@misc{yan2026consistency,
  title        = {Consistency in Diffusion-Based Visual Generation: A Survey},
  author       = {Yan, Song and Zhai, Wei and Wang, Chenfeng and Li, Ruixuan and Yang, Zhangping and Cai, Yancheng and Zhang, Tao and Wang, Ling and Lan, Yunwei and He, Yujie and Cao, Yang and Li, Min and Zha, Zheng-Jun},
  year         = {2026},
  doi          = {10.20944/preprints202606.0870.v1},
  url          = {https://www.preprints.org/manuscript/202606.0870/v1},
  note         = {Preprints}
}

@inproceedings{hrsbench,
  title     = {{HRS-Bench}: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models},
  author    = {Bakr, Eslam Mohamed and Sun, Pengzhan and Shen, Xiaoqian and Khan, Faizan Farooq and Li, Li Erran and Elhoseiny, Mohamed},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages     = {20041--20053},
  year      = {2023}
}

@inproceedings{editbench,
  title     = {Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting},
  author    = {Wang, Su and Saharia, Chitwan and Montgomery, Ceslee and Pont-Tuset, Jordi and Noy, Shai and Pellegrini, Stefano and Onoe, Yasumasa and Laszlo, Sarah and Fleet, David J. and Soricut, Radu and Baldridge, Jason and Norouzi, Mohammad and Anderson, Peter and Chan, William},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages     = {18359--18369},
  year      = {2023}
}

@inproceedings{magicbrush,
  title     = {MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing},
  author    = {Zhang, Kai and Mo, Lingbo and Chen, Wenhu and Sun, Huan and Su, Yu},
  booktitle = {Advances in Neural Information Processing Systems},
  year      = {2023}
}

@inproceedings{vbench,
  title     = {{VBench}: Comprehensive Benchmark Suite for Video Generative Models},
  author    = {Huang, Ziqi and He, Yinan and Yu, Jiashuo and Zhang, Fan and Si, Chenyang and Jiang, Yuming and Zhang, Yuanhan and Wu, Tianxing and Jin, Qingyang and Chanpaisit, Nattapol and Wang, Yaohui and Chen, Xinyuan and Wang, Limin and Lin, Dahua and Qiao, Yu and Liu, Ziwei},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages     = {21807--21818},
  year      = {2024}
}

@inproceedings{evalcrafter,
  title     = {EvalCrafter: Benchmarking and Evaluating Large Video Generation Models},
  author    = {Liu, Yaofang and Cun, Xiaodong and Liu, Xuebo and Wang, Xintao and Zhang, Yong and Chen, Haoxin and Liu, Yang and Zeng, Tieyong and Chan, Raymond and Shan, Ying},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision},
  pages     = {22139--22149},
  year      = {2024}
}

@inproceedings{videophy,
  title     = {VideoPhy: Evaluating Physical Commonsense for Video Generation},
  author    = {Bansal, Hritik and Lin, Zongyu and Xie, Tianyi and Zong, Zeshun and Yarom, Michal and Bitton, Yonatan and Jiang, Chenfanfu and Sun, Yizhou and Chang, Kai-Wei and Grover, Aditya},
  booktitle = {International Conference on Learning Representations},
  year      = {2025}
}

@inproceedings{physics_iq_wacv2026,
  title     = {Do Generative Video Models Understand Physical Principles?},
  author    = {Motamed, Saman and Culp, Laura and Swersky, Kevin and Jaini, Priyank and Geirhos, Robert},
  booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2026}
}