion: Flash Interpretable Controllable Diffusion Model
    Eslam Mohamed BAKR, Liangbing Zhao, Vincent Tao Hu, Matthieu Cord, Patrick Perez, and Mohamed Elhoseiny
    In Submission, 2024

2023

  1. ./scribbleseg.png
    Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation
    Jacob Schnell, Jieke Wang, Lu Qi, Vincent Tao Hu, and Meng Tang
    In ARXIV, 2023
    Explore diffusion model for data augmention in segmentation task.
  2. ./fsinr.png
    On the Few-Shot Generalization of Learning on Implicit Neural Representations
    Tao HuDavid W Zhang, Yunlu Chen, Teng Long, Yuki Asano, Pascal MettesEfstratios GavvesBasura Fernando, and Cees G.M. Snoek
    In ICCV NeRF4ADR Workshop, 2023
    Explore few-shot generalization of INR on images.
  3. ./fm-s2s.png
    Flow Matching for Conditional Text Generation in a Single Sampling Step
    In Submission, 2023
    Flow Matching for text generation
  4. ./fm.png
    Latent Space Editing in Transformer-based Flow Matching
    In ICML 2023 Workshop, New Frontiers in Learning, Control, and Dynamical Systems, 2023
  5. ./sgdm-why.png
    Self-Guided Diffusion Models
    In CVPR, 2023
    A bridge between the community of self-supervised learning and diffusion models. Short version to appear in NeurIPS 2022 Workshop on Score-Based Methods and NeurIPS 2022 Workshop Self-Supervised Learning Theory and Practice.

Misc

Youtube(For Fun): Vincent Talk

Chainlink hodler.