% Key papers for Adapting VLMs for zero-shot classification (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2022_simvlm_31079,
  title = {{SimVLM: Simple Visual Language Model Pretraining with Weak Supervision}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6262},
}

@inproceedings{aaai2024_anomalygpt_5193,
  title = {{AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27963},
}

@inproceedings{cvpr2024_vila_25185,
  title = {{VILA: On Pre-training for Visual Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30868},
}

@inproceedings{cvpr2023_bidirectional_20476,
  title = {{Bidirectional Cross-Modal Knowledge Exploration for Video Recognition With Pre-Trained Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21577},
}

@inproceedings{cvpr2024_adapting_22722,
  title = {{Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29250},
}

@inproceedings{cvpr2023_visual_22539,
  title = {{Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23021},
}

@inproceedings{aaai2024_skyscript_7356,
  title = {{SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28393},
}

@inproceedings{neurips2021_multimodal_62418,
  title = {{Multimodal Few-Shot Learning with Frozen Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27148},
}

@inproceedings{cvpr2022_uni_20120,
  title = {{Uni-Perceiver: Pre-Training Unified Architecture for Generic Perception for Zero-Shot and Few-Shot Tasks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{iclr2023_visual_33050,
  title = {{Visual Classification via Description from Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11733},
}

@inproceedings{cvpr2024_grounding_23646,
  title = {{Grounding Everything: Emerging Localization Properties in Vision-Language Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29967},
}

@inproceedings{cvpr2023_filtering_20996,
  title = {{Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22259},
}

@inproceedings{cvpr2023_teaching_22315,
  title = {{Teaching Structured Vision \& Language Concepts to Vision \& Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22718},
}

@inproceedings{cvpr2024_dual_23279,
  title = {{Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31048},
}

@inproceedings{cvpr2022_towards_20047,
  title = {{Towards General Purpose Vision Systems: An End-to-End Task-Agnostic Vision-Language Architecture}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_position_21900,
  title = {{Position-Guided Text Prompt for Vision-Language Pre-Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22379},
}

@inproceedings{cvpr2024_improved_23767,
  title = {{Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31839},
}

@inproceedings{cvpr2024_visual_25252,
  title = {{Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30648},
}

@inproceedings{cvpr2023_dear_20716,
  title = {{DeAR: Debiasing Vision-Language Models With Additive Residuals}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21167},
}

@inproceedings{cvpr2024_the_25009,
  title = {{The Neglected Tails in Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30229},
}

@inproceedings{cvpr2024_cplip_22931,
  title = {{CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30577},
}

@inproceedings{cvpr2025_seeground_27602,
  title = {{SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32903},
}

@inproceedings{cvpr2025_skysense_27691,
  title = {{SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33431},
}

@inproceedings{aaai2024_groundvlp_6166,
  title = {{GroundVLP: Harnessing Zero-Shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28278},
}

@inproceedings{cvpr2024_decomposing_23123,
  title = {{Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30353},
}

@inproceedings{cvpr2024_large_23929,
  title = {{Large Language Models are Good Prompt Learners for Low-Shot Image Classification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30926},
}

@inproceedings{cvpr2025_mamba_26908,
  title = {{Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32595},
}

@inproceedings{aaai2025_zero_11325,
  title = {{Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32971},
}

@inproceedings{cvpr2024_label_23912,
  title = {{Label Propagation for Zero-shot Classification with Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29452},
}

@inproceedings{iclr2024_fine_33863,
  title = {{Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19212},
}

@inproceedings{neurips2024_revisiting_70364,
  title = {{Revisiting Few-Shot Object Detection with Vision-Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97860},
}