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

@inproceedings{icml2021_scaling_39929,
  title = {{Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/10657},
}

@inproceedings{neurips2022_laion_64694,
  title = {{LAION-5B: An open large-scale dataset for training next generation image-text models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55659},
}

@inproceedings{cvpr2022_unified_20125,
  title = {{Unified Contrastive Learning in Image-Text-Label Space}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2018_stack_104007,
  title = {{Stack-Captioning: Coarse-to-Fine Learning for Image Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12266},
}

@inproceedings{cvpr2022_general_18914,
  title = {{General Facial Representation Learning in a Visual-Linguistic Manner}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_maskclip_21529,
  title = {{MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23245},
}

@inproceedings{cvpr2023_prompt_21933,
  title = {{Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22883},
}

@inproceedings{cvpr2023_smallcap_22225,
  title = {{SmallCap: Lightweight Image Captioning Prompted With Retrieval Augmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21303},
}

@inproceedings{neurips2023_datacomp_68836,
  title = {{DataComp: In search of the next generation of multimodal datasets}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73525},
}

@inproceedings{neurips2022_multimodal_64919,
  title = {{Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54648},
}

@inproceedings{neurips2023_quilt_67951,
  title = {{Quilt-1M: One Million Image-Text Pairs for Histopathology}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73608},
}

@inproceedings{cvpr2022_robust_19750,
  title = {{Robust Cross-Modal Representation Learning With Progressive Self-Distillation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_mlip_24064,
  title = {{MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29392},
}

@inproceedings{iclr2023_linearly_32149,
  title = {{Linearly Mapping from Image to Text Space}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10815},
}

@inproceedings{cvpr2024_learning_23972,
  title = {{Learning Vision from Models Rivals Learning Vision from Data}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29614},
}

@inproceedings{neurips2022_contrastive_63871,
  title = {{Contrastive Language-Image Pre-Training with Knowledge Graphs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53541},
}

@inproceedings{cvpr2024_a_22658,
  title = {{A Simple Recipe for Language-guided Domain Generalized Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29196},
}

@inproceedings{cvpr2024_capsfusion_22951,
  title = {{CapsFusion: Rethinking Image-Text Data at Scale}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29637},
}

@inproceedings{cvpr2025_multimodal_27038,
  title = {{Multimodal Autoregressive Pre-training of Large Vision Encoders}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34237},
}

@inproceedings{cvpr2023_learning_21417,
  title = {{Learning Visual Representations via Language-Guided Sampling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23019},
}

@inproceedings{cvpr2024_image_23756,
  title = {{Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29659},
}

@inproceedings{aaai2024_bridging_5317,
  title = {{Bridging the Semantic Latent Space between Brain and Machine: Similarity Is All You Need}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29009},
}

@inproceedings{cvpr2024_tamm_24935,
  title = {{TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29780},
}

@inproceedings{iclr2024_tag2text_35605,
  title = {{Tag2Text: Guiding Vision-Language Model via Image Tagging}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17468},
}

@inproceedings{neurips2025_perception_76359,
  title = {{Perception Encoder: The best visual embeddings are not at the output of the network}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=INqBOmwIpG},
}

@inproceedings{cvpr2024_do_23245,
  title = {{Do Vision and Language Encoders Represent the World Similarly?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31676},
}

@inproceedings{cvpr2024_enhancing_23375,
  title = {{Enhancing Vision-Language Pre-training with Rich Supervisions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29766},
}

@inproceedings{cvpr2024_pairaug_24427,
  title = {{PairAug: What Can Augmented Image-Text Pairs Do for Radiology?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30664},
}

@inproceedings{icml2024_scalable_44848,
  title = {{Scalable Pre-training of Large Autoregressive Image Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33604},
}

@inproceedings{cvpr2025_active_25425,
  title = {{Active Data Curation Effectively Distills Large-Scale Multimodal Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35213},
}

@inproceedings{iclr2024_cobit_33744,
  title = {{CoBIT: A Contrastive Bi-directional Image-Text Generation Model}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19331},
}

@inproceedings{iclr2024_t_34577,
  title = {{T-MARS: Improving Visual Representations by Circumventing Text Feature Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18497},
}

@inproceedings{iclr2024_mofi_34398,
  title = {{MOFI: Learning Image Representations from Noisy Entity Annotated Images}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18677},
}

@inproceedings{iclr2025_clibd_82790,
  title = {{CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29009},
}

@inproceedings{cvpr2025_harnessing_26493,
  title = {{Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33930},
}