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

@inproceedings{cvpr2024_glamm_23551,
  title = {{GLaMM: Pixel Grounding Large Multimodal Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31094},
}

@inproceedings{cvpr2018_parallel_13457,
  title = {{Parallel Attention: A Unified Framework for Visual Object Discovery Through Dialogs and Queries}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Zhuang_Parallel_Attention_A_CVPR_2018_paper.html},
}

@inproceedings{cvpr2022_shifting_19869,
  title = {{Shifting More Attention to Visual Backbone: Query-Modulated Refinement Networks for End-to-End Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2016_visual_11961,
  title = {{Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{neurips2024_cogvlm_70609,
  title = {{CogVLM: Visual Expert for Pretrained Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96510},
}

@inproceedings{cvpr2021_cyclic_16779,
  title = {{Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{neurips2022_coarse_65970,
  title = {{Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54881},
}

@inproceedings{aaai2023_mner_4117,
  title = {{MNER-QG: An End-to-End MRC Framework for Multimodal Named Entity Recognition with Query Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25971},
}

@inproceedings{cvpr2023_context_20640,
  title = {{Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22858},
}

@inproceedings{cvpr2018_separating_13579,
  title = {{Separating Self-Expression and Visual Content in Hashtag Supervision}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Veit_Separating_Self-Expression_and_CVPR_2018_paper.html},
}

@inproceedings{aaai2024_vision_7774,
  title = {{Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28559},
}

@inproceedings{aaai2021_efficient_501,
  title = {{Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/02720-efficient-object-level-visual-context-modeling-for-multimodal-machine-translation-masking-irrelevant-objects-helps-grounding/},
}

@inproceedings{aaai2019_connecting_103518,
  title = {{Connecting Language to Images: A Progressive Attention-Guided Network for Simultaneous Image Captioning and Language Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4916},
}

@inproceedings{aaai2024_weakly_7794,
  title = {{Weakly Supervised Multimodal Affordance Grounding for Egocentric Images}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28451},
}

@inproceedings{cvpr2024_pixel_24470,
  title = {{Pixel-Aligned Language Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31639},
}

@inproceedings{neurips2023_pop_68882,
  title = {{POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70977},
}

@inproceedings{cvpr2025_beyond_25577,
  title = {{Beyond Human Perception: Understanding Multi-Object World from Monocular View}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34458},
}

@inproceedings{neurips2024_lexicon3d_70355,
  title = {{Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96742},
}

@inproceedings{cvpr2025_asap_25408,
  title = {{ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33251},
}

@inproceedings{cvpr2025_task_27829,
  title = {{Task-aware Cross-modal Feature Refinement Transformer with Large Language Models for Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33672},
}

@inproceedings{aaai2025_idseq_9488,
  title = {{IDseq: Decoupled and Sequentially Detecting and Grounding Multi-Modal Media Manipulation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32029},
}

@inproceedings{cvpr2025_annexe_25401,
  title = {{ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34752},
}

@inproceedings{cvpr2025_dynrefer_26035,
  title = {{DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33204},
}

@inproceedings{iclr2024_neurosymbolic_33603,
  title = {{Neurosymbolic Grounding for Compositional World Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19472},
}

@inproceedings{icml2025_unifying_46693,
  title = {{Unifying 2D and 3D Vision-Language Understanding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45879},
}

@inproceedings{icml2026_referring_55174,
  title = {{Referring Multiple Regions with Large Multimodal Models via Contextual Latent Steering}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=wLE7pnypx2},
}

@inproceedings{neurips2024_mmscan_74611,
  title = {{MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97429},
}

@inproceedings{neurips2025_talk2event_78558,
  title = {{Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=fxERuSBpfQ},
}

@inproceedings{cvpr2026_hammer_97609,
  title = {{HAMMER: Harnessing MLLMs via Cross-Modal Integration for Intention-Driven 3D Affordance Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Yao_HAMMER_Harnessing_MLLMs_via_Cross-Modal_Integration_for_Intention-Driven_3D_Affordance_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_beyond_99488,
  title = {{Beyond Explicit Language: Plug-and-Play Visual-to-Linguistic Modeling Toward General Object Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Lan_Beyond_Explicit_Language_Plug-and-Play_Visual-to-Linguistic_Modeling_Toward_General_Object_Tracking_CVPR_2026_paper.html},
}