publications

2025

1. Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions

   Stefan Andreas Baumann , Felix Krause , Michael Neumayr , Nick Stracke , Vincent Tao Hu , and Björn Ommer

   In CVPR , 2025

   Prompt Editing in T2I models

   Bib PDF Code Website

   @inproceedings{baumann2024attributecontrol,
     title = {{C}ontinuous, {S}ubject-{S}pecific {A}ttribute {C}ontrol in {T}2{I} {M}odels by {I}dentifying {S}emantic {D}irections},
     author = {Baumann, Stefan Andreas and Krause, Felix and Neumayr, Michael and Stracke, Nick and Hu, Vincent Tao and Ommer, Björn},
     year = {2025},
     note = {Prompt Editing in T2I models},
     booktitle = {CVPR},
     repostar = {CompVis/attribute-control}
   }

2. MaskFlow: Discrete Flows for Flexible and Efficient Long Video Generation

   Michael Fuest , Vincent Tao Hu , and Björn Ommer

   In Arxiv , 2025

   Bib PDF Code Website

   @inproceedings{maskflow,
     title = {MaskFlow: Discrete Flows for Flexible and Efficient Long Video Generation},
     author = {Fuest, Michael and Hu, Vincent Tao and Ommer, Björn},
     year = {2025},
     booktitle = {Arxiv},
     preview1111 = {./mask.jpg},
     repostar = {CompVis/maskflow}
   }

3. ToddlerDiffusion: Flash Interpretable Controllable Diffusion Model

   Eslam Mohamed BAKR , Liangbing Zhao , Vincent Tao Hu , Matthieu Cord , Patrick Perez , and Mohamed Elhoseiny

   In ICLR , 2025

   Bib PDF Website

   @inproceedings{ToddlerDiffusion,
     title = {ToddlerDiffusion: Flash Interpretable Controllable Diffusion Model},
     author = {BAKR, Eslam Mohamed and Zhao, Liangbing and Hu, Vincent Tao and Cord, Matthieu and Perez, Patrick and Elhoseiny, Mohamed},
     year = {2025},
     booktitle = {ICLR},
     repostar = {toddlerdiffusion/code}
   }

4. DepthFM: Fast Monocular Depth Estimation with Flow Matching

   Ming Gui , Johannes S. Fischer , Ulrich Prestel , Pingchuan Ma , Dmytro Kotovenko , Olga Grebenkova , Stefan A. Baumann , Vincent Tao Hu , and Björn Ommer

   In AAAI , 2025

   An exploration of flow matching for blazing fast and zero-shot depth estimation

   Bib PDF Code Website Oral

   @inproceedings{depthfm,
     title = {DepthFM: Fast Monocular Depth Estimation with Flow Matching},
     author = {Gui, Ming and Fischer, Johannes S. and Prestel, Ulrich and Ma, Pingchuan and Kotovenko, Dmytro and Grebenkova, Olga and Baumann, Stefan A. and Hu, Vincent Tao and Ommer, Björn},
     year = {2025},
     note = {An exploration of flow matching for blazing fast and zero-shot depth estimation},
     booktitle = {AAAI},
     highlight = {Oral},
     repostar = {CompVis/depth-fm}
   }

5. Does VLM Classification Benefit from LLM Description Semantics?

   Pingchuan Ma , Lennart Rietdorf , Dmytro Kotovenko , Vincent Tao Hu , and Björn Ommer

   In AAAI , 2025

   PDF Code Website Oral at Workshop
6. TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training

   Felix Krause , Timy Phan , Vincent Tao Hu , and Björn Ommer

   In arxiv , 2025

   PDF Code Website
7. Distillation of Diffusion Features for Semantic Correspondence

   Frank Fundel , Johannes Schusterbauer , Vincent Tao Hu , and Björn Ommer

   In WACV , 2025

   Bib PDF Code Website

   @inproceedings{fundel2025distilldift,
     title = {Distillation of Diffusion Features for Semantic Correspondence},
     author = {Fundel, Frank and Schusterbauer, Johannes and Hu, Vincent Tao and Ommer, Björn},
     year = {2025},
     note = {},
     booktitle = {WACV},
     repostar = {CompVis/DistillDIFT}
   }

2024

1. 

