% Key papers for CLIP training recipes and data curation (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2022_how_31868,
  title = {{How Much Can CLIP Benefit Vision-and-Language Tasks?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6845},
}

@inproceedings{iclr2022_supervision_31870,
  title = {{Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6406},
}

@inproceedings{aaai2023_calip_3205,
  title = {{CALIP: Zero-Shot Enhancement of CLIP with Parameter-Free Attention}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25152},
}

@inproceedings{aaai2024_an_5180,
  title = {{An Empirical Study of CLIP for Text-Based Person Search}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27801},
}

@inproceedings{cvpr2023_turning_22427,
  title = {{Turning a CLIP Model Into a Scene Text Detector}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21866},
}

@inproceedings{cvpr2023_hoiclip_21119,
  title = {{HOICLIP: Efficient Knowledge Transfer for HOI Detection With Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21598},
}

@inproceedings{neurips2022_cyclip_64512,
  title = {{CyCLIP: Cyclic Contrastive Language-Image Pretraining}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54080},
}

@inproceedings{cvpr2023_clippo_20546,
  title = {{CLIPPO: Image-and-Language Understanding From Pixels Only}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21069},
}

@inproceedings{cvpr2023_ra_21961,
  title = {{RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21186},
}

@inproceedings{neurips2023_improving_68192,
  title = {{Improving CLIP Training with Language Rewrites}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71601},
}

@inproceedings{icml2022_data_40404,
  title = {{Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/18149},
}

@inproceedings{iclr2024_demystifying_33637,
  title = {{Demystifying CLIP Data}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19438},
}

@inproceedings{cvpr2023_non_21715,
  title = {{Non-Contrastive Learning Meets Language-Image Pre-Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22870},
}

@inproceedings{neurips2022_uniclip_66480,
  title = {{UniCLIP: Unified Framework for Contrastive Language-Image Pre-training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54544},
}

@inproceedings{neurips2024_plip_73132,
  title = {{PLIP: Language-Image Pre-training for Person Representation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94298},
}

@inproceedings{cvpr2023_iclip_22602,
  title = {{iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21070},
}

@inproceedings{aaai2025_clip_8347,
  title = {{CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35505},
}

@inproceedings{neurips2024_fineclip_73805,
  title = {{FineCLIP: Self-distilled Region-based CLIP for Better Fine-grained Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93703},
}

@inproceedings{cvpr2024_contrasting_23037,
  title = {{Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29738},
}

@inproceedings{cvpr2025_proker_27301,
  title = {{ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32412},
}

@inproceedings{aaai2024_mining_6644,
  title = {{Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28260},
}

@inproceedings{cvpr2025_finelip_26263,
  title = {{FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32839},
}

@inproceedings{aaai2025_text_10954,
  title = {{Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32534},
}

@inproceedings{neurips2024_tripletclip_72774,
  title = {{TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94621},
}

@inproceedings{cvpr2025_post_27284,
  title = {{Post-pre-training for Modality Alignment in Vision-Language Foundation Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32768},
}

@inproceedings{neurips2025_meta_78053,
  title = {{Meta CLIP 2: A Worldwide Scaling Recipe}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=aYRNINhNGV},
}

@inproceedings{cvpr2025_clip_25652,
  title = {{CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33346},
}

@inproceedings{cvpr2025_smartclip_27694,
  title = {{SmartCLIP: Modular Vision-language Alignment with Identification Guarantees}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34525},
}

@inproceedings{iclr2024_retrieval_34726,
  title = {{Retrieval-Enhanced Contrastive Vision-Text Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18348},
}

@inproceedings{neurips2024_interpreting_73787,
  title = {{Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93719},
}

@inproceedings{neurips2024_cliploss_74062,
  title = {{CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93467},
}

@inproceedings{aaai2025_diffclip_8723,
  title = {{DiffCLIP: Few-shot Language-driven Multimodal Classifier}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34401},
}

@inproceedings{cvpr2025_retaining_27437,
  title = {{Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33339},
}