% Key papers for Compositional text-to-video diffusion (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2023_make_33152,
  title = {{Make-A-Video: Text-to-Video Generation without Text-Video Data}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11001},
}

@inproceedings{cvpr2024_videocrafter2_25228,
  title = {{VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29306},
}

@inproceedings{aaai2018_video_103974,
  title = {{Video Generation From Text}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12233},
}

@inproceedings{iclr2023_cogvideo_33237,
  title = {{CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11213},
}

@inproceedings{iclr2023_phenaki_33337,
  title = {{Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/12256},
}

@inproceedings{cvpr2022_make_19308,
  title = {{Make It Move: Controllable Image-to-Video Generation With Text Descriptions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_celebv_20574,
  title = {{CelebV-Text: A Large-Scale Facial Text-Video Dataset}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22754},
}

@inproceedings{cvpr2024_simda_24821,
  title = {{SimDA: Simple Diffusion Adapter for Efficient Video Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31202},
}

@inproceedings{cvpr2024_videobooth_25226,
  title = {{VideoBooth: Diffusion-based Video Generation with Image Prompts}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30042},
}

@inproceedings{cvpr2025_streamingt2v_27760,
  title = {{StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33995},
}

@inproceedings{iclr2024_controlvideo_33651,
  title = {{ControlVideo: Training-free Controllable Text-to-video Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19424},
}

@inproceedings{neurips2023_learning_68715,
  title = {{Learning Universal Policies via Text-Guided Video Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71128},
}

@inproceedings{cvpr2024_vlogger_25256,
  title = {{Vlogger: Make Your Dream A Vlog}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30553},
}

@inproceedings{iclr2024_language_34955,
  title = {{Language Model Beats Diffusion - Tokenizer is key to visual generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18119},
}

@inproceedings{icml2024_videopoet_44156,
  title = {{VideoPoet: A Large Language Model for Zero-Shot Video Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34296},
}

@inproceedings{cvpr2024_a_22654,
  title = {{A Recipe for Scaling up Text-to-Video Generation with Text-free Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29368},
}

@inproceedings{neurips2024_vidprom_73969,
  title = {{VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97505},
}

@inproceedings{cvpr2025_aigv_25394,
  title = {{AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34887},
}

@inproceedings{cvpr2024_ti2v_24942,
  title = {{TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30978},
}

@inproceedings{cvpr2025_t2v_27799,
  title = {{T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34118},
}

@inproceedings{cvpr2025_one_27142,
  title = {{One-Minute Video Generation with Test-Time Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33506},
}

@inproceedings{neurips2024_evaluation_74242,
  title = {{Evaluation of Text-to-Video Generation Models: A Dynamics Perspective}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93313},
}

@inproceedings{cvpr2025_identity_26582,
  title = {{Identity-Preserving Text-to-Video Generation by Frequency Decomposition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32871},
}

@inproceedings{cvpr2025_phyt2v_27250,
  title = {{PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33052},
}

@inproceedings{neurips2025_videorepa_79338,
  title = {{VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=oHjLfABsK4},
}

@inproceedings{cvpr2025_lingen_26797,
  title = {{LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32499},
}

@inproceedings{neurips2024_omnitokenizer_71395,
  title = {{OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95856},
}