   [MASK] is All You Need

   Vincent Tao Hu , and Björn Ommer

   In Arxiv , 2024

   Bib PDF Code Website

   @inproceedings{hu24mask,
     title = {[MASK] is All You Need},
     author = {Hu, Vincent Tao and Ommer, Björn},
     year = {2024},
     booktitle = {Arxiv},
     repostar = {CompVis/discrete-interpolants}
   }

2. Scaling Image Tokenizers with Grouped Spherical Quantization

   Jiangtao Wang , Zhen Qin , Yifan Zhang , Vincent Tao Hu , Björn Ommer , Rania Briq , and Stefan Kesselheim

   2024

   Bib PDF Code

   @article{wang2024scaling,
     title = {Scaling Image Tokenizers with Grouped Spherical Quantization},
     author = {Wang, Jiangtao and Qin, Zhen and Zhang, Yifan and Hu, Vincent Tao and Ommer, Bj{\"o}rn and Briq, Rania and Kesselheim, Stefan},
     booktitle = {Arxiv},
     year = {2024},
     note = {},
     repostar = {HelmholtzAI-FZJ/flex_gen}
   }

3. Diffusion Models and Representation Learning: A Survey

   Michael Fuest , Pingchuan Ma , Ming Gui , Johannes Fischer , Vincent Tao Hu , and Bjorn Ommer

   In Arxiv , 2024

   The interplay between diffusion models and representation learning

   Bib PDF

   @inproceedings{diffusion_rl_survey,
     title = {Diffusion Models and Representation Learning: A Survey},
     author = {Fuest, Michael and Ma, Pingchuan and Gui, Ming and Fischer, Johannes and Hu, Vincent Tao and Ommer, Bjorn},
     year = {2024},
     note = {The interplay between diffusion models and representation learning},
     booktitle = {Arxiv},
     repostar = {dongzhuoyao/Diffusion-Representation-Learning-Survey-Taxonomy}
   }

4. ZigMa: A DiT-style Zigzag Mamba Diffusion Model

   Vincent Tao Hu , Stefan Andreas Baumann , Ming Gui , Olga Grebenkova , Pingchuan Ma , Johannes Fischer , and Bjorn Ommer

   In ECCV , 2024

   a DiT-style Mamba-based diffusion models

   Bib PDF Code Website

   @inproceedings{hu2024zigmaa,
     title = {ZigMa: A DiT-style Zigzag Mamba Diffusion Model},
     author = {Hu, Vincent Tao and Baumann, Stefan Andreas and Gui, Ming and Grebenkova, Olga and Ma, Pingchuan and Fischer, Johannes and Ommer, Bjorn},
     year = {2024},
     note = {a DiT-style Mamba-based diffusion models },
     booktitle = {ECCV},
     repostar = {CompVis/zigma}
   }

5. Boosting Latent Diffusion with Flow Matching

   Johannes S. Fischer , Ming Gui , Pingchuan Ma , Nick Stracke , Stefan A. Baumann , Vincent Tao Hu , and Bjorn Ommer

   In ECCV , 2024

   flow matching for super-resolution

   Bib PDF Code Website Oral

   @inproceedings{fischer2023boosting,
     title = {Boosting Latent Diffusion with Flow Matching},
     author = {Fischer, Johannes S. and Gui, Ming and Ma, Pingchuan and Stracke, Nick and Baumann, Stefan A. and Hu, Vincent Tao and Ommer, Bjorn},
     year = {2024},
     note = {flow matching for super-resolution},
     booktitle = {ECCV},
     highlight = {Oral},
     repostar = {CompVis/fm-boosting}
   }

6. Guided Flow Vision Transformer from Self-Supervised Diffusion Features

   Vincent Tao Hu , Yunlu Chen , Mathilde Caron , Yuki M. Asano , Cees G.M. Snoek , and Björn Ommer

