Tao Hu

@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}
}

@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}
}

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

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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},
}

@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}
}

@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}
}

@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}
}

@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}
}