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

@inproceedings{cvpr2023_imagebind_21212,
  title = {{ImageBind: One Embedding Space To Bind Them All}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23114},
}

@inproceedings{cvpr2022_flava_18818,
  title = {{FLAVA: A Foundational Language and Vision Alignment Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_vision_20185,
  title = {{Vision-Language Pre-Training With Triple Contrastive Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_learning_17332,
  title = {{Learning the Best Pooling Strategy for Visual Semantic Embedding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{icml2022_ofa_40907,
  title = {{OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17835},
}

@inproceedings{cvpr2020_bi_15194,
  title = {{Bi-Directional Relationship Inferring Network for Referring Image Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2023_cvt_20558,
  title = {{CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition With Variational Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21450},
}

@inproceedings{cvpr2022_cots_18424,
  title = {{COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2023_bridgetower_3200,
  title = {{BridgeTower: Building Bridges between Encoders in Vision-Language Representation Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26263},
}

@inproceedings{cvpr2022_multi_19385,
  title = {{Multi-Modal Alignment Using Representation Codebook}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_fame_20957,
  title = {{FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23158},
}

@inproceedings{cvpr2023_clover_20592,
  title = {{Clover: Towards a Unified Video-Language Alignment and Fusion Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22766},
}

@inproceedings{aaai2020_visual_103174,
  title = {{Visual Agreement Regularized Training for Multi-Modal Machine Translation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6484},
}

@inproceedings{aaai2018_cross_106029,
  title = {{Cross-Lingual Propagation for Deep Sentiment Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12071},
}

@inproceedings{cvpr2023_revisiting_22056,
  title = {{Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22172},
}

@inproceedings{cvpr2021_learning_17318,
  title = {{Learning To Segment Actions From Visual and Language Instructions via Differentiable Weak Sequence Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2018_learning_105879,
  title = {{Learning Multi-Modal Word Representation Grounded in Visual Context}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11939},
}

@inproceedings{aaai2023_efficient_3553,
  title = {{Efficient Image Captioning for Edge Devices}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25359},
}

@inproceedings{cvpr2023_exif_20880,
  title = {{EXIF As Language: Learning Cross-Modal Associations Between Images and Camera Metadata}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22183},
}

@inproceedings{iclr2023_masked_32776,
  title = {{Masked Vision and Language Modeling for Multi-modal Representation Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11764},
}

@inproceedings{aaai2024_conditional_5465,
  title = {{Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29937},
}

@inproceedings{cvpr2024_language_23926,
  title = {{Language-guided Image Reflection Separation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31159},
}

@inproceedings{cvpr2025_align_25467,
  title = {{Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model Enhancement}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33163},
}

@inproceedings{aaai2025_dusss_8820,
  title = {{DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image Segmentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32674},
}

@inproceedings{aaai2025_protclip_10389,
  title = {{ProtCLIP: Function-Informed Protein Multi-Modal Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34456},
}

@inproceedings{neurips2024_procedure_74668,
  title = {{Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/92928},
}

@inproceedings{aaai2024_aligner_5158,
  title = {{Aligner²: Enhancing Joint Multiple Intent Detection and Slot Filling via Adjustive and Forced Cross-Task Alignment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29952},
}

@inproceedings{aaai2024_cross_5530,
  title = {{Cross-Modal Match for Language Conditioned 3D Object Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28566},
}

@inproceedings{aaai2024_visual_7780,
  title = {{Visual Language – Let the Product Say What You Want}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30583},
}

@inproceedings{cvpr2024_saco_24735,
  title = {{SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30034},
}

@inproceedings{aaai2024_timix_7564,
  title = {{TiMix: Text-Aware Image Mixing for Effective Vision-Language Pre-training}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28025},
}

@inproceedings{aaai2025_decider_8597,
  title = {{DECIDER: Difference-aware Contrastive Diffusion Model with Adversarial Perturbations for Image Change Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33158},
}

@inproceedings{cvpr2025_dh_25822,
  title = {{DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32951},
}

@inproceedings{neurips2024_seeing_71900,
  title = {{Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95404},
}

@inproceedings{neurips2025_guiding_78911,
  title = {{Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=jZs26lJ0pl},
}

@inproceedings{cvpr2025_incorporating_26620,
  title = {{Incorporating Dense Knowledge Alignment into Unified Multimodal Representation Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33799},
}

@inproceedings{iclr2024_bridging_35136,
  title = {{Bridging Vision and Language Spaces with Assignment Prediction}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17937},
}

@inproceedings{icml2024_libra_43898,
  title = {{Libra: Building Decoupled Vision System on Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34554},
}

@inproceedings{icml2025_vision_46220,
  title = {{Vision-Language Models Create Cross-Modal Task Representations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46340},
}

@inproceedings{icml2025_sae_47346,
  title = {{SAE-V: Interpreting Multimodal Models for Enhanced Alignment}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45246},
}