   In Arxiv , 2024

   Bib PDF Code Website

   @inproceedings{sgfm,
     title = {Guided Flow Vision Transformer from Self-Supervised Diffusion Features},
     author = {Hu, Vincent Tao and Chen, Yunlu and Caron, Mathilde and Asano, Yuki M. and Snoek, Cees G.M. and Ommer, Björn},
     year = {2024},
     note = {},
     booktitle = {Arxiv},
     repostar = {dongzhuoyao/sgfm}
   }

7. Motion Flow Matching for Human Motion Synthesis and Editing

   Vincent Tao Hu , Wenzhe Yin , Pingchuan Ma , Yunlu Chen , Basura Fernando , Yuki M. Asano , Efstratios Gavves , Pascal Mettes , Björn Ommer , and Cees G.M. Snoek

   In Arxiv , 2024

   Bib PDF Code Website

   @inproceedings{motionfm,
     title = {Motion Flow Matching for Human Motion Synthesis and Editing},
     author = {Hu, Vincent Tao and Yin, Wenzhe and Ma, Pingchuan and Chen, Yunlu and Fernando, Basura and Asano, Yuki M. and Gavves, Efstratios and Mettes, Pascal and Ommer, Björn and Snoek, Cees G.M.},
     year = {2024},
     note1 = {},
     booktitle = {Arxiv},
     repostar = {dongzhuoyao/motionfm}
   }

8. Training Class-Imbalanced Diffusion Model Via Overlap Optimization

   Divin Yan , Lu Qi , Vincent Tao Hu , Ming-Hsuan Yang , and Meng Tang

   In arxiv , 2024

   Bib PDF

   @inproceedings{constrastivediffusion,
     title = {Training Class-Imbalanced Diffusion Model Via Overlap Optimization},
     author = {Yan, Divin and Qi, Lu and Hu, Vincent Tao and Yang, Ming-Hsuan and Tang, Meng},
     year = {2024},
     note = {},
     booktitle = {arxiv},
   }

9. 

   Latent Space Editing in Transformer-based Flow Matching

   Vincent Tao Hu , David W Zhang , Pascal Mettes , Meng Tang , Deli Zhao , and Cees G.M. Snoek

   In AAAI 2024. Also appear in ICML 2023 Workshop, New Frontiers in Learning, Control, and Dynamical Systems , 2024

   Bib PDF Code Poster Website

   @inproceedings{hulfm,
     title = {Latent Space Editing in Transformer-based Flow Matching},
     author = {Hu, Vincent Tao and Zhang, David W and Mettes, Pascal and Tang, Meng and Zhao, Deli and Snoek, Cees G.M.},
     year = {2024},
     note = {},
     booktitle = {AAAI 2024. Also appear in ICML 2023 Workshop, New Frontiers in Learning, Control, and Dynamical Systems},
     repostar = {dongzhuoyao/uspace}
   }

10. 

    Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation

    Jacob Schnell , Jieke Wang , Lu Qi , Vincent Tao Hu , and Meng Tang

    In SyntaGen CVPR workshop , 2024

    Explore diffusion model for data augmention in segmentation task.

    Bib PDF

    @inproceedings{hu_fsinr,
      title = {Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation},
      author = {Schnell, Jacob and Wang, Jieke and Qi, Lu and Hu, Vincent Tao and Tang, Meng},
      year = {2024},
      note = {Explore diffusion model for data augmention in segmentation task.},
      booktitle = {SyntaGen CVPR workshop},
      repostar = {mengtang-lab/scribblegen}
    }

11. 

    Flow Matching for Conditional Text Generation in a Few Sampling Steps

    Vincent Tao Hu , Di Wu , Yuki M. Asano , Pascal Mettes , Basura Fernando , Björn Ommer , and Cees G.M. Snoek

    In EACL , 2024

    Flow Matching for text generation

    Bib PDF Code Website

    @inproceedings{huflowseq,
      title = {Flow Matching for Conditional Text Generation in a Few Sampling Steps},
      author = {Hu, Vincent Tao and Wu, Di and Asano, Yuki M. and Mettes, Pascal and Fernando, Basura and Ommer, Björn and Snoek, Cees G.M.},
      year = {2024},
      booktitle = {EACL},
      note = {Flow Matching for text generation},
      selectedddd = {true},
      repostar = {dongzhuoyao/flowseq}
    }

2023

1. 

