Computer Vision & Learning Group
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]
|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.|
|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~|
|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.|
ToddlerDiffusion: Flash Interpretable Controllable Diffusion ModelIn Submission, 2024
Generative Data Augmentation Improves Scribble-supervised Semantic SegmentationIn ARXIV, 2023Explore diffusion model for data augmention in segmentation task.
On the Few-Shot Generalization of Learning on Implicit Neural RepresentationsIn ICCV NeRF4ADR Workshop, 2023Explore few-shot generalization of INR on images.
Flow Matching for Conditional Text Generation in a Single Sampling StepIn Submission, 2023Flow Matching for text generation
Latent Space Editing in Transformer-based Flow MatchingIn ICML 2023 Workshop, New Frontiers in Learning, Control, and Dynamical Systems, 2023
Self-Guided Diffusion ModelsIn CVPR, 2023A 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.