% Key papers for Vision-language pretraining (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2022_beit_31690,
  title = {{BEiT: BERT Pre-Training of Image Transformers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6323},
}

@inproceedings{aaai2020_unified_103898,
  title = {{Unified Vision-Language Pre-Training for Image Captioning and VQA}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/7005},
}

@inproceedings{neurips2021_align_62095,
  title = {{Align before Fuse: Vision and Language Representation Learning with Momentum Distillation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28238},
}

@inproceedings{iclr2020_vl_29716,
  title = {{VL-BERT: Pre-training of Generic Visual-Linguistic Representations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=SygXPaEYvH},
}

@inproceedings{aaai2020_unicoder_103688,
  title = {{Unicoder-VL: A Universal Encoder for Vision and Language by Cross-Modal Pre-Training}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6795},
}

@inproceedings{neurips2017_learning_56437,
  title = {{Learning multiple visual domains with residual adapters}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8847},
}

@inproceedings{cvpr2023_image_21211,
  title = {{Image as a Foreign Language: BEiT Pretraining for Vision and Vision-Language Tasks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21115},
}

@inproceedings{icml2021_vilt_40104,
  title = {{ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9491},
}

@inproceedings{cvpr2023_autoregressive_20421,
  title = {{Autoregressive Visual Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22452},
}

@inproceedings{cvpr2022_an_18288,
  title = {{An Empirical Study of Training End-to-End Vision-and-Language Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{icml2022_data2vec_41365,
  title = {{data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16643},
}

@inproceedings{cvpr2023_explicit_20940,
  title = {{Explicit Visual Prompting for Low-Level Structure Segmentations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21917},
}

@inproceedings{cvpr2023_learning_21399,
  title = {{Learning To Exploit Temporal Structure for Biomedical Vision-Language Processing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21900},
}

@inproceedings{iclr2023_pali_33125,
  title = {{PaLI: A Jointly-Scaled Multilingual Language-Image Model}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11441},
}

@inproceedings{cvpr2022_visualgpt_20190,
  title = {{VisualGPT: Data-Efficient Adaptation of Pretrained Language Models for Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_merlot_19289,
  title = {{MERLOT Reserve: Neural Script Knowledge Through Vision and Language and Sound}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{iclr2023_unified_32267,
  title = {{UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11770},
}

@inproceedings{cvpr2024_sequential_24805,
  title = {{Sequential Modeling Enables Scalable Learning for Large Vision Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30779},
}

@inproceedings{iclr2020_neural_29379,
  title = {{Neural Machine Translation with Universal Visual Representation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=Byl8hhNYPS},
}

@inproceedings{cvpr2023_lavender_21307,
  title = {{LAVENDER: Unifying Video-Language Understanding As Masked Language Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22799},
}

@inproceedings{cvpr2024_rethinking_24638,
  title = {{Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31579},
}

@inproceedings{cvpr2024_fairclip_23448,
  title = {{FairCLIP: Harnessing Fairness in Vision-Language Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31879},
}

@inproceedings{cvpr2025_janus_26664,
  title = {{Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35230},
}

@inproceedings{cvpr2024_instruct_23820,
  title = {{Instruct-Imagen: Image Generation with Multi-modal Instruction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30449},
}

@inproceedings{cvpr2024_autoad_22800,
  title = {{AutoAD III: The Prequel - Back to the Pixels}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29382},
}

@inproceedings{cvpr2025_tokenflow_27880,
  title = {{TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33362},
}

@inproceedings{cvpr2025_janusflow_26665,
  title = {{JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34669},
}

@inproceedings{aaai2025_from_9240,
  title = {{From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32858},
}

@inproceedings{cvpr2025_dynamic_26047,
  title = {{Dynamic Updates for Language Adaptation in Visual-Language Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34874},
}

@inproceedings{cvpr2024_beyond_22835,
  title = {{Beyond Text: Frozen Large Language Models in Visual Signal Comprehension}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30250},
}

@inproceedings{neurips2024_4m_74026,
  title = {{4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93496},
}

@inproceedings{aaai2024_eve_5787,
  title = {{EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27872},
}

@inproceedings{cvpr2025_vision_28115,
  title = {{Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32941},
}

@inproceedings{neurips2025_show_75386,
  title = {{Show-o2: Improved Native Unified Multimodal Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=7VMg7Jb7AL},
}

@inproceedings{cvpr2024_a_22671,
  title = {{A Vision Check-up for Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31073},
}

@inproceedings{cvpr2024_syncmask_24926,
  title = {{SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29248},
}

@inproceedings{cvpr2024_codebook_22986,
  title = {{Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29565},
}

@inproceedings{iclr2024_frozen_35446,
  title = {{Frozen Transformers in Language Models Are Effective Visual Encoder Layers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17627},
}

@inproceedings{cvpr2024_towards_25052,
  title = {{Towards More Unified In-context Visual Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31793},
}