   On the Few-Shot Generalization of Learning on Implicit Neural Representations

   Vincent Tao Hu , David W Zhang , Yunlu Chen , Teng Long , Yuki M. Asano , Pascal Mettes , Efstratios Gavves , Basura Fernando , and Cees G.M. Snoek

   In ICCV NeRF4ADR Workshop , 2023

   Explore few-shot generalization of INR on images.

   Bib

   @inproceedings{hu_fsins,
     title = {On the Few-Shot Generalization of Learning on Implicit Neural Representations},
     author = {Hu, Vincent Tao and Zhang, David W and Chen, Yunlu and Long, Teng and Asano, Yuki M. and Mettes, Pascal and Gavves, Efstratios and Fernando, Basura and Snoek, Cees G.M.},
     year = {2023},
     note = {Explore few-shot generalization of INR on images.},
     booktitle = {ICCV NeRF4ADR Workshop},
   }

2. Query by Activity Video in the Wild

   Vincent Tao Hu , William Thong , Pascal Mettes , and Cees G.M. Snoek

   In ICIP , 2023

   Few-shot video retrieval

   Bib PDF Code

   @inproceedings{huvideoretrieval,
     title = {Query by Activity Video in the Wild},
     author = {Hu, Vincent Tao and Thong, William and Mettes, Pascal and Snoek, Cees G.M.},
     booktitle = {ICIP},
     year = {2023},
     note = {Few-shot video retrieval},
   }

3. 

   Self-Guided Diffusion Models

   Tao Hu* , David W Zhang* , Yuki M. Asano , Gertjan J. Burghouts , and Cees G.M. Snoek

   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.

   Bib PDF Code Website

   @inproceedings{hu2022selfguided,
     title = {Self-Guided Diffusion Models},
     author = {Hu*, Tao and Zhang*, David W and Asano, Yuki M. and Burghouts, Gertjan J. and Snoek, Cees G.M.},
     year = {2023},
     booktitle = {CVPR},
     note = {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.},
     repostar = {dongzhuoyao/self-guided-diffusion-models}
   }

2021

1. 

   Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting

   Martine Toering , Ioannis Gatopoulos , Maarten Stol , and Tao Hu

   In WACV , 2021

   Improve video representation by constrasting Prototypical features.

   Bib PDF Code

   @inproceedings{toering2022self,
     title = {Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting},
     author = {Toering, Martine and Gatopoulos, Ioannis and Stol, Maarten and Hu, Tao},
     booktitle = {WACV},
     year = {2021},
     note = {Improve video representation by constrasting Prototypical features.},
     repostar = {martinetoering/ViCC}
   }

2020

1. 

   Localizing the Common Action Among a Few Videos

   Pengwan Yang* , Tao Hu* , Pascal Mettes , and Cees G.M. Snoek

   In European Conference on Computer Vision(ECCV) , 2020

   Localizing the temporal extent of an action in a long untrimmed video by attention techniques.

   Bib PDF Code

   @inproceedings{YangECCV20,
     author = {Yang*, Pengwan and Hu*, Tao and Mettes, Pascal and Snoek, Cees G.M.},
     title = {Localizing the Common Action Among a Few Videos},
     booktitle = {European Conference on Computer Vision(ECCV)},
     year = {2020},
     note = {Localizing the temporal extent of an action in a long untrimmed video by attention techniques.},
     repostar = {PengWan-Yang/commonLocalization}
   }

2. 

   Pointmixup: Augmentation for point clouds

   Yunlu Chen* , Tao Hu* , Efstratios Gavves , Thomas Mensink , Pascal Mettes , Pengwan Yang , and Cees G.M. Snoek

   In European Conference on Computer Vision(ECCV) , 2020

   A simple augmentation method based on MixUp to boost the performance on related tasks of point cloud.

   Bib PDF Code Spotlight

   @inproceedings{chen2020pointmixup,
     title = {Pointmixup: Augmentation for point clouds},
     author = {Chen*, Yunlu and Hu*, Tao and Gavves, Efstratios and Mensink, Thomas and Mettes, Pascal and Yang, Pengwan and Snoek, Cees G.M.},
     booktitle = {European Conference on Computer Vision(ECCV)},
     highlight = {Spotlight},
     year = {2020},
     note = {A simple augmentation method based on MixUp to boost the performance on related tasks of point cloud.},
     repostar = {yunlu-chen/PointMixup}
   }

3. Interactivity proposals for surveillance videos

   Shuo Chen , Pascal Mettes , Tao Hu , and Cees G.M. Snoek

   In International Conference on Multimedia Retrieval(ICMR) , 2020

   Bib PDF Code Oral

   @inproceedings{chen2020interactivity,
     title = {Interactivity proposals for surveillance videos},
     author = {Chen, Shuo and Mettes, Pascal and Hu, Tao and Snoek, Cees G.M.},
     booktitle = {International Conference on Multimedia Retrieval(ICMR)},
     highlight = {Oral},
     year = {2020},
   }

2019

1. 

   Attention-based Multi-Context Guiding for Few-Shot Semantic Segmentation

   Tao Hu , Pengwan Yang , Chiliang Zhang , Gang Yu , Yadong Mu , and Cees G.M. Snoek

   In AAAI , 2019

   Solve the few-shot segmentation problem by applying attention in multi-scales.

   Bib PDF Code Poster Spotlight

   @inproceedings{tao2018fss,
     title = {Attention-based Multi-Context Guiding for Few-Shot Semantic Segmentation},
     author = {Hu, Tao and Yang, Pengwan and Zhang, Chiliang and Yu, Gang and Mu, Yadong and Snoek, Cees G.M.},
     booktitle = {AAAI},
     highlight = {Spotlight},
     year = {2019},
     note = {Solve the few-shot segmentation problem by applying attention in multi-scales.},
   }

2. 

   SILCO: Show a Few Images, Localize the Common Object

   Tao Hu , Pascal Mettes , Jia-Hong Huang , and Cees G.M. Snoek

   In International Conference on Computer Vision(ICCV) , 2019

   Design a graph network and apply attention on them to solve the problem of common object localization.

   Bib PDF Code Poster Website

   @inproceedings{silco2019,
     title = {SILCO: Show a Few Images, Localize the Common Object},
     author = {Hu, Tao and Mettes, Pascal and Huang, Jia-Hong and Snoek, Cees G.M.},
     booktitle = {International Conference on Computer Vision(ICCV)},
     year = {2019},
     note = {Design a graph network and apply attention on them to solve the problem of common object localization.},
     repostar = {dongzhuoyao/silco_}
   }

2018

1. Dense In Dense: Training Segmentation from Scratch

   Tao Hu

   In Asian Conference on Computer Vision(ACCV) , 2018

   Bib

   @inproceedings{hu2018dense,
     title = {Dense In Dense: Training Segmentation from Scratch},
     author = {Hu, Tao},
     booktitle = {Asian Conference on Computer Vision(ACCV)},
     year = {2018},
   }

2. Sobel heuristic kernel for aerial semantic segmentation

   Tao Hu , Yao Wang , Yisong Chen , Peng Lu , and Heng Wang

   In IEEE International Conference on Image Processing (ICIP) , 2018

   Bib

   @inproceedings{hu2018sobel,
     title = {Sobel heuristic kernel for aerial semantic segmentation},
     author = {Hu, Tao and Wang, Yao and Chen, Yisong and Lu, Peng and Wang, Heng},
     booktitle = {IEEE International Conference on Image Processing (ICIP)},
     year = {2018},
   }

3. Accelerating convolutional neural networks with dynamic channel pruning

   Chiliang Zhang , Tao Hu , Yingda Guan , and Zuochang Ye

   In Data Compression Conference (DCC) , 2018

   Bib

   @inproceedings{chiliang2019accelerating,
     title = {Accelerating convolutional neural networks with dynamic channel pruning},
     author = {Zhang, Chiliang and Hu, Tao and Guan, Yingda and Ye, Zuochang},
     booktitle = {Data Compression Conference (DCC)},
     year = {2018},
   }